summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--include/bpf_api.h275
-rw-r--r--include/bpf_elf.h53
-rw-r--r--include/bpf_scm.h77
-rw-r--r--include/bpf_util.h326
-rw-r--r--include/cg_map.h7
-rw-r--r--include/color.h29
-rw-r--r--include/dlfcn.h41
-rw-r--r--include/json_print.h114
-rw-r--r--include/json_writer.h76
-rw-r--r--include/libgenl.h29
-rw-r--r--include/libnetlink.h358
-rw-r--r--include/list.h134
-rw-r--r--include/ll_map.h17
-rw-r--r--include/mnl_utils.h35
-rw-r--r--include/names.h26
-rw-r--r--include/namespace.h65
-rw-r--r--include/netinet/tcp.h231
-rw-r--r--include/rt_names.h47
-rw-r--r--include/rtm_map.h10
-rw-r--r--include/selinux.h10
-rw-r--r--include/uapi/asm-generic/posix_types.h99
-rw-r--r--include/uapi/asm-generic/sockios.h14
-rw-r--r--include/uapi/linux/amt.h62
-rw-r--r--include/uapi/linux/atm.h242
-rw-r--r--include/uapi/linux/atmapi.h30
-rw-r--r--include/uapi/linux/atmarp.h42
-rw-r--r--include/uapi/linux/atmdev.h212
-rw-r--r--include/uapi/linux/atmioc.h42
-rw-r--r--include/uapi/linux/atmsap.h163
-rw-r--r--include/uapi/linux/ax25.h117
-rw-r--r--include/uapi/linux/batman_adv.h704
-rw-r--r--include/uapi/linux/bpf.h7368
-rw-r--r--include/uapi/linux/bpf_common.h57
-rw-r--r--include/uapi/linux/btf.h200
-rw-r--r--include/uapi/linux/can.h289
-rw-r--r--include/uapi/linux/can/netlink.h185
-rw-r--r--include/uapi/linux/can/vxcan.h13
-rw-r--r--include/uapi/linux/capability.h431
-rw-r--r--include/uapi/linux/const.h36
-rw-r--r--include/uapi/linux/dcbnl.h779
-rw-r--r--include/uapi/linux/devlink.h709
-rw-r--r--include/uapi/linux/elf-em.h71
-rw-r--r--include/uapi/linux/fib_rules.h90
-rw-r--r--include/uapi/linux/filter.h90
-rw-r--r--include/uapi/linux/fou.h46
-rw-r--r--include/uapi/linux/gen_stats.h78
-rw-r--r--include/uapi/linux/genetlink.h103
-rw-r--r--include/uapi/linux/hdlc/ioctl.h94
-rw-r--r--include/uapi/linux/icmpv6.h178
-rw-r--r--include/uapi/linux/if.h296
-rw-r--r--include/uapi/linux/if_addr.h77
-rw-r--r--include/uapi/linux/if_addrlabel.h33
-rw-r--r--include/uapi/linux/if_alg.h61
-rw-r--r--include/uapi/linux/if_arp.h165
-rw-r--r--include/uapi/linux/if_bonding.h155
-rw-r--r--include/uapi/linux/if_bridge.h858
-rw-r--r--include/uapi/linux/if_ether.h181
-rw-r--r--include/uapi/linux/if_infiniband.h30
-rw-r--r--include/uapi/linux/if_link.h1956
-rw-r--r--include/uapi/linux/if_macsec.h194
-rw-r--r--include/uapi/linux/if_packet.h319
-rw-r--r--include/uapi/linux/if_tun.h118
-rw-r--r--include/uapi/linux/if_tunnel.h185
-rw-r--r--include/uapi/linux/if_vlan.h66
-rw-r--r--include/uapi/linux/ife.h19
-rw-r--r--include/uapi/linux/ila.h68
-rw-r--r--include/uapi/linux/in.h333
-rw-r--r--include/uapi/linux/in6.h302
-rw-r--r--include/uapi/linux/in_route.h33
-rw-r--r--include/uapi/linux/inet_diag.h239
-rw-r--r--include/uapi/linux/ioam6.h133
-rw-r--r--include/uapi/linux/ioam6_genl.h52
-rw-r--r--include/uapi/linux/ioam6_iptunnel.h58
-rw-r--r--include/uapi/linux/ip.h181
-rw-r--r--include/uapi/linux/ip6_tunnel.h56
-rw-r--r--include/uapi/linux/ipsec.h48
-rw-r--r--include/uapi/linux/kernel.h8
-rw-r--r--include/uapi/linux/l2tp.h203
-rw-r--r--include/uapi/linux/libc-compat.h267
-rw-r--r--include/uapi/linux/limits.h21
-rw-r--r--include/uapi/linux/lwtunnel.h124
-rw-r--r--include/uapi/linux/magic.h105
-rw-r--r--include/uapi/linux/mpls.h77
-rw-r--r--include/uapi/linux/mpls_iptunnel.h31
-rw-r--r--include/uapi/linux/mptcp.h122
-rw-r--r--include/uapi/linux/mptcp_pm.h150
-rw-r--r--include/uapi/linux/neighbour.h224
-rw-r--r--include/uapi/linux/net.h58
-rw-r--r--include/uapi/linux/net_namespace.h26
-rw-r--r--include/uapi/linux/netconf.h30
-rw-r--r--include/uapi/linux/netdevice.h66
-rw-r--r--include/uapi/linux/netfilter.h76
-rw-r--r--include/uapi/linux/netfilter/ipset/ip_set.h312
-rw-r--r--include/uapi/linux/netfilter/x_tables.h186
-rw-r--r--include/uapi/linux/netfilter/xt_set.h94
-rw-r--r--include/uapi/linux/netfilter/xt_tcpudp.h37
-rw-r--r--include/uapi/linux/netfilter_ipv4.h53
-rw-r--r--include/uapi/linux/netfilter_ipv4/ip_tables.h229
-rw-r--r--include/uapi/linux/netfilter_ipv6.h50
-rw-r--r--include/uapi/linux/netfilter_ipv6/ip6_tables.h270
-rw-r--r--include/uapi/linux/netlink.h379
-rw-r--r--include/uapi/linux/netlink_diag.h65
-rw-r--r--include/uapi/linux/nexthop.h104
-rw-r--r--include/uapi/linux/packet_diag.h81
-rw-r--r--include/uapi/linux/param.h7
-rw-r--r--include/uapi/linux/pfkeyv2.h386
-rw-r--r--include/uapi/linux/pkt_cls.h773
-rw-r--r--include/uapi/linux/pkt_sched.h1211
-rw-r--r--include/uapi/linux/posix_types.h38
-rw-r--r--include/uapi/linux/ppp_defs.h165
-rw-r--r--include/uapi/linux/rose.h91
-rw-r--r--include/uapi/linux/rpl.h48
-rw-r--r--include/uapi/linux/rpl_iptunnel.h21
-rw-r--r--include/uapi/linux/rtnetlink.h830
-rw-r--r--include/uapi/linux/sctp.h1220
-rw-r--r--include/uapi/linux/seg6.h55
-rw-r--r--include/uapi/linux/seg6_genl.h33
-rw-r--r--include/uapi/linux/seg6_hmac.h23
-rw-r--r--include/uapi/linux/seg6_iptunnel.h42
-rw-r--r--include/uapi/linux/seg6_local.h137
-rw-r--r--include/uapi/linux/snmp.h362
-rw-r--r--include/uapi/linux/sock_diag.h65
-rw-r--r--include/uapi/linux/socket.h38
-rw-r--r--include/uapi/linux/sockios.h174
-rw-r--r--include/uapi/linux/stddef.h58
-rw-r--r--include/uapi/linux/sysinfo.h25
-rw-r--r--include/uapi/linux/tc_act/tc_bpf.h30
-rw-r--r--include/uapi/linux/tc_act/tc_connmark.h22
-rw-r--r--include/uapi/linux/tc_act/tc_csum.h33
-rw-r--r--include/uapi/linux/tc_act/tc_ct.h44
-rw-r--r--include/uapi/linux/tc_act/tc_ctinfo.h29
-rw-r--r--include/uapi/linux/tc_act/tc_defact.h21
-rw-r--r--include/uapi/linux/tc_act/tc_gact.h33
-rw-r--r--include/uapi/linux/tc_act/tc_gate.h47
-rw-r--r--include/uapi/linux/tc_act/tc_ife.h32
-rw-r--r--include/uapi/linux/tc_act/tc_mirred.h29
-rw-r--r--include/uapi/linux/tc_act/tc_mpls.h34
-rw-r--r--include/uapi/linux/tc_act/tc_nat.h27
-rw-r--r--include/uapi/linux/tc_act/tc_pedit.h70
-rw-r--r--include/uapi/linux/tc_act/tc_sample.h25
-rw-r--r--include/uapi/linux/tc_act/tc_skbedit.h41
-rw-r--r--include/uapi/linux/tc_act/tc_skbmod.h34
-rw-r--r--include/uapi/linux/tc_act/tc_tunnel_key.h95
-rw-r--r--include/uapi/linux/tc_act/tc_vlan.h36
-rw-r--r--include/uapi/linux/tc_ematch/tc_em_cmp.h26
-rw-r--r--include/uapi/linux/tc_ematch/tc_em_ipt.h20
-rw-r--r--include/uapi/linux/tc_ematch/tc_em_meta.h93
-rw-r--r--include/uapi/linux/tc_ematch/tc_em_nbyte.h14
-rw-r--r--include/uapi/linux/tcp.h486
-rw-r--r--include/uapi/linux/tcp_metrics.h61
-rw-r--r--include/uapi/linux/tipc.h315
-rw-r--r--include/uapi/linux/tipc_netlink.h341
-rw-r--r--include/uapi/linux/tipc_sockets_diag.h17
-rw-r--r--include/uapi/linux/tls.h206
-rw-r--r--include/uapi/linux/types.h57
-rw-r--r--include/uapi/linux/udp.h47
-rw-r--r--include/uapi/linux/unix_diag.h61
-rw-r--r--include/uapi/linux/veth.h13
-rw-r--r--include/uapi/linux/virtio_config.h121
-rw-r--r--include/uapi/linux/virtio_ids.h84
-rw-r--r--include/uapi/linux/virtio_net.h409
-rw-r--r--include/uapi/linux/virtio_types.h46
-rw-r--r--include/uapi/linux/vm_sockets_diag.h34
-rw-r--r--include/uapi/linux/wwan.h16
-rw-r--r--include/uapi/linux/xdp_diag.h83
-rw-r--r--include/uapi/linux/xfrm.h569
-rw-r--r--include/utils.h396
-rw-r--r--include/version.h1
-rw-r--r--include/xt-internal.h67
-rw-r--r--include/xtables.h598
170 files changed, 34833 insertions, 0 deletions
diff --git a/include/bpf_api.h b/include/bpf_api.h
new file mode 100644
index 0000000..287f96b
--- /dev/null
+++ b/include/bpf_api.h
@@ -0,0 +1,275 @@
+/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */
+#ifndef __BPF_API__
+#define __BPF_API__
+
+/* Note:
+ *
+ * This file can be included into eBPF kernel programs. It contains
+ * a couple of useful helper functions, map/section ABI (bpf_elf.h),
+ * misc macros and some eBPF specific LLVM built-ins.
+ */
+
+#include <stdint.h>
+
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+
+#include <asm/byteorder.h>
+
+#include "bpf_elf.h"
+
+/** libbpf pin type. */
+enum libbpf_pin_type {
+ LIBBPF_PIN_NONE,
+ /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */
+ LIBBPF_PIN_BY_NAME,
+};
+
+/** Type helper macros. */
+
+#define __uint(name, val) int (*name)[val]
+#define __type(name, val) typeof(val) *name
+#define __array(name, val) typeof(val) *name[]
+
+/** Misc macros. */
+
+#ifndef __stringify
+# define __stringify(X) #X
+#endif
+
+#ifndef __maybe_unused
+# define __maybe_unused __attribute__((__unused__))
+#endif
+
+#ifndef offsetof
+# define offsetof(TYPE, MEMBER) __builtin_offsetof(TYPE, MEMBER)
+#endif
+
+#ifndef likely
+# define likely(X) __builtin_expect(!!(X), 1)
+#endif
+
+#ifndef unlikely
+# define unlikely(X) __builtin_expect(!!(X), 0)
+#endif
+
+#ifndef htons
+# define htons(X) __constant_htons((X))
+#endif
+
+#ifndef ntohs
+# define ntohs(X) __constant_ntohs((X))
+#endif
+
+#ifndef htonl
+# define htonl(X) __constant_htonl((X))
+#endif
+
+#ifndef ntohl
+# define ntohl(X) __constant_ntohl((X))
+#endif
+
+#ifndef __inline__
+# define __inline__ __attribute__((always_inline))
+#endif
+
+/** Section helper macros. */
+
+#ifndef __section
+# define __section(NAME) \
+ __attribute__((section(NAME), used))
+#endif
+
+#ifndef __section_tail
+# define __section_tail(ID, KEY) \
+ __section(__stringify(ID) "/" __stringify(KEY))
+#endif
+
+#ifndef __section_xdp_entry
+# define __section_xdp_entry \
+ __section(ELF_SECTION_PROG)
+#endif
+
+#ifndef __section_cls_entry
+# define __section_cls_entry \
+ __section(ELF_SECTION_CLASSIFIER)
+#endif
+
+#ifndef __section_act_entry
+# define __section_act_entry \
+ __section(ELF_SECTION_ACTION)
+#endif
+
+#ifndef __section_lwt_entry
+# define __section_lwt_entry \
+ __section(ELF_SECTION_PROG)
+#endif
+
+#ifndef __section_license
+# define __section_license \
+ __section(ELF_SECTION_LICENSE)
+#endif
+
+#ifndef __section_maps
+# define __section_maps \
+ __section(ELF_SECTION_MAPS)
+#endif
+
+/** Declaration helper macros. */
+
+#ifndef BPF_LICENSE
+# define BPF_LICENSE(NAME) \
+ char ____license[] __section_license = NAME
+#endif
+
+/** Classifier helper */
+
+#ifndef BPF_H_DEFAULT
+# define BPF_H_DEFAULT -1
+#endif
+
+/** BPF helper functions for tc. Individual flags are in linux/bpf.h */
+
+#ifndef __BPF_FUNC
+# define __BPF_FUNC(NAME, ...) \
+ (* NAME)(__VA_ARGS__) __maybe_unused
+#endif
+
+#ifndef BPF_FUNC
+# define BPF_FUNC(NAME, ...) \
+ __BPF_FUNC(NAME, __VA_ARGS__) = (void *) BPF_FUNC_##NAME
+#endif
+
+/* Map access/manipulation */
+static void *BPF_FUNC(map_lookup_elem, void *map, const void *key);
+static int BPF_FUNC(map_update_elem, void *map, const void *key,
+ const void *value, uint32_t flags);
+static int BPF_FUNC(map_delete_elem, void *map, const void *key);
+
+/* Time access */
+static uint64_t BPF_FUNC(ktime_get_ns);
+
+/* Debugging */
+
+/* FIXME: __attribute__ ((format(printf, 1, 3))) not possible unless
+ * llvm bug https://llvm.org/bugs/show_bug.cgi?id=26243 gets resolved.
+ * It would require ____fmt to be made const, which generates a reloc
+ * entry (non-map).
+ */
+static void BPF_FUNC(trace_printk, const char *fmt, int fmt_size, ...);
+
+#ifndef printt
+# define printt(fmt, ...) \
+ ({ \
+ char ____fmt[] = fmt; \
+ trace_printk(____fmt, sizeof(____fmt), ##__VA_ARGS__); \
+ })
+#endif
+
+/* Random numbers */
+static uint32_t BPF_FUNC(get_prandom_u32);
+
+/* Tail calls */
+static void BPF_FUNC(tail_call, struct __sk_buff *skb, void *map,
+ uint32_t index);
+
+/* System helpers */
+static uint32_t BPF_FUNC(get_smp_processor_id);
+static uint32_t BPF_FUNC(get_numa_node_id);
+
+/* Packet misc meta data */
+static uint32_t BPF_FUNC(get_cgroup_classid, struct __sk_buff *skb);
+static int BPF_FUNC(skb_under_cgroup, void *map, uint32_t index);
+
+static uint32_t BPF_FUNC(get_route_realm, struct __sk_buff *skb);
+static uint32_t BPF_FUNC(get_hash_recalc, struct __sk_buff *skb);
+static uint32_t BPF_FUNC(set_hash_invalid, struct __sk_buff *skb);
+
+/* Packet redirection */
+static int BPF_FUNC(redirect, int ifindex, uint32_t flags);
+static int BPF_FUNC(clone_redirect, struct __sk_buff *skb, int ifindex,
+ uint32_t flags);
+
+/* Packet manipulation */
+static int BPF_FUNC(skb_load_bytes, struct __sk_buff *skb, uint32_t off,
+ void *to, uint32_t len);
+static int BPF_FUNC(skb_store_bytes, struct __sk_buff *skb, uint32_t off,
+ const void *from, uint32_t len, uint32_t flags);
+
+static int BPF_FUNC(l3_csum_replace, struct __sk_buff *skb, uint32_t off,
+ uint32_t from, uint32_t to, uint32_t flags);
+static int BPF_FUNC(l4_csum_replace, struct __sk_buff *skb, uint32_t off,
+ uint32_t from, uint32_t to, uint32_t flags);
+static int BPF_FUNC(csum_diff, const void *from, uint32_t from_size,
+ const void *to, uint32_t to_size, uint32_t seed);
+static int BPF_FUNC(csum_update, struct __sk_buff *skb, uint32_t wsum);
+
+static int BPF_FUNC(skb_change_type, struct __sk_buff *skb, uint32_t type);
+static int BPF_FUNC(skb_change_proto, struct __sk_buff *skb, uint32_t proto,
+ uint32_t flags);
+static int BPF_FUNC(skb_change_tail, struct __sk_buff *skb, uint32_t nlen,
+ uint32_t flags);
+
+static int BPF_FUNC(skb_pull_data, struct __sk_buff *skb, uint32_t len);
+
+/* Event notification */
+static int __BPF_FUNC(skb_event_output, struct __sk_buff *skb, void *map,
+ uint64_t index, const void *data, uint32_t size) =
+ (void *) BPF_FUNC_perf_event_output;
+
+/* Packet vlan encap/decap */
+static int BPF_FUNC(skb_vlan_push, struct __sk_buff *skb, uint16_t proto,
+ uint16_t vlan_tci);
+static int BPF_FUNC(skb_vlan_pop, struct __sk_buff *skb);
+
+/* Packet tunnel encap/decap */
+static int BPF_FUNC(skb_get_tunnel_key, struct __sk_buff *skb,
+ struct bpf_tunnel_key *to, uint32_t size, uint32_t flags);
+static int BPF_FUNC(skb_set_tunnel_key, struct __sk_buff *skb,
+ const struct bpf_tunnel_key *from, uint32_t size,
+ uint32_t flags);
+
+static int BPF_FUNC(skb_get_tunnel_opt, struct __sk_buff *skb,
+ void *to, uint32_t size);
+static int BPF_FUNC(skb_set_tunnel_opt, struct __sk_buff *skb,
+ const void *from, uint32_t size);
+
+/** LLVM built-ins, mem*() routines work for constant size */
+
+#ifndef lock_xadd
+# define lock_xadd(ptr, val) ((void) __sync_fetch_and_add(ptr, val))
+#endif
+
+#ifndef memset
+# define memset(s, c, n) __builtin_memset((s), (c), (n))
+#endif
+
+#ifndef memcpy
+# define memcpy(d, s, n) __builtin_memcpy((d), (s), (n))
+#endif
+
+#ifndef memmove
+# define memmove(d, s, n) __builtin_memmove((d), (s), (n))
+#endif
+
+/* FIXME: __builtin_memcmp() is not yet fully usable unless llvm bug
+ * https://llvm.org/bugs/show_bug.cgi?id=26218 gets resolved. Also
+ * this one would generate a reloc entry (non-map), otherwise.
+ */
+#if 0
+#ifndef memcmp
+# define memcmp(a, b, n) __builtin_memcmp((a), (b), (n))
+#endif
+#endif
+
+unsigned long long load_byte(void *skb, unsigned long long off)
+ asm ("llvm.bpf.load.byte");
+
+unsigned long long load_half(void *skb, unsigned long long off)
+ asm ("llvm.bpf.load.half");
+
+unsigned long long load_word(void *skb, unsigned long long off)
+ asm ("llvm.bpf.load.word");
+
+#endif /* __BPF_API__ */
diff --git a/include/bpf_elf.h b/include/bpf_elf.h
new file mode 100644
index 0000000..ea8a11c
--- /dev/null
+++ b/include/bpf_elf.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */
+#ifndef __BPF_ELF__
+#define __BPF_ELF__
+
+#include <asm/types.h>
+
+/* Note:
+ *
+ * Below ELF section names and bpf_elf_map structure definition
+ * are not (!) kernel ABI. It's rather a "contract" between the
+ * application and the BPF loader in tc. For compatibility, the
+ * section names should stay as-is. Introduction of aliases, if
+ * needed, are a possibility, though.
+ */
+
+/* ELF section names, etc */
+#define ELF_SECTION_LICENSE "license"
+#define ELF_SECTION_MAPS "maps"
+#define ELF_SECTION_PROG "prog"
+#define ELF_SECTION_CLASSIFIER "classifier"
+#define ELF_SECTION_ACTION "action"
+
+#define ELF_MAX_MAPS 64
+#define ELF_MAX_LICENSE_LEN 128
+
+/* Object pinning settings */
+#define PIN_NONE 0
+#define PIN_OBJECT_NS 1
+#define PIN_GLOBAL_NS 2
+
+/* ELF map definition */
+struct bpf_elf_map {
+ __u32 type;
+ __u32 size_key;
+ __u32 size_value;
+ __u32 max_elem;
+ __u32 flags;
+ __u32 id;
+ __u32 pinning;
+ __u32 inner_id;
+ __u32 inner_idx;
+};
+
+#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \
+ struct ____btf_map_##name { \
+ type_key key; \
+ type_val value; \
+ }; \
+ struct ____btf_map_##name \
+ __attribute__ ((section(".maps." #name), used)) \
+ ____btf_map_##name = { }
+
+#endif /* __BPF_ELF__ */
diff --git a/include/bpf_scm.h b/include/bpf_scm.h
new file mode 100644
index 0000000..669f053
--- /dev/null
+++ b/include/bpf_scm.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_SCM__
+#define __BPF_SCM__
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+
+#include "utils.h"
+#include "bpf_elf.h"
+
+#define BPF_SCM_AUX_VER 1
+#define BPF_SCM_MAX_FDS ELF_MAX_MAPS
+#define BPF_SCM_MSG_SIZE 1024
+
+struct bpf_elf_st {
+ dev_t st_dev;
+ ino_t st_ino;
+};
+
+struct bpf_map_aux {
+ unsigned short uds_ver;
+ unsigned short num_ent;
+ char obj_name[64];
+ struct bpf_elf_st obj_st;
+ struct bpf_elf_map ent[BPF_SCM_MAX_FDS];
+};
+
+struct bpf_map_set_msg {
+ struct msghdr hdr;
+ struct iovec iov;
+ char msg_buf[BPF_SCM_MSG_SIZE];
+ struct bpf_map_aux aux;
+};
+
+static inline int *bpf_map_set_init(struct bpf_map_set_msg *msg,
+ struct sockaddr_un *addr,
+ unsigned int addr_len)
+{
+ const unsigned int cmsg_ctl_len = sizeof(int) * BPF_SCM_MAX_FDS;
+ struct cmsghdr *cmsg;
+
+ msg->iov.iov_base = &msg->aux;
+ msg->iov.iov_len = sizeof(msg->aux);
+
+ msg->hdr.msg_iov = &msg->iov;
+ msg->hdr.msg_iovlen = 1;
+
+ msg->hdr.msg_name = (struct sockaddr *)addr;
+ msg->hdr.msg_namelen = addr_len;
+
+ BUILD_BUG_ON(sizeof(msg->msg_buf) < cmsg_ctl_len);
+ msg->hdr.msg_control = &msg->msg_buf;
+ msg->hdr.msg_controllen = cmsg_ctl_len;
+
+ cmsg = CMSG_FIRSTHDR(&msg->hdr);
+ cmsg->cmsg_len = msg->hdr.msg_controllen;
+ cmsg->cmsg_level = SOL_SOCKET;
+ cmsg->cmsg_type = SCM_RIGHTS;
+
+ return (int *)CMSG_DATA(cmsg);
+}
+
+static inline void bpf_map_set_init_single(struct bpf_map_set_msg *msg,
+ int num)
+{
+ struct cmsghdr *cmsg;
+
+ msg->hdr.msg_controllen = CMSG_LEN(sizeof(int) * num);
+ msg->iov.iov_len = offsetof(struct bpf_map_aux, ent) +
+ sizeof(struct bpf_elf_map) * num;
+
+ cmsg = CMSG_FIRSTHDR(&msg->hdr);
+ cmsg->cmsg_len = msg->hdr.msg_controllen;
+}
+
+#endif /* __BPF_SCM__ */
diff --git a/include/bpf_util.h b/include/bpf_util.h
new file mode 100644
index 0000000..8951a5e
--- /dev/null
+++ b/include/bpf_util.h
@@ -0,0 +1,326 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * bpf_util.h BPF common code
+ *
+ * Authors: Daniel Borkmann <daniel@iogearbox.net>
+ * Jiri Pirko <jiri@resnulli.us>
+ */
+
+#ifndef __BPF_UTIL__
+#define __BPF_UTIL__
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/filter.h>
+#include <linux/magic.h>
+#include <linux/elf-em.h>
+#include <linux/if_alg.h>
+
+#include "utils.h"
+#include "bpf_scm.h"
+
+#define BPF_ENV_UDS "TC_BPF_UDS"
+#define BPF_ENV_MNT "TC_BPF_MNT"
+
+#ifndef BPF_MAX_LOG
+# define BPF_MAX_LOG 4096
+#endif
+
+#define BPF_DIR_GLOBALS "globals"
+
+#ifndef BPF_FS_MAGIC
+# define BPF_FS_MAGIC 0xcafe4a11
+#endif
+
+#define BPF_DIR_MNT "/sys/fs/bpf"
+
+#ifndef TRACEFS_MAGIC
+# define TRACEFS_MAGIC 0x74726163
+#endif
+
+#define TRACE_DIR_MNT "/sys/kernel/tracing"
+
+#ifndef AF_ALG
+# define AF_ALG 38
+#endif
+
+#ifndef EM_BPF
+# define EM_BPF 247
+#endif
+
+struct bpf_cfg_ops {
+ void (*cbpf_cb)(void *nl, const struct sock_filter *ops, int ops_len);
+ void (*ebpf_cb)(void *nl, int fd, const char *annotation);
+};
+
+enum bpf_mode {
+ CBPF_BYTECODE,
+ CBPF_FILE,
+ EBPF_OBJECT,
+ EBPF_PINNED,
+ BPF_MODE_MAX,
+};
+
+struct bpf_cfg_in {
+ const char *object;
+ const char *section;
+ const char *prog_name;
+ const char *uds;
+ enum bpf_prog_type type;
+ enum bpf_mode mode;
+ __u32 ifindex;
+ bool verbose;
+ int argc;
+ char **argv;
+ struct sock_filter opcodes[BPF_MAXINSNS];
+ union {
+ int n_opcodes;
+ int prog_fd;
+ };
+};
+
+/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
+
+#define BPF_ALU64_REG(OP, DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+#define BPF_ALU32_REG(OP, DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
+
+#define BPF_ALU64_IMM(OP, DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+#define BPF_ALU32_IMM(OP, DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+/* Short form of mov, dst_reg = src_reg */
+
+#define BPF_MOV64_REG(DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_MOV | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+#define BPF_MOV32_REG(DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_MOV | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+/* Short form of mov, dst_reg = imm32 */
+
+#define BPF_MOV64_IMM(DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_MOV | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+#define BPF_MOV32_IMM(DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_MOV | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
+#define BPF_LD_IMM64(DST, IMM) \
+ BPF_LD_IMM64_RAW(DST, 0, IMM)
+
+#define BPF_LD_IMM64_RAW(DST, SRC, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_DW | BPF_IMM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = (__u32) (IMM) }), \
+ ((struct bpf_insn) { \
+ .code = 0, /* zero is reserved opcode */ \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = ((__u64) (IMM)) >> 32 })
+
+#ifndef BPF_PSEUDO_MAP_FD
+# define BPF_PSEUDO_MAP_FD 1
+#endif
+
+/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
+#define BPF_LD_MAP_FD(DST, MAP_FD) \
+ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+
+
+/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */
+
+#define BPF_LD_ABS(SIZE, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
+
+#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = src_reg */
+
+#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
+
+#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */
+
+#define BPF_JMP_REG(OP, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
+
+#define BPF_JMP_IMM(OP, DST, IMM, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* Raw code statement block */
+
+#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \
+ ((struct bpf_insn) { \
+ .code = CODE, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* Program exit */
+
+#define BPF_EXIT_INSN() \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_EXIT, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = 0 })
+
+int bpf_parse_common(struct bpf_cfg_in *cfg, const struct bpf_cfg_ops *ops);
+int bpf_load_common(struct bpf_cfg_in *cfg, const struct bpf_cfg_ops *ops,
+ void *nl);
+int bpf_parse_and_load_common(struct bpf_cfg_in *cfg,
+ const struct bpf_cfg_ops *ops, void *nl);
+
+const char *bpf_prog_to_default_section(enum bpf_prog_type type);
+
+int bpf_graft_map(const char *map_path, uint32_t *key, int argc, char **argv);
+int bpf_trace_pipe(void);
+
+void bpf_print_ops(struct rtattr *bpf_ops, __u16 len);
+
+int bpf_prog_load_dev(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t size_insns, const char *license, __u32 ifindex,
+ char *log, size_t size_log, bool verbose);
+int bpf_program_load(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t size_insns, const char *license, char *log,
+ size_t size_log, bool verbose);
+
+int bpf_prog_attach_fd(int prog_fd, int target_fd, enum bpf_attach_type type);
+int bpf_prog_detach_fd(int target_fd, enum bpf_attach_type type);
+int bpf_program_attach(int prog_fd, int target_fd, enum bpf_attach_type type);
+
+int bpf_dump_prog_info(FILE *f, uint32_t id);
+
+int bpf(int cmd, union bpf_attr *attr, unsigned int size);
+
+#ifdef HAVE_ELF
+int bpf_send_map_fds(const char *path, const char *obj);
+int bpf_recv_map_fds(const char *path, int *fds, struct bpf_map_aux *aux,
+ unsigned int entries);
+#ifdef HAVE_LIBBPF
+int iproute2_bpf_elf_ctx_init(struct bpf_cfg_in *cfg);
+int iproute2_bpf_fetch_ancillary(void);
+int iproute2_get_root_path(char *root_path, size_t len);
+bool iproute2_is_pin_map(const char *libbpf_map_name, char *pathname);
+bool iproute2_is_map_in_map(const char *libbpf_map_name, struct bpf_elf_map *imap,
+ struct bpf_elf_map *omap, char *omap_name);
+int iproute2_find_map_name_by_id(unsigned int map_id, char *name);
+int iproute2_load_libbpf(struct bpf_cfg_in *cfg);
+#endif /* HAVE_LIBBPF */
+#else
+static inline int bpf_send_map_fds(const char *path, const char *obj)
+{
+ return 0;
+}
+
+static inline int bpf_recv_map_fds(const char *path, int *fds,
+ struct bpf_map_aux *aux,
+ unsigned int entries)
+{
+ return -1;
+}
+#ifdef HAVE_LIBBPF
+static inline int iproute2_load_libbpf(struct bpf_cfg_in *cfg)
+{
+ fprintf(stderr, "No ELF library support compiled in.\n");
+ return -1;
+}
+#endif /* HAVE_LIBBPF */
+#endif /* HAVE_ELF */
+
+const char *get_libbpf_version(void);
+
+#endif /* __BPF_UTIL__ */
diff --git a/include/cg_map.h b/include/cg_map.h
new file mode 100644
index 0000000..6293b50
--- /dev/null
+++ b/include/cg_map.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __CG_MAP_H__
+#define __CG_MAP_H__
+
+const char *cg_id_to_path(__u64 id);
+
+#endif /* __CG_MAP_H__ */
diff --git a/include/color.h b/include/color.h
new file mode 100644
index 0000000..17ec56f
--- /dev/null
+++ b/include/color.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __COLOR_H__
+#define __COLOR_H__ 1
+
+#include <stdbool.h>
+
+enum color_attr {
+ COLOR_IFNAME,
+ COLOR_MAC,
+ COLOR_INET,
+ COLOR_INET6,
+ COLOR_OPERSTATE_UP,
+ COLOR_OPERSTATE_DOWN,
+ COLOR_NONE
+};
+
+enum color_opt {
+ COLOR_OPT_NEVER = 0,
+ COLOR_OPT_AUTO = 1,
+ COLOR_OPT_ALWAYS = 2
+};
+
+bool check_enable_color(int color, int json);
+bool matches_color(const char *arg, int *val);
+int color_fprintf(FILE *fp, enum color_attr attr, const char *fmt, ...);
+enum color_attr ifa_family_color(__u8 ifa_family);
+enum color_attr oper_state_color(__u8 state);
+
+#endif
diff --git a/include/dlfcn.h b/include/dlfcn.h
new file mode 100644
index 0000000..1d8890a
--- /dev/null
+++ b/include/dlfcn.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Stub dlfcn implementation for systems that lack shared library support
+ * but obviously can still reference compiled-in symbols.
+ */
+
+#ifndef NO_SHARED_LIBS
+#include_next <dlfcn.h>
+#else
+
+#define RTLD_LAZY 0
+#define RTLD_GLOBAL 1
+#define _FAKE_DLFCN_HDL (void *)0xbeefcafe
+
+static inline void *dlopen(const char *file, int flag)
+{
+ if (file == NULL)
+ return _FAKE_DLFCN_HDL;
+ else
+ return NULL;
+}
+
+void *_dlsym(const char *sym);
+static inline void *dlsym(void *handle, const char *sym)
+{
+ if (handle != _FAKE_DLFCN_HDL)
+ return NULL;
+ return _dlsym(sym);
+}
+
+static inline char *dlerror(void)
+{
+ return NULL;
+}
+
+static inline int dlclose(void *handle)
+{
+ return (handle == _FAKE_DLFCN_HDL) ? 0 : 1;
+}
+
+#endif
diff --git a/include/json_print.h b/include/json_print.h
new file mode 100644
index 0000000..daebcf5
--- /dev/null
+++ b/include/json_print.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * json_print.h print regular or json output, based on json_writer.
+ *
+ * Authors: Julien Fortin, <julien@cumulusnetworks.com>
+ */
+
+#ifndef _JSON_PRINT_H_
+#define _JSON_PRINT_H_
+
+#include "json_writer.h"
+#include "color.h"
+
+#define _IS_JSON_CONTEXT(type) (is_json_context() && (type & PRINT_JSON || type & PRINT_ANY))
+#define _IS_FP_CONTEXT(type) (!is_json_context() && (type & PRINT_FP || type & PRINT_ANY))
+
+json_writer_t *get_json_writer(void);
+
+/*
+ * use:
+ * - PRINT_ANY for context based output
+ * - PRINT_FP for non json specific output
+ * - PRINT_JSON for json specific output
+ */
+enum output_type {
+ PRINT_FP = 1,
+ PRINT_JSON = 2,
+ PRINT_ANY = 4,
+};
+
+void new_json_obj(int json);
+void delete_json_obj(void);
+void new_json_obj_plain(int json);
+void delete_json_obj_plain(void);
+
+bool is_json_context(void);
+
+void open_json_object(const char *str);
+void close_json_object(void);
+void open_json_array(enum output_type type, const char *delim);
+void close_json_array(enum output_type type, const char *delim);
+
+void print_nl(void);
+
+#define _PRINT_FUNC(type_name, type) \
+ int print_color_##type_name(enum output_type t, \
+ enum color_attr color, \
+ const char *key, \
+ const char *fmt, \
+ type value); \
+ \
+ static inline int print_##type_name(enum output_type t, \
+ const char *key, \
+ const char *fmt, \
+ type value) \
+ { \
+ return print_color_##type_name(t, COLOR_NONE, key, fmt, \
+ value); \
+ }
+
+/* These functions return 0 if printing to a JSON context, number of
+ * characters printed otherwise (as calculated by printf(3)).
+ */
+_PRINT_FUNC(int, int)
+_PRINT_FUNC(s64, int64_t)
+_PRINT_FUNC(bool, bool)
+_PRINT_FUNC(on_off, bool)
+_PRINT_FUNC(null, const char*)
+_PRINT_FUNC(string, const char*)
+_PRINT_FUNC(uint, unsigned int)
+_PRINT_FUNC(size, __u32)
+_PRINT_FUNC(u64, uint64_t)
+_PRINT_FUNC(hhu, unsigned char)
+_PRINT_FUNC(hu, unsigned short)
+_PRINT_FUNC(hex, unsigned int)
+_PRINT_FUNC(0xhex, unsigned long long)
+_PRINT_FUNC(luint, unsigned long)
+_PRINT_FUNC(lluint, unsigned long long)
+_PRINT_FUNC(float, double)
+_PRINT_FUNC(tv, const struct timeval *)
+#undef _PRINT_FUNC
+
+#define _PRINT_NAME_VALUE_FUNC(type_name, type, format_char) \
+ void print_##type_name##_name_value(const char *name, type value) \
+
+_PRINT_NAME_VALUE_FUNC(uint, unsigned int, u);
+_PRINT_NAME_VALUE_FUNC(string, const char*, s);
+#undef _PRINT_NAME_VALUE_FUNC
+
+int print_color_rate(bool use_iec, enum output_type t, enum color_attr color,
+ const char *key, const char *fmt, unsigned long long rate);
+
+static inline int print_rate(bool use_iec, enum output_type t,
+ const char *key, const char *fmt,
+ unsigned long long rate)
+{
+ return print_color_rate(use_iec, t, COLOR_NONE, key, fmt, rate);
+}
+
+unsigned int print_range(const char *name, __u32 start, __u32 end);
+
+int print_color_bool_opt(enum output_type type, enum color_attr color,
+ const char *key, bool value, bool show);
+
+static inline int print_bool_opt(enum output_type type,
+ const char *key, bool value, bool show)
+{
+ return print_color_bool_opt(type, COLOR_NONE, key, value, show);
+}
+
+/* A backdoor to the size formatter. Please use print_size() instead. */
+char *sprint_size(__u32 sz, char *buf);
+
+#endif /* _JSON_PRINT_H_ */
diff --git a/include/json_writer.h b/include/json_writer.h
new file mode 100644
index 0000000..b52dc2d
--- /dev/null
+++ b/include/json_writer.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
+/*
+ * Simple streaming JSON writer
+ *
+ * This takes care of the annoying bits of JSON syntax like the commas
+ * after elements
+ *
+ * Authors: Stephen Hemminger <stephen@networkplumber.org>
+ */
+
+#ifndef _JSON_WRITER_H_
+#define _JSON_WRITER_H_
+
+#include <stdbool.h>
+#include <stdint.h>
+
+/* Opaque class structure */
+typedef struct json_writer json_writer_t;
+
+/* Create a new JSON stream */
+json_writer_t *jsonw_new(FILE *f);
+/* End output to JSON stream */
+void jsonw_destroy(json_writer_t **self_p);
+
+/* Cause output to have pretty whitespace */
+void jsonw_pretty(json_writer_t *self, bool on);
+
+/* Add property name */
+void jsonw_name(json_writer_t *self, const char *name);
+
+/* Add value */
+__attribute__((format(printf, 2, 3)))
+void jsonw_printf(json_writer_t *self, const char *fmt, ...);
+void jsonw_string(json_writer_t *self, const char *value);
+void jsonw_bool(json_writer_t *self, bool value);
+void jsonw_float(json_writer_t *self, double number);
+void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num);
+void jsonw_uint(json_writer_t *self, unsigned int number);
+void jsonw_u64(json_writer_t *self, uint64_t number);
+void jsonw_xint(json_writer_t *self, uint64_t number);
+void jsonw_hhu(json_writer_t *self, unsigned char num);
+void jsonw_hu(json_writer_t *self, unsigned short number);
+void jsonw_int(json_writer_t *self, int number);
+void jsonw_s64(json_writer_t *self, int64_t number);
+void jsonw_null(json_writer_t *self);
+void jsonw_luint(json_writer_t *self, unsigned long num);
+void jsonw_lluint(json_writer_t *self, unsigned long long num);
+
+/* Useful Combinations of name and value */
+void jsonw_string_field(json_writer_t *self, const char *prop, const char *val);
+void jsonw_bool_field(json_writer_t *self, const char *prop, bool value);
+void jsonw_float_field(json_writer_t *self, const char *prop, double num);
+void jsonw_uint_field(json_writer_t *self, const char *prop, unsigned int num);
+void jsonw_u64_field(json_writer_t *self, const char *prop, uint64_t num);
+void jsonw_xint_field(json_writer_t *self, const char *prop, uint64_t num);
+void jsonw_hhu_field(json_writer_t *self, const char *prop, unsigned char num);
+void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num);
+void jsonw_int_field(json_writer_t *self, const char *prop, int num);
+void jsonw_s64_field(json_writer_t *self, const char *prop, int64_t num);
+void jsonw_null_field(json_writer_t *self, const char *prop);
+void jsonw_luint_field(json_writer_t *self, const char *prop,
+ unsigned long num);
+void jsonw_lluint_field(json_writer_t *self, const char *prop,
+ unsigned long long num);
+
+/* Collections */
+void jsonw_start_object(json_writer_t *self);
+void jsonw_end_object(json_writer_t *self);
+
+void jsonw_start_array(json_writer_t *self);
+void jsonw_end_array(json_writer_t *self);
+
+/* Override default exception handling */
+typedef void (jsonw_err_handler_fn)(const char *);
+
+#endif /* _JSON_WRITER_H_ */
diff --git a/include/libgenl.h b/include/libgenl.h
new file mode 100644
index 0000000..97281cc
--- /dev/null
+++ b/include/libgenl.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LIBGENL_H__
+#define __LIBGENL_H__
+
+#include "libnetlink.h"
+
+#define GENL_REQUEST(_req, _bufsiz, _family, _hdrsiz, _ver, _cmd, _flags) \
+struct { \
+ struct nlmsghdr n; \
+ struct genlmsghdr g; \
+ char buf[NLMSG_ALIGN(_hdrsiz) + (_bufsiz)]; \
+} _req = { \
+ .n = { \
+ .nlmsg_type = (_family), \
+ .nlmsg_flags = (_flags), \
+ .nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN + (_hdrsiz)), \
+ }, \
+ .g = { \
+ .cmd = (_cmd), \
+ .version = (_ver), \
+ }, \
+}
+
+int genl_add_mcast_grp(struct rtnl_handle *grth, __u16 genl_family, const char *group);
+int genl_resolve_family(struct rtnl_handle *grth, const char *family);
+int genl_init_handle(struct rtnl_handle *grth, const char *family,
+ int *genl_family);
+
+#endif /* __LIBGENL_H__ */
diff --git a/include/libnetlink.h b/include/libnetlink.h
new file mode 100644
index 0000000..ad7e712
--- /dev/null
+++ b/include/libnetlink.h
@@ -0,0 +1,358 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LIBNETLINK_H__
+#define __LIBNETLINK_H__ 1
+
+#include <stdio.h>
+#include <string.h>
+#include <asm/types.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_link.h>
+#include <linux/if_addr.h>
+#include <linux/neighbour.h>
+#include <linux/netconf.h>
+#include <arpa/inet.h>
+
+struct rtnl_handle {
+ int fd;
+ struct sockaddr_nl local;
+ struct sockaddr_nl peer;
+ __u32 seq;
+ __u32 dump;
+ int proto;
+ FILE *dump_fp;
+#define RTNL_HANDLE_F_LISTEN_ALL_NSID 0x01
+#define RTNL_HANDLE_F_SUPPRESS_NLERR 0x02
+#define RTNL_HANDLE_F_STRICT_CHK 0x04
+ int flags;
+};
+
+struct nlmsg_list {
+ struct nlmsg_list *next;
+ struct nlmsghdr h;
+};
+
+struct nlmsg_chain {
+ struct nlmsg_list *head;
+ struct nlmsg_list *tail;
+};
+
+struct ipstats_req {
+ struct nlmsghdr nlh;
+ struct if_stats_msg ifsm;
+ char buf[128];
+};
+
+extern int rcvbuf;
+
+int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions)
+ __attribute__((warn_unused_result));
+
+int rtnl_open_byproto(struct rtnl_handle *rth, unsigned int subscriptions,
+ int protocol)
+ __attribute__((warn_unused_result));
+int rtnl_add_nl_group(struct rtnl_handle *rth, unsigned int group)
+ __attribute__((warn_unused_result));
+void rtnl_close(struct rtnl_handle *rth);
+void rtnl_set_strict_dump(struct rtnl_handle *rth);
+
+typedef int (*req_filter_fn_t)(struct nlmsghdr *nlh, int reqlen);
+
+int rtnl_addrdump_req(struct rtnl_handle *rth, int family,
+ req_filter_fn_t filter_fn)
+ __attribute__((warn_unused_result));
+int rtnl_addrlbldump_req(struct rtnl_handle *rth, int family)
+ __attribute__((warn_unused_result));
+int rtnl_routedump_req(struct rtnl_handle *rth, int family,
+ req_filter_fn_t filter_fn)
+ __attribute__((warn_unused_result));
+int rtnl_ruledump_req(struct rtnl_handle *rth, int family)
+ __attribute__((warn_unused_result));
+int rtnl_neighdump_req(struct rtnl_handle *rth, int family,
+ req_filter_fn_t filter_fn)
+ __attribute__((warn_unused_result));
+int rtnl_neightbldump_req(struct rtnl_handle *rth, int family)
+ __attribute__((warn_unused_result));
+int rtnl_mdbdump_req(struct rtnl_handle *rth, int family)
+ __attribute__((warn_unused_result));
+int rtnl_brvlandump_req(struct rtnl_handle *rth, int family, __u32 dump_flags)
+ __attribute__((warn_unused_result));
+int rtnl_netconfdump_req(struct rtnl_handle *rth, int family)
+ __attribute__((warn_unused_result));
+
+int rtnl_linkdump_req(struct rtnl_handle *rth, int fam)
+ __attribute__((warn_unused_result));
+int rtnl_linkdump_req_filter(struct rtnl_handle *rth, int fam, __u32 filt_mask)
+ __attribute__((warn_unused_result));
+
+int rtnl_linkdump_req_filter_fn(struct rtnl_handle *rth, int fam,
+ req_filter_fn_t fn)
+ __attribute__((warn_unused_result));
+int rtnl_fdb_linkdump_req_filter_fn(struct rtnl_handle *rth,
+ req_filter_fn_t filter_fn)
+ __attribute__((warn_unused_result));
+int rtnl_nsiddump_req_filter_fn(struct rtnl_handle *rth, int family,
+ req_filter_fn_t filter_fn)
+ __attribute__((warn_unused_result));
+int rtnl_statsdump_req_filter(struct rtnl_handle *rth, int fam, __u32 filt_mask,
+ int (*filter_fn)(struct ipstats_req *req,
+ void *data),
+ void *filter_data)
+ __attribute__((warn_unused_result));
+int rtnl_dump_request(struct rtnl_handle *rth, int type, void *req,
+ int len)
+ __attribute__((warn_unused_result));
+int rtnl_dump_request_n(struct rtnl_handle *rth, struct nlmsghdr *n)
+ __attribute__((warn_unused_result));
+
+int rtnl_nexthopdump_req(struct rtnl_handle *rth, int family,
+ req_filter_fn_t filter_fn)
+ __attribute__((warn_unused_result));
+int rtnl_nexthop_bucket_dump_req(struct rtnl_handle *rth, int family,
+ req_filter_fn_t filter_fn)
+ __attribute__((warn_unused_result));
+
+int rtnl_tunneldump_req(struct rtnl_handle *rth, int family, int ifindex,
+ __u8 flags)
+ __attribute__((warn_unused_result));
+
+struct rtnl_ctrl_data {
+ int nsid;
+};
+
+typedef int (*rtnl_filter_t)(struct nlmsghdr *n, void *);
+
+/**
+ * rtnl error handler called from
+ * rtnl_dump_done()
+ * rtnl_dump_error()
+ *
+ * Return value is a bitmask of the following values:
+ * RTNL_LET_NLERR
+ * error handled as usual
+ * RTNL_SUPPRESS_NLMSG_DONE_NLERR
+ * error in nlmsg_type == NLMSG_DONE will be suppressed
+ * RTNL_SUPPRESS_NLMSG_ERROR_NLERR
+ * error in nlmsg_type == NLMSG_ERROR will be suppressed
+ * and nlmsg will be skipped
+ * RTNL_SUPPRESS_NLERR - suppress error in both previous cases
+ */
+#define RTNL_LET_NLERR 0x01
+#define RTNL_SUPPRESS_NLMSG_DONE_NLERR 0x02
+#define RTNL_SUPPRESS_NLMSG_ERROR_NLERR 0x04
+#define RTNL_SUPPRESS_NLERR 0x06
+typedef int (*rtnl_err_hndlr_t)(struct nlmsghdr *n, void *);
+
+typedef int (*rtnl_listen_filter_t)(struct rtnl_ctrl_data *,
+ struct nlmsghdr *n, void *);
+
+typedef int (*nl_ext_ack_fn_t)(const char *errmsg, uint32_t off,
+ const struct nlmsghdr *inner_nlh);
+
+struct rtnl_dump_filter_arg {
+ rtnl_filter_t filter;
+ void *arg1;
+ rtnl_err_hndlr_t errhndlr;
+ void *arg2;
+ __u16 nc_flags;
+};
+
+int rtnl_dump_filter_nc(struct rtnl_handle *rth,
+ rtnl_filter_t filter,
+ void *arg, __u16 nc_flags);
+#define rtnl_dump_filter(rth, filter, arg) \
+ rtnl_dump_filter_nc(rth, filter, arg, 0)
+int rtnl_dump_filter_errhndlr_nc(struct rtnl_handle *rth,
+ rtnl_filter_t filter,
+ void *arg1,
+ rtnl_err_hndlr_t errhndlr,
+ void *arg2,
+ __u16 nc_flags);
+#define rtnl_dump_filter_errhndlr(rth, filter, farg, errhndlr, earg) \
+ rtnl_dump_filter_errhndlr_nc(rth, filter, farg, errhndlr, earg, 0)
+
+int rtnl_echo_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n, int json,
+ int (*print_info)(struct nlmsghdr *n, void *arg))
+ __attribute__((warn_unused_result));
+int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+ struct nlmsghdr **answer)
+ __attribute__((warn_unused_result));
+int rtnl_talk_suppress_rtnl_errmsg(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+ struct nlmsghdr **answer)
+ __attribute__((warn_unused_result));
+int rtnl_send(struct rtnl_handle *rth, const void *buf, int)
+ __attribute__((warn_unused_result));
+int rtnl_send_check(struct rtnl_handle *rth, const void *buf, int)
+ __attribute__((warn_unused_result));
+int nl_dump_ext_ack(const struct nlmsghdr *nlh, nl_ext_ack_fn_t errfn);
+int nl_dump_ext_ack_done(const struct nlmsghdr *nlh, unsigned int offset, int error);
+
+int addattr(struct nlmsghdr *n, int maxlen, int type);
+int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data);
+int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data);
+int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data);
+int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data);
+int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *data);
+
+int addattr_l(struct nlmsghdr *n, int maxlen, int type,
+ const void *data, int alen);
+int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len);
+struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type);
+int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest);
+struct rtattr *addattr_nest_compat(struct nlmsghdr *n, int maxlen, int type,
+ const void *data, int len);
+int addattr_nest_compat_end(struct nlmsghdr *n, struct rtattr *nest);
+int rta_addattr8(struct rtattr *rta, int maxlen, int type, __u8 data);
+int rta_addattr16(struct rtattr *rta, int maxlen, int type, __u16 data);
+int rta_addattr32(struct rtattr *rta, int maxlen, int type, __u32 data);
+int rta_addattr64(struct rtattr *rta, int maxlen, int type, __u64 data);
+int rta_addattr_l(struct rtattr *rta, int maxlen, int type,
+ const void *data, int alen);
+
+int parse_rtattr(struct rtattr *tb[], int max, struct rtattr *rta, int len);
+int parse_rtattr_flags(struct rtattr *tb[], int max, struct rtattr *rta,
+ int len, unsigned short flags);
+struct rtattr *parse_rtattr_one(int type, struct rtattr *rta, int len);
+int __parse_rtattr_nested_compat(struct rtattr *tb[], int max, struct rtattr *rta, int len);
+
+struct rtattr *rta_nest(struct rtattr *rta, int maxlen, int type);
+int rta_nest_end(struct rtattr *rta, struct rtattr *nest);
+
+#define RTA_TAIL(rta) \
+ ((struct rtattr *) (((void *) (rta)) + \
+ RTA_ALIGN((rta)->rta_len)))
+
+#define parse_rtattr_nested(tb, max, rta) \
+ (parse_rtattr_flags((tb), (max), RTA_DATA(rta), RTA_PAYLOAD(rta), \
+ NLA_F_NESTED))
+
+#define parse_rtattr_one_nested(type, rta) \
+ (parse_rtattr_one(type, RTA_DATA(rta), RTA_PAYLOAD(rta)))
+
+#define parse_rtattr_nested_compat(tb, max, rta, data, len) \
+ ({ data = RTA_PAYLOAD(rta) >= len ? RTA_DATA(rta) : NULL; \
+ __parse_rtattr_nested_compat(tb, max, rta, len); })
+
+static inline __u8 rta_getattr_u8(const struct rtattr *rta)
+{
+ return *(__u8 *)RTA_DATA(rta);
+}
+static inline __u16 rta_getattr_u16(const struct rtattr *rta)
+{
+ return *(__u16 *)RTA_DATA(rta);
+}
+static inline __be16 rta_getattr_be16(const struct rtattr *rta)
+{
+ return ntohs(rta_getattr_u16(rta));
+}
+static inline __u32 rta_getattr_u32(const struct rtattr *rta)
+{
+ return *(__u32 *)RTA_DATA(rta);
+}
+static inline __be32 rta_getattr_be32(const struct rtattr *rta)
+{
+ return ntohl(rta_getattr_u32(rta));
+}
+static inline __u64 rta_getattr_u64(const struct rtattr *rta)
+{
+ __u64 tmp;
+
+ memcpy(&tmp, RTA_DATA(rta), sizeof(__u64));
+ return tmp;
+}
+static inline __s32 rta_getattr_s32(const struct rtattr *rta)
+{
+ return *(__s32 *)RTA_DATA(rta);
+}
+static inline __s64 rta_getattr_s64(const struct rtattr *rta)
+{
+ __s64 tmp;
+
+ memcpy(&tmp, RTA_DATA(rta), sizeof(tmp));
+ return tmp;
+}
+static inline const char *rta_getattr_str(const struct rtattr *rta)
+{
+ return (const char *)RTA_DATA(rta);
+}
+static inline int rta_type(const struct rtattr *rta)
+{
+ return rta->rta_type & NLA_TYPE_MASK;
+}
+
+int rtnl_listen_all_nsid(struct rtnl_handle *);
+int rtnl_listen(struct rtnl_handle *, rtnl_listen_filter_t handler,
+ void *jarg);
+int rtnl_from_file(FILE *, rtnl_listen_filter_t handler,
+ void *jarg);
+
+#define NLMSG_TAIL(nmsg) \
+ ((struct rtattr *) (((void *) (nmsg)) + NLMSG_ALIGN((nmsg)->nlmsg_len)))
+
+#ifndef IFA_RTA
+#define IFA_RTA(r) \
+ ((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg))))
+#endif
+#ifndef IFA_PAYLOAD
+#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n, sizeof(struct ifaddrmsg))
+#endif
+
+#ifndef IFLA_RTA
+#define IFLA_RTA(r) \
+ ((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
+#endif
+#ifndef IFLA_PAYLOAD
+#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n, sizeof(struct ifinfomsg))
+#endif
+
+#ifndef NDA_RTA
+#define NDA_RTA(r) \
+ ((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct ndmsg))))
+#endif
+#ifndef NDA_PAYLOAD
+#define NDA_PAYLOAD(n) NLMSG_PAYLOAD(n, sizeof(struct ndmsg))
+#endif
+
+#ifndef NDTA_RTA
+#define NDTA_RTA(r) \
+ ((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct ndtmsg))))
+#endif
+#ifndef NDTA_PAYLOAD
+#define NDTA_PAYLOAD(n) NLMSG_PAYLOAD(n, sizeof(struct ndtmsg))
+#endif
+
+#ifndef NETNS_RTA
+#define NETNS_RTA(r) \
+ ((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct rtgenmsg))))
+#endif
+#ifndef NETNS_PAYLOAD
+#define NETNS_PAYLOAD(n) NLMSG_PAYLOAD(n, sizeof(struct rtgenmsg))
+#endif
+
+#ifndef IFLA_STATS_RTA
+#define IFLA_STATS_RTA(r) \
+ ((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct if_stats_msg))))
+#endif
+
+#ifndef BRVLAN_RTA
+#define BRVLAN_RTA(r) \
+ ((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct br_vlan_msg))))
+#endif
+
+#ifndef TUNNEL_RTA
+#define TUNNEL_RTA(r) \
+ ((struct rtattr *)(((char *)(r)) + NLMSG_ALIGN(sizeof(struct tunnel_msg))))
+#endif
+
+/* User defined nlmsg_type which is used mostly for logging netlink
+ * messages from dump file */
+#define NLMSG_TSTAMP 15
+
+#define rtattr_for_each_nested(attr, nest) \
+ for ((attr) = (void *)RTA_DATA(nest); \
+ RTA_OK(attr, RTA_PAYLOAD(nest) - ((char *)(attr) - (char *)RTA_DATA((nest)))); \
+ (attr) = RTA_TAIL((attr)))
+
+void nl_print_policy(const struct rtattr *attr, FILE *fp);
+
+#endif /* __LIBNETLINK_H__ */
diff --git a/include/list.h b/include/list.h
new file mode 100644
index 0000000..5d86b13
--- /dev/null
+++ b/include/list.h
@@ -0,0 +1,134 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LIST_H__
+#define __LIST_H__ 1
+/* List and hash list stuff from kernel */
+
+#include <stddef.h>
+
+#define container_of(ptr, type, member) ({ \
+ const typeof( ((type *)0)->member ) *__mptr = (ptr); \
+ (type *)( (char *)__mptr - offsetof(type,member) );})
+
+struct list_head {
+ struct list_head *next, *prev;
+};
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+ list->next = list;
+ list->prev = list;
+}
+
+static inline void __list_add(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next)
+{
+ next->prev = new;
+ new->next = next;
+ new->prev = prev;
+ prev->next = new;
+}
+
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+ __list_add(new, head, head->next);
+}
+
+static inline void list_add_tail(struct list_head *new, struct list_head *head)
+{
+ __list_add(new, head->prev, head);
+}
+
+static inline void __list_del(struct list_head *prev, struct list_head *next)
+{
+ next->prev = prev;
+ prev->next = next;
+}
+
+static inline void list_del(struct list_head *entry)
+{
+ __list_del(entry->prev, entry->next);
+}
+
+#define list_entry(ptr, type, member) \
+ container_of(ptr, type, member)
+
+#define list_first_entry(ptr, type, member) \
+ list_entry((ptr)->next, type, member)
+
+#define list_last_entry(ptr, type, member) \
+ list_entry((ptr)->prev, type, member)
+
+#define list_next_entry(pos, member) \
+ list_entry((pos)->member.next, typeof(*(pos)), member)
+
+#define list_prev_entry(pos, member) \
+ list_entry((pos)->member.prev, typeof(*(pos)), member)
+
+#define list_for_each_entry(pos, head, member) \
+ for (pos = list_first_entry(head, typeof(*pos), member); \
+ &pos->member != (head); \
+ pos = list_next_entry(pos, member))
+
+#define list_for_each_entry_safe(pos, n, head, member) \
+ for (pos = list_first_entry(head, typeof(*pos), member), \
+ n = list_next_entry(pos, member); \
+ &pos->member != (head); \
+ pos = n, n = list_next_entry(n, member))
+
+#define list_for_each_entry_reverse(pos, head, member) \
+ for (pos = list_last_entry(head, typeof(*pos), member); \
+ &pos->member != (head); \
+ pos = list_prev_entry(pos, member))
+
+struct hlist_head {
+ struct hlist_node *first;
+};
+
+struct hlist_node {
+ struct hlist_node *next, **pprev;
+};
+
+static inline void hlist_del(struct hlist_node *n)
+{
+ struct hlist_node *next = n->next;
+ struct hlist_node **pprev = n->pprev;
+ *pprev = next;
+ if (next)
+ next->pprev = pprev;
+}
+
+static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
+{
+ struct hlist_node *first = h->first;
+ n->next = first;
+ if (first)
+ first->pprev = &n->next;
+ h->first = n;
+ n->pprev = &h->first;
+}
+
+static inline int list_empty(const struct list_head *head)
+{
+ return head->next == head;
+}
+
+#define hlist_for_each(pos, head) \
+ for (pos = (head)->first; pos ; pos = pos->next)
+
+
+#define hlist_for_each_safe(pos, n, head) \
+ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
+ pos = n)
+
+#define hlist_entry_safe(ptr, type, member) \
+ ({ typeof(ptr) ____ptr = (ptr); \
+ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \
+ })
+
+#define hlist_for_each_entry(pos, head, member) \
+ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\
+ pos; \
+ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+#endif /* __LIST_H__ */
diff --git a/include/ll_map.h b/include/ll_map.h
new file mode 100644
index 0000000..4de1041
--- /dev/null
+++ b/include/ll_map.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LL_MAP_H__
+#define __LL_MAP_H__ 1
+
+int ll_remember_index(struct nlmsghdr *n, void *arg);
+
+void ll_init_map(struct rtnl_handle *rth);
+unsigned ll_name_to_index(const char *name);
+const char *ll_index_to_name(unsigned idx);
+int ll_index_to_type(unsigned idx);
+int ll_index_to_flags(unsigned idx);
+void ll_drop_by_index(unsigned index);
+unsigned namehash(const char *str);
+
+const char *ll_idx_n2a(unsigned int idx);
+
+#endif /* __LL_MAP_H__ */
diff --git a/include/mnl_utils.h b/include/mnl_utils.h
new file mode 100644
index 0000000..76fe1df
--- /dev/null
+++ b/include/mnl_utils.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __MNL_UTILS_H__
+#define __MNL_UTILS_H__ 1
+
+struct mnlu_gen_socket {
+ struct mnl_socket *nl;
+ char *buf;
+ uint32_t family;
+ uint32_t maxattr;
+ unsigned int seq;
+ uint8_t version;
+};
+
+int mnlu_gen_socket_open(struct mnlu_gen_socket *nlg, const char *family_name,
+ uint8_t version);
+void mnlu_gen_socket_close(struct mnlu_gen_socket *nlg);
+struct nlmsghdr *
+_mnlu_gen_socket_cmd_prepare(struct mnlu_gen_socket *nlg,
+ uint8_t cmd, uint16_t flags,
+ uint32_t id, uint8_t version);
+struct nlmsghdr *mnlu_gen_socket_cmd_prepare(struct mnlu_gen_socket *nlg,
+ uint8_t cmd, uint16_t flags);
+int mnlu_gen_socket_sndrcv(struct mnlu_gen_socket *nlg, const struct nlmsghdr *nlh,
+ mnl_cb_t data_cb, void *data);
+
+struct mnl_socket *mnlu_socket_open(int bus);
+struct nlmsghdr *mnlu_msg_prepare(void *buf, uint32_t nlmsg_type, uint16_t flags,
+ void *extra_header, size_t extra_header_size);
+int mnlu_socket_recv_run(struct mnl_socket *nl, unsigned int seq, void *buf, size_t buf_size,
+ mnl_cb_t cb, void *data);
+int mnlu_gen_socket_recv_run(struct mnlu_gen_socket *nlg, mnl_cb_t cb,
+ void *data);
+int mnlu_gen_cmd_dump_policy(struct mnlu_gen_socket *nlg, uint8_t cmd);
+
+#endif /* __MNL_UTILS_H__ */
diff --git a/include/names.h b/include/names.h
new file mode 100644
index 0000000..2fcaacc
--- /dev/null
+++ b/include/names.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef DB_NAMES_H_
+#define DB_NAMES_H_ 1
+
+#define IDNAME_MAX 256
+
+struct db_entry {
+ struct db_entry *next;
+ unsigned int id;
+ char *name;
+};
+
+struct db_names {
+ unsigned int size;
+ struct db_entry *cached;
+ struct db_entry **hash;
+ int max;
+};
+
+struct db_names *db_names_alloc(void);
+int db_names_load(struct db_names *db, const char *path);
+void db_names_free(struct db_names *db);
+
+char *id_to_name(struct db_names *db, int id, char *name);
+
+#endif
diff --git a/include/namespace.h b/include/namespace.h
new file mode 100644
index 0000000..8600054
--- /dev/null
+++ b/include/namespace.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NAMESPACE_H__
+#define __NAMESPACE_H__ 1
+
+#include <sched.h>
+#include <sys/mount.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <errno.h>
+#include <libnetlink.h>
+
+#ifndef NETNS_RUN_DIR
+#define NETNS_RUN_DIR "/var/run/netns"
+#endif
+
+#ifndef NETNS_ETC_DIR
+#define NETNS_ETC_DIR "/etc/netns"
+#endif
+
+#ifndef CLONE_NEWNET
+#define CLONE_NEWNET 0x40000000 /* New network namespace (lo, device, names sockets, etc) */
+#endif
+
+#ifndef MNT_DETACH
+#define MNT_DETACH 0x00000002 /* Just detach from the tree */
+#endif /* MNT_DETACH */
+
+/* sys/mount.h may be out too old to have these */
+#ifndef MS_REC
+#define MS_REC 16384
+#endif
+
+#ifndef MS_SLAVE
+#define MS_SLAVE (1 << 19)
+#endif
+
+#ifndef MS_SHARED
+#define MS_SHARED (1 << 20)
+#endif
+
+#ifndef HAVE_SETNS
+static inline int setns(int fd, int nstype)
+{
+#ifdef __NR_setns
+ return syscall(__NR_setns, fd, nstype);
+#else
+ errno = ENOSYS;
+ return -1;
+#endif
+}
+#endif /* HAVE_SETNS */
+
+int netns_switch(char *netns);
+int netns_get_fd(const char *netns);
+int netns_foreach(int (*func)(char *nsname, void *arg), void *arg);
+
+struct netns_func {
+ int (*func)(char *nsname, void *arg);
+ void *arg;
+};
+
+int netns_id_from_name(struct rtnl_handle *rtnl, const char *name);
+char *netns_name_from_id(int32_t id);
+
+#endif /* __NAMESPACE_H__ */
diff --git a/include/netinet/tcp.h b/include/netinet/tcp.h
new file mode 100644
index 0000000..3f890a1
--- /dev/null
+++ b/include/netinet/tcp.h
@@ -0,0 +1,231 @@
+/*
+ * Copyright (c) 1982, 1986, 1993
+ * The Regents of the University of California. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 4. Neither the name of the University nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * @(#)tcp.h 8.1 (Berkeley) 6/10/93
+ */
+
+#ifndef _NETINET_TCP_H
+#define _NETINET_TCP_H 1
+
+#include <features.h>
+
+/*
+ * User-settable options (used with setsockopt).
+ */
+#define TCP_NODELAY 1 /* Don't delay send to coalesce packets */
+#define TCP_MAXSEG 2 /* Set maximum segment size */
+#define TCP_CORK 3 /* Control sending of partial frames */
+#define TCP_KEEPIDLE 4 /* Start keeplives after this period */
+#define TCP_KEEPINTVL 5 /* Interval between keepalives */
+#define TCP_KEEPCNT 6 /* Number of keepalives before death */
+#define TCP_SYNCNT 7 /* Number of SYN retransmits */
+#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */
+#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */
+#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */
+#define TCP_INFO 11 /* Information about this connection. */
+#define TCP_QUICKACK 12 /* Bock/reenable quick ACKs. */
+#define TCP_CONGESTION 13 /* Congestion control algorithm. */
+
+#ifdef __USE_MISC
+# include <sys/types.h>
+
+# ifdef __FAVOR_BSD
+typedef u_int32_t tcp_seq;
+/*
+ * TCP header.
+ * Per RFC 793, September, 1981.
+ */
+struct tcphdr
+ {
+ u_int16_t th_sport; /* source port */
+ u_int16_t th_dport; /* destination port */
+ tcp_seq th_seq; /* sequence number */
+ tcp_seq th_ack; /* acknowledgement number */
+# if __BYTE_ORDER == __LITTLE_ENDIAN
+ u_int8_t th_x2:4; /* (unused) */
+ u_int8_t th_off:4; /* data offset */
+# endif
+# if __BYTE_ORDER == __BIG_ENDIAN
+ u_int8_t th_off:4; /* data offset */
+ u_int8_t th_x2:4; /* (unused) */
+# endif
+ u_int8_t th_flags;
+# define TH_FIN 0x01
+# define TH_SYN 0x02
+# define TH_RST 0x04
+# define TH_PUSH 0x08
+# define TH_ACK 0x10
+# define TH_URG 0x20
+ u_int16_t th_win; /* window */
+ u_int16_t th_sum; /* checksum */
+ u_int16_t th_urp; /* urgent pointer */
+};
+
+# else /* !__FAVOR_BSD */
+struct tcphdr
+ {
+ u_int16_t source;
+ u_int16_t dest;
+ u_int32_t seq;
+ u_int32_t ack_seq;
+# if __BYTE_ORDER == __LITTLE_ENDIAN
+ u_int16_t res1:4;
+ u_int16_t doff:4;
+ u_int16_t fin:1;
+ u_int16_t syn:1;
+ u_int16_t rst:1;
+ u_int16_t psh:1;
+ u_int16_t ack:1;
+ u_int16_t urg:1;
+ u_int16_t res2:2;
+# elif __BYTE_ORDER == __BIG_ENDIAN
+ u_int16_t doff:4;
+ u_int16_t res1:4;
+ u_int16_t res2:2;
+ u_int16_t urg:1;
+ u_int16_t ack:1;
+ u_int16_t psh:1;
+ u_int16_t rst:1;
+ u_int16_t syn:1;
+ u_int16_t fin:1;
+# else
+# error "Adjust your <bits/endian.h> defines"
+# endif
+ u_int16_t window;
+ u_int16_t check;
+ u_int16_t urg_ptr;
+};
+# endif /* __FAVOR_BSD */
+
+enum
+{
+ TCP_ESTABLISHED = 1,
+ TCP_SYN_SENT,
+ TCP_SYN_RECV,
+ TCP_FIN_WAIT1,
+ TCP_FIN_WAIT2,
+ TCP_TIME_WAIT,
+ TCP_CLOSE,
+ TCP_CLOSE_WAIT,
+ TCP_LAST_ACK,
+ TCP_LISTEN,
+ TCP_CLOSING /* now a valid state */
+};
+
+# define TCPOPT_EOL 0
+# define TCPOPT_NOP 1
+# define TCPOPT_MAXSEG 2
+# define TCPOLEN_MAXSEG 4
+# define TCPOPT_WINDOW 3
+# define TCPOLEN_WINDOW 3
+# define TCPOPT_SACK_PERMITTED 4 /* Experimental */
+# define TCPOLEN_SACK_PERMITTED 2
+# define TCPOPT_SACK 5 /* Experimental */
+# define TCPOPT_TIMESTAMP 8
+# define TCPOLEN_TIMESTAMP 10
+# define TCPOLEN_TSTAMP_APPA (TCPOLEN_TIMESTAMP+2) /* appendix A */
+
+# define TCPOPT_TSTAMP_HDR \
+ (TCPOPT_NOP<<24|TCPOPT_NOP<<16|TCPOPT_TIMESTAMP<<8|TCPOLEN_TIMESTAMP)
+
+/*
+ * Default maximum segment size for TCP.
+ * With an IP MSS of 576, this is 536,
+ * but 512 is probably more convenient.
+ * This should be defined as MIN(512, IP_MSS - sizeof (struct tcpiphdr)).
+ */
+# define TCP_MSS 512
+
+# define TCP_MAXWIN 65535 /* largest value for (unscaled) window */
+
+# define TCP_MAX_WINSHIFT 14 /* maximum window shift */
+
+# define SOL_TCP 6 /* TCP level */
+
+
+# define TCPI_OPT_TIMESTAMPS 1
+# define TCPI_OPT_SACK 2
+# define TCPI_OPT_WSCALE 4
+# define TCPI_OPT_ECN 8
+# define TCPI_OPT_ECN_SEEN 16
+
+/* Values for tcpi_state. */
+enum tcp_ca_state
+{
+ TCP_CA_Open = 0,
+ TCP_CA_Disorder = 1,
+ TCP_CA_CWR = 2,
+ TCP_CA_Recovery = 3,
+ TCP_CA_Loss = 4
+};
+
+struct tcp_info
+{
+ u_int8_t tcpi_state;
+ u_int8_t tcpi_ca_state;
+ u_int8_t tcpi_retransmits;
+ u_int8_t tcpi_probes;
+ u_int8_t tcpi_backoff;
+ u_int8_t tcpi_options;
+ u_int8_t tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;
+
+ u_int32_t tcpi_rto;
+ u_int32_t tcpi_ato;
+ u_int32_t tcpi_snd_mss;
+ u_int32_t tcpi_rcv_mss;
+
+ u_int32_t tcpi_unacked;
+ u_int32_t tcpi_sacked;
+ u_int32_t tcpi_lost;
+ u_int32_t tcpi_retrans;
+ u_int32_t tcpi_fackets;
+
+ /* Times. */
+ u_int32_t tcpi_last_data_sent;
+ u_int32_t tcpi_last_ack_sent; /* Not remembered, sorry. */
+ u_int32_t tcpi_last_data_recv;
+ u_int32_t tcpi_last_ack_recv;
+
+ /* Metrics. */
+ u_int32_t tcpi_pmtu;
+ u_int32_t tcpi_rcv_ssthresh;
+ u_int32_t tcpi_rtt;
+ u_int32_t tcpi_rttvar;
+ u_int32_t tcpi_snd_ssthresh;
+ u_int32_t tcpi_snd_cwnd;
+ u_int32_t tcpi_advmss;
+ u_int32_t tcpi_reordering;
+ u_int32_t tcpi_rcv_rtt;
+ u_int32_t tcpi_rcv_space;
+ u_int32_t tcpi_total_retrans;
+
+};
+
+#endif /* Misc. */
+
+#endif /* netinet/tcp.h */
diff --git a/include/rt_names.h b/include/rt_names.h
new file mode 100644
index 0000000..0275030
--- /dev/null
+++ b/include/rt_names.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef RT_NAMES_H_
+#define RT_NAMES_H_ 1
+
+#include <asm/types.h>
+
+const char *rtnl_rtprot_n2a(int id, char *buf, int len);
+const char *rtnl_addrprot_n2a(__u8 id, char *buf, int len);
+const char *rtnl_rtscope_n2a(int id, char *buf, int len);
+const char *rtnl_rttable_n2a(__u32 id, char *buf, int len);
+const char *rtnl_rtrealm_n2a(int id, char *buf, int len);
+const char *rtnl_dsfield_n2a(int id, char *buf, int len);
+const char *rtnl_dsfield_get_name(int id);
+const char *rtnl_group_n2a(int id, char *buf, int len);
+
+int rtnl_rtprot_a2n(__u32 *id, const char *arg);
+int rtnl_addrprot_a2n(__u8 *id, const char *arg);
+int rtnl_rtscope_a2n(__u32 *id, const char *arg);
+int rtnl_rttable_a2n(__u32 *id, const char *arg);
+int rtnl_rtrealm_a2n(__u32 *id, const char *arg);
+int rtnl_dsfield_a2n(__u32 *id, const char *arg);
+int rtnl_group_a2n(int *id, const char *arg);
+
+const char *inet_proto_n2a(int proto, char *buf, int len);
+int inet_proto_a2n(const char *buf);
+
+
+const char * ll_type_n2a(int type, char *buf, int len);
+const char *ll_addr_n2a(const unsigned char *addr, int alen,
+ int type, char *buf, int blen);
+int ll_addr_a2n(char *lladdr, int len, const char *arg);
+
+const char * ll_proto_n2a(unsigned short id, char *buf, int len);
+int ll_proto_a2n(unsigned short *id, const char *buf);
+
+const char *ppp_proto_n2a(unsigned short id, char *buf, int len);
+int ppp_proto_a2n(unsigned short *id, const char *buf);
+
+const char *nl_proto_n2a(int id, char *buf, int len);
+int nl_proto_a2n(__u32 *id, const char *arg);
+
+int protodown_reason_a2n(__u32 *id, const char *arg);
+int protodown_reason_n2a(int id, char *buf, int len);
+
+extern int numeric;
+
+#endif
diff --git a/include/rtm_map.h b/include/rtm_map.h
new file mode 100644
index 0000000..f85e52c
--- /dev/null
+++ b/include/rtm_map.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __RTM_MAP_H__
+#define __RTM_MAP_H__ 1
+
+char *rtnl_rtntype_n2a(int id, char *buf, int len);
+int rtnl_rtntype_a2n(int *id, char *arg);
+
+int get_rt_realms_or_raw(__u32 *realms, char *arg);
+
+#endif /* __RTM_MAP_H__ */
diff --git a/include/selinux.h b/include/selinux.h
new file mode 100644
index 0000000..592c768
--- /dev/null
+++ b/include/selinux.h
@@ -0,0 +1,10 @@
+#if HAVE_SELINUX
+#include <selinux/selinux.h>
+#else
+int is_selinux_enabled(void);
+void freecon(char *context);
+int getpidcon(pid_t pid, char **context);
+int getfilecon(const char *path, char **context);
+int security_get_initial_context(const char *name, char **context);
+int setexecfilecon(const char *filename, const char *fallback_type);
+#endif
diff --git a/include/uapi/asm-generic/posix_types.h b/include/uapi/asm-generic/posix_types.h
new file mode 100644
index 0000000..2f9c805
--- /dev/null
+++ b/include/uapi/asm-generic/posix_types.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_POSIX_TYPES_H
+#define __ASM_GENERIC_POSIX_TYPES_H
+
+#include <asm/bitsperlong.h>
+/*
+ * This file is generally used by user-level software, so you need to
+ * be a little careful about namespace pollution etc.
+ *
+ * First the types that are often defined in different ways across
+ * architectures, so that you can override them.
+ */
+
+#ifndef __kernel_long_t
+typedef long __kernel_long_t;
+typedef unsigned long __kernel_ulong_t;
+#endif
+
+#ifndef __kernel_ino_t
+typedef __kernel_ulong_t __kernel_ino_t;
+#endif
+
+#ifndef __kernel_mode_t
+typedef unsigned int __kernel_mode_t;
+#endif
+
+#ifndef __kernel_pid_t
+typedef int __kernel_pid_t;
+#endif
+
+#ifndef __kernel_ipc_pid_t
+typedef int __kernel_ipc_pid_t;
+#endif
+
+#ifndef __kernel_uid_t
+typedef unsigned int __kernel_uid_t;
+typedef unsigned int __kernel_gid_t;
+#endif
+
+#ifndef __kernel_suseconds_t
+typedef __kernel_long_t __kernel_suseconds_t;
+#endif
+
+#ifndef __kernel_daddr_t
+typedef int __kernel_daddr_t;
+#endif
+
+#ifndef __kernel_uid32_t
+typedef unsigned int __kernel_uid32_t;
+typedef unsigned int __kernel_gid32_t;
+#endif
+
+#ifndef __kernel_old_uid_t
+typedef __kernel_uid_t __kernel_old_uid_t;
+typedef __kernel_gid_t __kernel_old_gid_t;
+#endif
+
+#ifndef __kernel_old_dev_t
+typedef unsigned int __kernel_old_dev_t;
+#endif
+
+/*
+ * Most 32 bit architectures use "unsigned int" size_t,
+ * and all 64 bit architectures use "unsigned long" size_t.
+ */
+#ifndef __kernel_size_t
+#if __BITS_PER_LONG != 64
+typedef unsigned int __kernel_size_t;
+typedef int __kernel_ssize_t;
+typedef int __kernel_ptrdiff_t;
+#else
+typedef __kernel_ulong_t __kernel_size_t;
+typedef __kernel_long_t __kernel_ssize_t;
+typedef __kernel_long_t __kernel_ptrdiff_t;
+#endif
+#endif
+
+#ifndef __kernel_fsid_t
+typedef struct {
+ int val[2];
+} __kernel_fsid_t;
+#endif
+
+/*
+ * anything below here should be completely generic
+ */
+typedef __kernel_long_t __kernel_off_t;
+typedef long long __kernel_loff_t;
+typedef __kernel_long_t __kernel_old_time_t;
+typedef __kernel_long_t __kernel_time_t;
+typedef long long __kernel_time64_t;
+typedef __kernel_long_t __kernel_clock_t;
+typedef int __kernel_timer_t;
+typedef int __kernel_clockid_t;
+typedef char * __kernel_caddr_t;
+typedef unsigned short __kernel_uid16_t;
+typedef unsigned short __kernel_gid16_t;
+
+#endif /* __ASM_GENERIC_POSIX_TYPES_H */
diff --git a/include/uapi/asm-generic/sockios.h b/include/uapi/asm-generic/sockios.h
new file mode 100644
index 0000000..44fa3ed
--- /dev/null
+++ b/include/uapi/asm-generic/sockios.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_SOCKIOS_H
+#define __ASM_GENERIC_SOCKIOS_H
+
+/* Socket-level I/O control calls. */
+#define FIOSETOWN 0x8901
+#define SIOCSPGRP 0x8902
+#define FIOGETOWN 0x8903
+#define SIOCGPGRP 0x8904
+#define SIOCATMARK 0x8905
+#define SIOCGSTAMP_OLD 0x8906 /* Get stamp (timeval) */
+#define SIOCGSTAMPNS_OLD 0x8907 /* Get stamp (timespec) */
+
+#endif /* __ASM_GENERIC_SOCKIOS_H */
diff --git a/include/uapi/linux/amt.h b/include/uapi/linux/amt.h
new file mode 100644
index 0000000..32aa2a0
--- /dev/null
+++ b/include/uapi/linux/amt.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2021 Taehee Yoo <ap420073@gmail.com>
+ */
+#ifndef _AMT_H_
+#define _AMT_H_
+
+enum ifla_amt_mode {
+ /* AMT interface works as Gateway mode.
+ * The Gateway mode encapsulates IGMP/MLD traffic and decapsulates
+ * multicast traffic.
+ */
+ AMT_MODE_GATEWAY = 0,
+ /* AMT interface works as Relay mode.
+ * The Relay mode encapsulates multicast traffic and decapsulates
+ * IGMP/MLD traffic.
+ */
+ AMT_MODE_RELAY,
+ __AMT_MODE_MAX,
+};
+
+#define AMT_MODE_MAX (__AMT_MODE_MAX - 1)
+
+enum {
+ IFLA_AMT_UNSPEC,
+ /* This attribute specify mode etier Gateway or Relay. */
+ IFLA_AMT_MODE,
+ /* This attribute specify Relay port.
+ * AMT interface is created as Gateway mode, this attribute is used
+ * to specify relay(remote) port.
+ * AMT interface is created as Relay mode, this attribute is used
+ * as local port.
+ */
+ IFLA_AMT_RELAY_PORT,
+ /* This attribute specify Gateway port.
+ * AMT interface is created as Gateway mode, this attribute is used
+ * as local port.
+ * AMT interface is created as Relay mode, this attribute is not used.
+ */
+ IFLA_AMT_GATEWAY_PORT,
+ /* This attribute specify physical device */
+ IFLA_AMT_LINK,
+ /* This attribute specify local ip address */
+ IFLA_AMT_LOCAL_IP,
+ /* This attribute specify Relay ip address.
+ * So, this is not used by Relay.
+ */
+ IFLA_AMT_REMOTE_IP,
+ /* This attribute specify Discovery ip address.
+ * When Gateway get started, it send discovery message to find the
+ * Relay's ip address.
+ * So, this is not used by Relay.
+ */
+ IFLA_AMT_DISCOVERY_IP,
+ /* This attribute specify number of maximum tunnel. */
+ IFLA_AMT_MAX_TUNNELS,
+ __IFLA_AMT_MAX,
+};
+
+#define IFLA_AMT_MAX (__IFLA_AMT_MAX - 1)
+
+#endif /* _AMT_H_ */
diff --git a/include/uapi/linux/atm.h b/include/uapi/linux/atm.h
new file mode 100644
index 0000000..e33ff6b
--- /dev/null
+++ b/include/uapi/linux/atm.h
@@ -0,0 +1,242 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* atm.h - general ATM declarations */
+
+/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */
+
+
+/*
+ * WARNING: User-space programs should not #include <linux/atm.h> directly.
+ * Instead, #include <atm.h>
+ */
+
+#ifndef _LINUX_ATM_H
+#define _LINUX_ATM_H
+
+/*
+ * BEGIN_xx and END_xx markers are used for automatic generation of
+ * documentation. Do not change them.
+ */
+
+
+#include <linux/atmapi.h>
+#include <linux/atmsap.h>
+#include <linux/atmioc.h>
+#include <linux/types.h>
+
+
+/* general ATM constants */
+#define ATM_CELL_SIZE 53 /* ATM cell size incl. header */
+#define ATM_CELL_PAYLOAD 48 /* ATM payload size */
+#define ATM_AAL0_SDU 52 /* AAL0 SDU size */
+#define ATM_MAX_AAL34_PDU 65535 /* maximum AAL3/4 PDU payload */
+#define ATM_AAL5_TRAILER 8 /* AAL5 trailer size */
+#define ATM_MAX_AAL5_PDU 65535 /* maximum AAL5 PDU payload */
+#define ATM_MAX_CDV 9999 /* maximum (default) CDV */
+#define ATM_NOT_RSV_VCI 32 /* first non-reserved VCI value */
+
+#define ATM_MAX_VPI 255 /* maximum VPI at the UNI */
+#define ATM_MAX_VPI_NNI 4096 /* maximum VPI at the NNI */
+#define ATM_MAX_VCI 65535 /* maximum VCI */
+
+
+/* "protcol" values for the socket system call */
+#define ATM_NO_AAL 0 /* AAL not specified */
+#define ATM_AAL0 13 /* "raw" ATM cells */
+#define ATM_AAL1 1 /* AAL1 (CBR) */
+#define ATM_AAL2 2 /* AAL2 (VBR) */
+#define ATM_AAL34 3 /* AAL3/4 (data) */
+#define ATM_AAL5 5 /* AAL5 (data) */
+
+/*
+ * socket option name coding functions
+ *
+ * Note that __SO_ENCODE and __SO_LEVEL are somewhat a hack since the
+ * << 22 only reserves 9 bits for the level. On some architectures
+ * SOL_SOCKET is 0xFFFF, so that's a bit of a problem
+ */
+
+#define __SO_ENCODE(l,n,t) ((((l) & 0x1FF) << 22) | ((n) << 16) | \
+ sizeof(t))
+#define __SO_LEVEL_MATCH(c,m) (((c) >> 22) == ((m) & 0x1FF))
+#define __SO_NUMBER(c) (((c) >> 16) & 0x3f)
+#define __SO_SIZE(c) ((c) & 0x3fff)
+
+/*
+ * ATM layer
+ */
+
+#define SO_SETCLP __SO_ENCODE(SOL_ATM,0,int)
+ /* set CLP bit value - TODO */
+#define SO_CIRANGE __SO_ENCODE(SOL_ATM,1,struct atm_cirange)
+ /* connection identifier range; socket must be
+ bound or connected */
+#define SO_ATMQOS __SO_ENCODE(SOL_ATM,2,struct atm_qos)
+ /* Quality of Service setting */
+#define SO_ATMSAP __SO_ENCODE(SOL_ATM,3,struct atm_sap)
+ /* Service Access Point */
+#define SO_ATMPVC __SO_ENCODE(SOL_ATM,4,struct sockaddr_atmpvc)
+ /* "PVC" address (also for SVCs); get only */
+#define SO_MULTIPOINT __SO_ENCODE(SOL_ATM, 5, int)
+ /* make this vc a p2mp */
+
+
+/*
+ * Note @@@: since the socket layers don't really distinguish the control and
+ * the data plane but generally seems to be data plane-centric, any layer is
+ * about equally wrong for the SAP. If you have a better idea about this,
+ * please speak up ...
+ */
+
+
+/* ATM cell header (for AAL0) */
+
+/* BEGIN_CH */
+#define ATM_HDR_GFC_MASK 0xf0000000
+#define ATM_HDR_GFC_SHIFT 28
+#define ATM_HDR_VPI_MASK 0x0ff00000
+#define ATM_HDR_VPI_SHIFT 20
+#define ATM_HDR_VCI_MASK 0x000ffff0
+#define ATM_HDR_VCI_SHIFT 4
+#define ATM_HDR_PTI_MASK 0x0000000e
+#define ATM_HDR_PTI_SHIFT 1
+#define ATM_HDR_CLP 0x00000001
+/* END_CH */
+
+
+/* PTI codings */
+
+/* BEGIN_PTI */
+#define ATM_PTI_US0 0 /* user data cell, congestion not exp, SDU-type 0 */
+#define ATM_PTI_US1 1 /* user data cell, congestion not exp, SDU-type 1 */
+#define ATM_PTI_UCES0 2 /* user data cell, cong. experienced, SDU-type 0 */
+#define ATM_PTI_UCES1 3 /* user data cell, cong. experienced, SDU-type 1 */
+#define ATM_PTI_SEGF5 4 /* segment OAM F5 flow related cell */
+#define ATM_PTI_E2EF5 5 /* end-to-end OAM F5 flow related cell */
+#define ATM_PTI_RSV_RM 6 /* reserved for traffic control/resource mgmt */
+#define ATM_PTI_RSV 7 /* reserved */
+/* END_PTI */
+
+
+/*
+ * The following items should stay in linux/atm.h, which should be linked to
+ * netatm/atm.h
+ */
+
+/* Traffic description */
+
+#define ATM_NONE 0 /* no traffic */
+#define ATM_UBR 1
+#define ATM_CBR 2
+#define ATM_VBR 3
+#define ATM_ABR 4
+#define ATM_ANYCLASS 5 /* compatible with everything */
+
+#define ATM_MAX_PCR -1 /* maximum available PCR */
+
+struct atm_trafprm {
+ unsigned char traffic_class; /* traffic class (ATM_UBR, ...) */
+ int max_pcr; /* maximum PCR in cells per second */
+ int pcr; /* desired PCR in cells per second */
+ int min_pcr; /* minimum PCR in cells per second */
+ int max_cdv; /* maximum CDV in microseconds */
+ int max_sdu; /* maximum SDU in bytes */
+ /* extra params for ABR */
+ unsigned int icr; /* Initial Cell Rate (24-bit) */
+ unsigned int tbe; /* Transient Buffer Exposure (24-bit) */
+ unsigned int frtt : 24; /* Fixed Round Trip Time (24-bit) */
+ unsigned int rif : 4; /* Rate Increment Factor (4-bit) */
+ unsigned int rdf : 4; /* Rate Decrease Factor (4-bit) */
+ unsigned int nrm_pres :1; /* nrm present bit */
+ unsigned int trm_pres :1; /* rm present bit */
+ unsigned int adtf_pres :1; /* adtf present bit */
+ unsigned int cdf_pres :1; /* cdf present bit*/
+ unsigned int nrm :3; /* Max # of Cells for each forward RM cell (3-bit) */
+ unsigned int trm :3; /* Time between forward RM cells (3-bit) */
+ unsigned int adtf :10; /* ACR Decrease Time Factor (10-bit) */
+ unsigned int cdf :3; /* Cutoff Decrease Factor (3-bit) */
+ unsigned int spare :9; /* spare bits */
+};
+
+struct atm_qos {
+ struct atm_trafprm txtp; /* parameters in TX direction */
+ struct atm_trafprm rxtp __ATM_API_ALIGN;
+ /* parameters in RX direction */
+ unsigned char aal __ATM_API_ALIGN;
+};
+
+/* PVC addressing */
+
+#define ATM_ITF_ANY -1 /* "magic" PVC address values */
+#define ATM_VPI_ANY -1
+#define ATM_VCI_ANY -1
+#define ATM_VPI_UNSPEC -2
+#define ATM_VCI_UNSPEC -2
+
+
+struct sockaddr_atmpvc {
+ unsigned short sap_family; /* address family, AF_ATMPVC */
+ struct { /* PVC address */
+ short itf; /* ATM interface */
+ short vpi; /* VPI (only 8 bits at UNI) */
+ int vci; /* VCI (only 16 bits at UNI) */
+ } sap_addr __ATM_API_ALIGN; /* PVC address */
+};
+
+/* SVC addressing */
+
+#define ATM_ESA_LEN 20 /* ATM End System Address length */
+#define ATM_E164_LEN 12 /* maximum E.164 number length */
+
+#define ATM_AFI_DCC 0x39 /* DCC ATM Format */
+#define ATM_AFI_ICD 0x47 /* ICD ATM Format */
+#define ATM_AFI_E164 0x45 /* E.164 ATM Format */
+#define ATM_AFI_LOCAL 0x49 /* Local ATM Format */
+
+#define ATM_AFI_DCC_GROUP 0xBD /* DCC ATM Group Format */
+#define ATM_AFI_ICD_GROUP 0xC5 /* ICD ATM Group Format */
+#define ATM_AFI_E164_GROUP 0xC3 /* E.164 ATM Group Format */
+#define ATM_AFI_LOCAL_GROUP 0xC7 /* Local ATM Group Format */
+
+#define ATM_LIJ_NONE 0 /* no leaf-initiated join */
+#define ATM_LIJ 1 /* request joining */
+#define ATM_LIJ_RPJ 2 /* set to root-prompted join */
+#define ATM_LIJ_NJ 3 /* set to network join */
+
+
+struct sockaddr_atmsvc {
+ unsigned short sas_family; /* address family, AF_ATMSVC */
+ struct { /* SVC address */
+ unsigned char prv[ATM_ESA_LEN];/* private ATM address */
+ char pub[ATM_E164_LEN+1]; /* public address (E.164) */
+ /* unused addresses must be bzero'ed */
+ char lij_type; /* role in LIJ call; one of ATM_LIJ* */
+ __u32 lij_id; /* LIJ call identifier */
+ } sas_addr __ATM_API_ALIGN; /* SVC address */
+};
+
+
+static __inline__ int atmsvc_addr_in_use(struct sockaddr_atmsvc addr)
+{
+ return *addr.sas_addr.prv || *addr.sas_addr.pub;
+}
+
+
+static __inline__ int atmpvc_addr_in_use(struct sockaddr_atmpvc addr)
+{
+ return addr.sap_addr.itf || addr.sap_addr.vpi || addr.sap_addr.vci;
+}
+
+
+/*
+ * Some stuff for linux/sockios.h
+ */
+
+struct atmif_sioc {
+ int number;
+ int length;
+ void *arg;
+};
+
+
+typedef unsigned short atm_backend_t;
+#endif /* _LINUX_ATM_H */
diff --git a/include/uapi/linux/atmapi.h b/include/uapi/linux/atmapi.h
new file mode 100644
index 0000000..c9bf5c2
--- /dev/null
+++ b/include/uapi/linux/atmapi.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* atmapi.h - ATM API user space/kernel compatibility */
+
+/* Written 1999,2000 by Werner Almesberger, EPFL ICA */
+
+
+#ifndef _LINUX_ATMAPI_H
+#define _LINUX_ATMAPI_H
+
+#if defined(__sparc__) || defined(__ia64__)
+/* such alignment is not required on 32 bit sparcs, but we can't
+ figure that we are on a sparc64 while compiling user-space programs. */
+#define __ATM_API_ALIGN __attribute__((aligned(8)))
+#else
+#define __ATM_API_ALIGN
+#endif
+
+
+/*
+ * Opaque type for kernel pointers. Note that _ is never accessed. We need
+ * the struct in order hide the array, so that we can make simple assignments
+ * instead of being forced to use memcpy. It also improves error reporting for
+ * code that still assumes that we're passing unsigned longs.
+ *
+ * Convention: NULL pointers are passed as a field of all zeroes.
+ */
+
+typedef struct { unsigned char _[8]; } __ATM_API_ALIGN atm_kptr_t;
+
+#endif
diff --git a/include/uapi/linux/atmarp.h b/include/uapi/linux/atmarp.h
new file mode 100644
index 0000000..8e44d12
--- /dev/null
+++ b/include/uapi/linux/atmarp.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* atmarp.h - ATM ARP protocol and kernel-demon interface definitions */
+
+/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */
+
+
+#ifndef _LINUX_ATMARP_H
+#define _LINUX_ATMARP_H
+
+#include <linux/types.h>
+#include <linux/atmapi.h>
+#include <linux/atmioc.h>
+
+
+#define ATMARP_RETRY_DELAY 30 /* request next resolution or forget
+ NAK after 30 sec - should go into
+ atmclip.h */
+#define ATMARP_MAX_UNRES_PACKETS 5 /* queue that many packets while
+ waiting for the resolver */
+
+
+#define ATMARPD_CTRL _IO('a',ATMIOC_CLIP+1) /* become atmarpd ctrl sock */
+#define ATMARP_MKIP _IO('a',ATMIOC_CLIP+2) /* attach socket to IP */
+#define ATMARP_SETENTRY _IO('a',ATMIOC_CLIP+3) /* fill or hide ARP entry */
+#define ATMARP_ENCAP _IO('a',ATMIOC_CLIP+5) /* change encapsulation */
+
+
+enum atmarp_ctrl_type {
+ act_invalid, /* catch uninitialized structures */
+ act_need, /* need address resolution */
+ act_up, /* interface is coming up */
+ act_down, /* interface is going down */
+ act_change /* interface configuration has changed */
+};
+
+struct atmarp_ctrl {
+ enum atmarp_ctrl_type type; /* message type */
+ int itf_num;/* interface number (if present) */
+ __be32 ip; /* IP address (act_need only) */
+};
+
+#endif
diff --git a/include/uapi/linux/atmdev.h b/include/uapi/linux/atmdev.h
new file mode 100644
index 0000000..c95786e
--- /dev/null
+++ b/include/uapi/linux/atmdev.h
@@ -0,0 +1,212 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* atmdev.h - ATM device driver declarations and various related items */
+
+/* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */
+
+
+#ifndef LINUX_ATMDEV_H
+#define LINUX_ATMDEV_H
+
+
+#include <linux/atmapi.h>
+#include <linux/atm.h>
+#include <linux/atmioc.h>
+
+
+#define ESI_LEN 6
+
+#define ATM_OC3_PCR (155520000/270*260/8/53)
+ /* OC3 link rate: 155520000 bps
+ SONET overhead: /270*260 (9 section, 1 path)
+ bits per cell: /8/53
+ max cell rate: 353207.547 cells/sec */
+#define ATM_25_PCR ((25600000/8-8000)/54)
+ /* 25 Mbps ATM cell rate (59111) */
+#define ATM_OC12_PCR (622080000/1080*1040/8/53)
+ /* OC12 link rate: 622080000 bps
+ SONET overhead: /1080*1040
+ bits per cell: /8/53
+ max cell rate: 1412830.188 cells/sec */
+#define ATM_DS3_PCR (8000*12)
+ /* DS3: 12 cells in a 125 usec time slot */
+
+
+#define __AAL_STAT_ITEMS \
+ __HANDLE_ITEM(tx); /* TX okay */ \
+ __HANDLE_ITEM(tx_err); /* TX errors */ \
+ __HANDLE_ITEM(rx); /* RX okay */ \
+ __HANDLE_ITEM(rx_err); /* RX errors */ \
+ __HANDLE_ITEM(rx_drop); /* RX out of memory */
+
+struct atm_aal_stats {
+#define __HANDLE_ITEM(i) int i
+ __AAL_STAT_ITEMS
+#undef __HANDLE_ITEM
+};
+
+
+struct atm_dev_stats {
+ struct atm_aal_stats aal0;
+ struct atm_aal_stats aal34;
+ struct atm_aal_stats aal5;
+} __ATM_API_ALIGN;
+
+
+#define ATM_GETLINKRATE _IOW('a',ATMIOC_ITF+1,struct atmif_sioc)
+ /* get link rate */
+#define ATM_GETNAMES _IOW('a',ATMIOC_ITF+3,struct atm_iobuf)
+ /* get interface names (numbers) */
+#define ATM_GETTYPE _IOW('a',ATMIOC_ITF+4,struct atmif_sioc)
+ /* get interface type name */
+#define ATM_GETESI _IOW('a',ATMIOC_ITF+5,struct atmif_sioc)
+ /* get interface ESI */
+#define ATM_GETADDR _IOW('a',ATMIOC_ITF+6,struct atmif_sioc)
+ /* get itf's local ATM addr. list */
+#define ATM_RSTADDR _IOW('a',ATMIOC_ITF+7,struct atmif_sioc)
+ /* reset itf's ATM address list */
+#define ATM_ADDADDR _IOW('a',ATMIOC_ITF+8,struct atmif_sioc)
+ /* add a local ATM address */
+#define ATM_DELADDR _IOW('a',ATMIOC_ITF+9,struct atmif_sioc)
+ /* remove a local ATM address */
+#define ATM_GETCIRANGE _IOW('a',ATMIOC_ITF+10,struct atmif_sioc)
+ /* get connection identifier range */
+#define ATM_SETCIRANGE _IOW('a',ATMIOC_ITF+11,struct atmif_sioc)
+ /* set connection identifier range */
+#define ATM_SETESI _IOW('a',ATMIOC_ITF+12,struct atmif_sioc)
+ /* set interface ESI */
+#define ATM_SETESIF _IOW('a',ATMIOC_ITF+13,struct atmif_sioc)
+ /* force interface ESI */
+#define ATM_ADDLECSADDR _IOW('a', ATMIOC_ITF+14, struct atmif_sioc)
+ /* register a LECS address */
+#define ATM_DELLECSADDR _IOW('a', ATMIOC_ITF+15, struct atmif_sioc)
+ /* unregister a LECS address */
+#define ATM_GETLECSADDR _IOW('a', ATMIOC_ITF+16, struct atmif_sioc)
+ /* retrieve LECS address(es) */
+
+#define ATM_GETSTAT _IOW('a',ATMIOC_SARCOM+0,struct atmif_sioc)
+ /* get AAL layer statistics */
+#define ATM_GETSTATZ _IOW('a',ATMIOC_SARCOM+1,struct atmif_sioc)
+ /* get AAL layer statistics and zero */
+#define ATM_GETLOOP _IOW('a',ATMIOC_SARCOM+2,struct atmif_sioc)
+ /* get loopback mode */
+#define ATM_SETLOOP _IOW('a',ATMIOC_SARCOM+3,struct atmif_sioc)
+ /* set loopback mode */
+#define ATM_QUERYLOOP _IOW('a',ATMIOC_SARCOM+4,struct atmif_sioc)
+ /* query supported loopback modes */
+#define ATM_SETSC _IOW('a',ATMIOC_SPECIAL+1,int)
+ /* enable or disable single-copy */
+#define ATM_SETBACKEND _IOW('a',ATMIOC_SPECIAL+2,atm_backend_t)
+ /* set backend handler */
+#define ATM_NEWBACKENDIF _IOW('a',ATMIOC_SPECIAL+3,atm_backend_t)
+ /* use backend to make new if */
+#define ATM_ADDPARTY _IOW('a', ATMIOC_SPECIAL+4,struct atm_iobuf)
+ /* add party to p2mp call */
+#define ATM_DROPPARTY _IOW('a', ATMIOC_SPECIAL+5,int)
+ /* drop party from p2mp call */
+
+/*
+ * These are backend handkers that can be set via the ATM_SETBACKEND call
+ * above. In the future we may support dynamic loading of these - for now,
+ * they're just being used to share the ATMIOC_BACKEND ioctls
+ */
+#define ATM_BACKEND_RAW 0
+#define ATM_BACKEND_PPP 1 /* PPPoATM - RFC2364 */
+#define ATM_BACKEND_BR2684 2 /* Bridged RFC1483/2684 */
+
+/* for ATM_GETTYPE */
+#define ATM_ITFTYP_LEN 8 /* maximum length of interface type name */
+
+/*
+ * Loopback modes for ATM_{PHY,SAR}_{GET,SET}LOOP
+ */
+
+/* Point of loopback CPU-->SAR-->PHY-->line--> ... */
+#define __ATM_LM_NONE 0 /* no loop back ^ ^ ^ ^ */
+#define __ATM_LM_AAL 1 /* loop back PDUs --' | | | */
+#define __ATM_LM_ATM 2 /* loop back ATM cells ---' | | */
+/* RESERVED 4 loop back on PHY side ---' */
+#define __ATM_LM_PHY 8 /* loop back bits (digital) ----' | */
+#define __ATM_LM_ANALOG 16 /* loop back the analog signal --------' */
+
+/* Direction of loopback */
+#define __ATM_LM_MKLOC(n) ((n)) /* Local (i.e. loop TX to RX) */
+#define __ATM_LM_MKRMT(n) ((n) << 8) /* Remote (i.e. loop RX to TX) */
+
+#define __ATM_LM_XTLOC(n) ((n) & 0xff)
+#define __ATM_LM_XTRMT(n) (((n) >> 8) & 0xff)
+
+#define ATM_LM_NONE 0 /* no loopback */
+
+#define ATM_LM_LOC_AAL __ATM_LM_MKLOC(__ATM_LM_AAL)
+#define ATM_LM_LOC_ATM __ATM_LM_MKLOC(__ATM_LM_ATM)
+#define ATM_LM_LOC_PHY __ATM_LM_MKLOC(__ATM_LM_PHY)
+#define ATM_LM_LOC_ANALOG __ATM_LM_MKLOC(__ATM_LM_ANALOG)
+
+#define ATM_LM_RMT_AAL __ATM_LM_MKRMT(__ATM_LM_AAL)
+#define ATM_LM_RMT_ATM __ATM_LM_MKRMT(__ATM_LM_ATM)
+#define ATM_LM_RMT_PHY __ATM_LM_MKRMT(__ATM_LM_PHY)
+#define ATM_LM_RMT_ANALOG __ATM_LM_MKRMT(__ATM_LM_ANALOG)
+
+/*
+ * Note: ATM_LM_LOC_* and ATM_LM_RMT_* can be combined, provided that
+ * __ATM_LM_XTLOC(x) <= __ATM_LM_XTRMT(x)
+ */
+
+
+struct atm_iobuf {
+ int length;
+ void *buffer;
+};
+
+/* for ATM_GETCIRANGE / ATM_SETCIRANGE */
+
+#define ATM_CI_MAX -1 /* use maximum range of VPI/VCI */
+
+struct atm_cirange {
+ signed char vpi_bits; /* 1..8, ATM_CI_MAX (-1) for maximum */
+ signed char vci_bits; /* 1..16, ATM_CI_MAX (-1) for maximum */
+};
+
+/* for ATM_SETSC; actually taken from the ATM_VF number space */
+
+#define ATM_SC_RX 1024 /* enable RX single-copy */
+#define ATM_SC_TX 2048 /* enable TX single-copy */
+
+#define ATM_BACKLOG_DEFAULT 32 /* if we get more, we're likely to time out
+ anyway */
+
+/* MF: change_qos (Modify) flags */
+
+#define ATM_MF_IMMED 1 /* Block until change is effective */
+#define ATM_MF_INC_RSV 2 /* Change reservation on increase */
+#define ATM_MF_INC_SHP 4 /* Change shaping on increase */
+#define ATM_MF_DEC_RSV 8 /* Change reservation on decrease */
+#define ATM_MF_DEC_SHP 16 /* Change shaping on decrease */
+#define ATM_MF_BWD 32 /* Set the backward direction parameters */
+
+#define ATM_MF_SET (ATM_MF_INC_RSV | ATM_MF_INC_SHP | ATM_MF_DEC_RSV | \
+ ATM_MF_DEC_SHP | ATM_MF_BWD)
+
+/*
+ * ATM_VS_* are used to express VC state in a human-friendly way.
+ */
+
+#define ATM_VS_IDLE 0 /* VC is not used */
+#define ATM_VS_CONNECTED 1 /* VC is connected */
+#define ATM_VS_CLOSING 2 /* VC is closing */
+#define ATM_VS_LISTEN 3 /* VC is listening for incoming setups */
+#define ATM_VS_INUSE 4 /* VC is in use (registered with atmsigd) */
+#define ATM_VS_BOUND 5 /* VC is bound */
+
+#define ATM_VS2TXT_MAP \
+ "IDLE", "CONNECTED", "CLOSING", "LISTEN", "INUSE", "BOUND"
+
+#define ATM_VF2TXT_MAP \
+ "ADDR", "READY", "PARTIAL", "REGIS", \
+ "RELEASED", "HASQOS", "LISTEN", "META", \
+ "256", "512", "1024", "2048", \
+ "SESSION", "HASSAP", "BOUND", "CLOSE"
+
+
+
+#endif /* LINUX_ATMDEV_H */
diff --git a/include/uapi/linux/atmioc.h b/include/uapi/linux/atmioc.h
new file mode 100644
index 0000000..a9030bc
--- /dev/null
+++ b/include/uapi/linux/atmioc.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* atmioc.h - ranges for ATM-related ioctl numbers */
+
+/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */
+
+
+/*
+ * See https://icawww1.epfl.ch/linux-atm/magic.html for the complete list of
+ * "magic" ioctl numbers.
+ */
+
+
+#ifndef _LINUX_ATMIOC_H
+#define _LINUX_ATMIOC_H
+
+#include <asm/ioctl.h>
+ /* everybody including atmioc.h will also need _IO{,R,W,WR} */
+
+#define ATMIOC_PHYCOM 0x00 /* PHY device common ioctls, globally unique */
+#define ATMIOC_PHYCOM_END 0x0f
+#define ATMIOC_PHYTYP 0x10 /* PHY dev type ioctls, unique per PHY type */
+#define ATMIOC_PHYTYP_END 0x2f
+#define ATMIOC_PHYPRV 0x30 /* PHY dev private ioctls, unique per driver */
+#define ATMIOC_PHYPRV_END 0x4f
+#define ATMIOC_SARCOM 0x50 /* SAR device common ioctls, globally unique */
+#define ATMIOC_SARCOM_END 0x50
+#define ATMIOC_SARPRV 0x60 /* SAR dev private ioctls, unique per driver */
+#define ATMIOC_SARPRV_END 0x7f
+#define ATMIOC_ITF 0x80 /* Interface ioctls, globally unique */
+#define ATMIOC_ITF_END 0x8f
+#define ATMIOC_BACKEND 0x90 /* ATM generic backend ioctls, u. per backend */
+#define ATMIOC_BACKEND_END 0xaf
+/* 0xb0-0xbf: Reserved for future use */
+#define ATMIOC_AREQUIPA 0xc0 /* Application requested IP over ATM, glob. u. */
+#define ATMIOC_LANE 0xd0 /* LAN Emulation, globally unique */
+#define ATMIOC_MPOA 0xd8 /* MPOA, globally unique */
+#define ATMIOC_CLIP 0xe0 /* Classical IP over ATM control, globally u. */
+#define ATMIOC_CLIP_END 0xef
+#define ATMIOC_SPECIAL 0xf0 /* Special-purpose controls, globally unique */
+#define ATMIOC_SPECIAL_END 0xff
+
+#endif
diff --git a/include/uapi/linux/atmsap.h b/include/uapi/linux/atmsap.h
new file mode 100644
index 0000000..fc05248
--- /dev/null
+++ b/include/uapi/linux/atmsap.h
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* atmsap.h - ATM Service Access Point addressing definitions */
+
+/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */
+
+
+#ifndef _LINUX_ATMSAP_H
+#define _LINUX_ATMSAP_H
+
+#include <linux/atmapi.h>
+
+/*
+ * BEGIN_xx and END_xx markers are used for automatic generation of
+ * documentation. Do not change them.
+ */
+
+
+/*
+ * Layer 2 protocol identifiers
+ */
+
+/* BEGIN_L2 */
+#define ATM_L2_NONE 0 /* L2 not specified */
+#define ATM_L2_ISO1745 0x01 /* Basic mode ISO 1745 */
+#define ATM_L2_Q291 0x02 /* ITU-T Q.291 (Rec. I.441) */
+#define ATM_L2_X25_LL 0x06 /* ITU-T X.25, link layer */
+#define ATM_L2_X25_ML 0x07 /* ITU-T X.25, multilink */
+#define ATM_L2_LAPB 0x08 /* Extended LAPB, half-duplex (Rec. T.71) */
+#define ATM_L2_HDLC_ARM 0x09 /* HDLC ARM (ISO/IEC 4335) */
+#define ATM_L2_HDLC_NRM 0x0a /* HDLC NRM (ISO/IEC 4335) */
+#define ATM_L2_HDLC_ABM 0x0b /* HDLC ABM (ISO/IEC 4335) */
+#define ATM_L2_ISO8802 0x0c /* LAN LLC (ISO/IEC 8802/2) */
+#define ATM_L2_X75 0x0d /* ITU-T X.75, SLP */
+#define ATM_L2_Q922 0x0e /* ITU-T Q.922 */
+#define ATM_L2_USER 0x10 /* user-specified */
+#define ATM_L2_ISO7776 0x11 /* ISO 7776 DTE-DTE */
+/* END_L2 */
+
+
+/*
+ * Layer 3 protocol identifiers
+ */
+
+/* BEGIN_L3 */
+#define ATM_L3_NONE 0 /* L3 not specified */
+#define ATM_L3_X25 0x06 /* ITU-T X.25, packet layer */
+#define ATM_L3_ISO8208 0x07 /* ISO/IEC 8208 */
+#define ATM_L3_X223 0x08 /* ITU-T X.223 | ISO/IEC 8878 */
+#define ATM_L3_ISO8473 0x09 /* ITU-T X.233 | ISO/IEC 8473 */
+#define ATM_L3_T70 0x0a /* ITU-T T.70 minimum network layer */
+#define ATM_L3_TR9577 0x0b /* ISO/IEC TR 9577 */
+#define ATM_L3_H310 0x0c /* ITU-T Recommendation H.310 */
+#define ATM_L3_H321 0x0d /* ITU-T Recommendation H.321 */
+#define ATM_L3_USER 0x10 /* user-specified */
+/* END_L3 */
+
+
+/*
+ * High layer identifiers
+ */
+
+/* BEGIN_HL */
+#define ATM_HL_NONE 0 /* HL not specified */
+#define ATM_HL_ISO 0x01 /* ISO */
+#define ATM_HL_USER 0x02 /* user-specific */
+#define ATM_HL_HLP 0x03 /* high layer profile - UNI 3.0 only */
+#define ATM_HL_VENDOR 0x04 /* vendor-specific application identifier */
+/* END_HL */
+
+
+/*
+ * ITU-T coded mode of operation
+ */
+
+/* BEGIN_IMD */
+#define ATM_IMD_NONE 0 /* mode not specified */
+#define ATM_IMD_NORMAL 1 /* normal mode of operation */
+#define ATM_IMD_EXTENDED 2 /* extended mode of operation */
+/* END_IMD */
+
+/*
+ * H.310 code points
+ */
+
+#define ATM_TT_NONE 0 /* terminal type not specified */
+#define ATM_TT_RX 1 /* receive only */
+#define ATM_TT_TX 2 /* send only */
+#define ATM_TT_RXTX 3 /* receive and send */
+
+#define ATM_MC_NONE 0 /* no multiplexing */
+#define ATM_MC_TS 1 /* transport stream (TS) */
+#define ATM_MC_TS_FEC 2 /* transport stream with forward error corr. */
+#define ATM_MC_PS 3 /* program stream (PS) */
+#define ATM_MC_PS_FEC 4 /* program stream with forward error corr. */
+#define ATM_MC_H221 5 /* ITU-T Rec. H.221 */
+
+/*
+ * SAP structures
+ */
+
+#define ATM_MAX_HLI 8 /* maximum high-layer information length */
+
+
+struct atm_blli {
+ unsigned char l2_proto; /* layer 2 protocol */
+ union {
+ struct {
+ unsigned char mode; /* mode of operation (ATM_IMD_xxx), 0 if */
+ /* absent */
+ unsigned char window; /* window size (k), 1-127 (0 to omit) */
+ } itu; /* ITU-T encoding */
+ unsigned char user; /* user-specified l2 information */
+ } l2;
+ unsigned char l3_proto; /* layer 3 protocol */
+ union {
+ struct {
+ unsigned char mode; /* mode of operation (ATM_IMD_xxx), 0 if */
+ /* absent */
+ unsigned char def_size; /* default packet size (log2), 4-12 (0 to */
+ /* omit) */
+ unsigned char window;/* packet window size, 1-127 (0 to omit) */
+ } itu; /* ITU-T encoding */
+ unsigned char user; /* user specified l3 information */
+ struct { /* if l3_proto = ATM_L3_H310 */
+ unsigned char term_type; /* terminal type */
+ unsigned char fw_mpx_cap; /* forward multiplexing capability */
+ /* only if term_type != ATM_TT_NONE */
+ unsigned char bw_mpx_cap; /* backward multiplexing capability */
+ /* only if term_type != ATM_TT_NONE */
+ } h310;
+ struct { /* if l3_proto = ATM_L3_TR9577 */
+ unsigned char ipi; /* initial protocol id */
+ unsigned char snap[5];/* IEEE 802.1 SNAP identifier */
+ /* (only if ipi == NLPID_IEEE802_1_SNAP) */
+ } tr9577;
+ } l3;
+} __ATM_API_ALIGN;
+
+
+struct atm_bhli {
+ unsigned char hl_type; /* high layer information type */
+ unsigned char hl_length; /* length (only if hl_type == ATM_HL_USER || */
+ /* hl_type == ATM_HL_ISO) */
+ unsigned char hl_info[ATM_MAX_HLI];/* high layer information */
+};
+
+
+#define ATM_MAX_BLLI 3 /* maximum number of BLLI elements */
+
+
+struct atm_sap {
+ struct atm_bhli bhli; /* local SAP, high-layer information */
+ struct atm_blli blli[ATM_MAX_BLLI] __ATM_API_ALIGN;
+ /* local SAP, low-layer info */
+};
+
+
+static __inline__ int blli_in_use(struct atm_blli blli)
+{
+ return blli.l2_proto || blli.l3_proto;
+}
+
+#endif
diff --git a/include/uapi/linux/ax25.h b/include/uapi/linux/ax25.h
new file mode 100644
index 0000000..b496b9d
--- /dev/null
+++ b/include/uapi/linux/ax25.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * These are the public elements of the Linux kernel AX.25 code. A similar
+ * file netrom.h exists for the NET/ROM protocol.
+ */
+
+#ifndef AX25_KERNEL_H
+#define AX25_KERNEL_H
+
+#include <linux/socket.h>
+
+#define AX25_MTU 256
+#define AX25_MAX_DIGIS 8
+
+#define AX25_WINDOW 1
+#define AX25_T1 2
+#define AX25_N2 3
+#define AX25_T3 4
+#define AX25_T2 5
+#define AX25_BACKOFF 6
+#define AX25_EXTSEQ 7
+#define AX25_PIDINCL 8
+#define AX25_IDLE 9
+#define AX25_PACLEN 10
+#define AX25_IAMDIGI 12
+
+#define AX25_KILL 99
+
+#define SIOCAX25GETUID (SIOCPROTOPRIVATE+0)
+#define SIOCAX25ADDUID (SIOCPROTOPRIVATE+1)
+#define SIOCAX25DELUID (SIOCPROTOPRIVATE+2)
+#define SIOCAX25NOUID (SIOCPROTOPRIVATE+3)
+#define SIOCAX25OPTRT (SIOCPROTOPRIVATE+7)
+#define SIOCAX25CTLCON (SIOCPROTOPRIVATE+8)
+#define SIOCAX25GETINFOOLD (SIOCPROTOPRIVATE+9)
+#define SIOCAX25ADDFWD (SIOCPROTOPRIVATE+10)
+#define SIOCAX25DELFWD (SIOCPROTOPRIVATE+11)
+#define SIOCAX25DEVCTL (SIOCPROTOPRIVATE+12)
+#define SIOCAX25GETINFO (SIOCPROTOPRIVATE+13)
+
+#define AX25_SET_RT_IPMODE 2
+
+#define AX25_NOUID_DEFAULT 0
+#define AX25_NOUID_BLOCK 1
+
+typedef struct {
+ char ax25_call[7]; /* 6 call + SSID (shifted ascii!) */
+} ax25_address;
+
+struct sockaddr_ax25 {
+ __kernel_sa_family_t sax25_family;
+ ax25_address sax25_call;
+ int sax25_ndigis;
+ /* Digipeater ax25_address sets follow */
+};
+
+#define sax25_uid sax25_ndigis
+
+struct full_sockaddr_ax25 {
+ struct sockaddr_ax25 fsa_ax25;
+ ax25_address fsa_digipeater[AX25_MAX_DIGIS];
+};
+
+struct ax25_routes_struct {
+ ax25_address port_addr;
+ ax25_address dest_addr;
+ unsigned char digi_count;
+ ax25_address digi_addr[AX25_MAX_DIGIS];
+};
+
+struct ax25_route_opt_struct {
+ ax25_address port_addr;
+ ax25_address dest_addr;
+ int cmd;
+ int arg;
+};
+
+struct ax25_ctl_struct {
+ ax25_address port_addr;
+ ax25_address source_addr;
+ ax25_address dest_addr;
+ unsigned int cmd;
+ unsigned long arg;
+ unsigned char digi_count;
+ ax25_address digi_addr[AX25_MAX_DIGIS];
+};
+
+/* this will go away. Please do not export to user land */
+struct ax25_info_struct_deprecated {
+ unsigned int n2, n2count;
+ unsigned int t1, t1timer;
+ unsigned int t2, t2timer;
+ unsigned int t3, t3timer;
+ unsigned int idle, idletimer;
+ unsigned int state;
+ unsigned int rcv_q, snd_q;
+};
+
+struct ax25_info_struct {
+ unsigned int n2, n2count;
+ unsigned int t1, t1timer;
+ unsigned int t2, t2timer;
+ unsigned int t3, t3timer;
+ unsigned int idle, idletimer;
+ unsigned int state;
+ unsigned int rcv_q, snd_q;
+ unsigned int vs, vr, va, vs_max;
+ unsigned int paclen;
+ unsigned int window;
+};
+
+struct ax25_fwd_struct {
+ ax25_address port_from;
+ ax25_address port_to;
+};
+
+#endif
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
new file mode 100644
index 0000000..ebe2177
--- /dev/null
+++ b/include/uapi/linux/batman_adv.h
@@ -0,0 +1,704 @@
+/* SPDX-License-Identifier: MIT */
+/* Copyright (C) B.A.T.M.A.N. contributors:
+ *
+ * Matthias Schiffer
+ */
+
+#ifndef _LINUX_BATMAN_ADV_H_
+#define _LINUX_BATMAN_ADV_H_
+
+#define BATADV_NL_NAME "batadv"
+
+#define BATADV_NL_MCAST_GROUP_CONFIG "config"
+#define BATADV_NL_MCAST_GROUP_TPMETER "tpmeter"
+
+/**
+ * enum batadv_tt_client_flags - TT client specific flags
+ *
+ * Bits from 0 to 7 are called _remote flags_ because they are sent on the wire.
+ * Bits from 8 to 15 are called _local flags_ because they are used for local
+ * computations only.
+ *
+ * Bits from 4 to 7 - a subset of remote flags - are ensured to be in sync with
+ * the other nodes in the network. To achieve this goal these flags are included
+ * in the TT CRC computation.
+ */
+enum batadv_tt_client_flags {
+ /**
+ * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table
+ */
+ BATADV_TT_CLIENT_DEL = (1 << 0),
+
+ /**
+ * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and
+ * the new update telling its new real location has not been
+ * received/sent yet
+ */
+ BATADV_TT_CLIENT_ROAM = (1 << 1),
+
+ /**
+ * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi
+ * interface. This information is used by the "AP Isolation" feature
+ */
+ BATADV_TT_CLIENT_WIFI = (1 << 4),
+
+ /**
+ * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This
+ * information is used by the Extended Isolation feature
+ */
+ BATADV_TT_CLIENT_ISOLA = (1 << 5),
+
+ /**
+ * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from
+ * the table
+ */
+ BATADV_TT_CLIENT_NOPURGE = (1 << 8),
+
+ /**
+ * @BATADV_TT_CLIENT_NEW: this client has been added to the local table
+ * but has not been announced yet
+ */
+ BATADV_TT_CLIENT_NEW = (1 << 9),
+
+ /**
+ * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it
+ * is kept in the table for one more originator interval for consistency
+ * purposes
+ */
+ BATADV_TT_CLIENT_PENDING = (1 << 10),
+
+ /**
+ * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be
+ * part of the network but no node has already announced it
+ */
+ BATADV_TT_CLIENT_TEMP = (1 << 11),
+};
+
+/**
+ * enum batadv_mcast_flags_priv - Private, own multicast flags
+ *
+ * These are internal, multicast related flags. Currently they describe certain
+ * multicast related attributes of the segment this originator bridges into the
+ * mesh.
+ *
+ * Those attributes are used to determine the public multicast flags this
+ * originator is going to announce via TT.
+ *
+ * For netlink, if BATADV_MCAST_FLAGS_BRIDGED is unset then all querier
+ * related flags are undefined.
+ */
+enum batadv_mcast_flags_priv {
+ /**
+ * @BATADV_MCAST_FLAGS_BRIDGED: There is a bridge on top of the mesh
+ * interface.
+ */
+ BATADV_MCAST_FLAGS_BRIDGED = (1 << 0),
+
+ /**
+ * @BATADV_MCAST_FLAGS_QUERIER_IPV4_EXISTS: Whether an IGMP querier
+ * exists in the mesh
+ */
+ BATADV_MCAST_FLAGS_QUERIER_IPV4_EXISTS = (1 << 1),
+
+ /**
+ * @BATADV_MCAST_FLAGS_QUERIER_IPV6_EXISTS: Whether an MLD querier
+ * exists in the mesh
+ */
+ BATADV_MCAST_FLAGS_QUERIER_IPV6_EXISTS = (1 << 2),
+
+ /**
+ * @BATADV_MCAST_FLAGS_QUERIER_IPV4_SHADOWING: If an IGMP querier
+ * exists, whether it is potentially shadowing multicast listeners
+ * (i.e. querier is behind our own bridge segment)
+ */
+ BATADV_MCAST_FLAGS_QUERIER_IPV4_SHADOWING = (1 << 3),
+
+ /**
+ * @BATADV_MCAST_FLAGS_QUERIER_IPV6_SHADOWING: If an MLD querier
+ * exists, whether it is potentially shadowing multicast listeners
+ * (i.e. querier is behind our own bridge segment)
+ */
+ BATADV_MCAST_FLAGS_QUERIER_IPV6_SHADOWING = (1 << 4),
+};
+
+/**
+ * enum batadv_gw_modes - gateway mode of node
+ */
+enum batadv_gw_modes {
+ /** @BATADV_GW_MODE_OFF: gw mode disabled */
+ BATADV_GW_MODE_OFF,
+
+ /** @BATADV_GW_MODE_CLIENT: send DHCP requests to gw servers */
+ BATADV_GW_MODE_CLIENT,
+
+ /** @BATADV_GW_MODE_SERVER: announce itself as gateway server */
+ BATADV_GW_MODE_SERVER,
+};
+
+/**
+ * enum batadv_nl_attrs - batman-adv netlink attributes
+ */
+enum batadv_nl_attrs {
+ /**
+ * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors
+ */
+ BATADV_ATTR_UNSPEC,
+
+ /**
+ * @BATADV_ATTR_VERSION: batman-adv version string
+ */
+ BATADV_ATTR_VERSION,
+
+ /**
+ * @BATADV_ATTR_ALGO_NAME: name of routing algorithm
+ */
+ BATADV_ATTR_ALGO_NAME,
+
+ /**
+ * @BATADV_ATTR_MESH_IFINDEX: index of the batman-adv interface
+ */
+ BATADV_ATTR_MESH_IFINDEX,
+
+ /**
+ * @BATADV_ATTR_MESH_IFNAME: name of the batman-adv interface
+ */
+ BATADV_ATTR_MESH_IFNAME,
+
+ /**
+ * @BATADV_ATTR_MESH_ADDRESS: mac address of the batman-adv interface
+ */
+ BATADV_ATTR_MESH_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface
+ */
+ BATADV_ATTR_HARD_IFINDEX,
+
+ /**
+ * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface
+ */
+ BATADV_ATTR_HARD_IFNAME,
+
+ /**
+ * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv
+ * interface
+ */
+ BATADV_ATTR_HARD_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_ORIG_ADDRESS: originator mac address
+ */
+ BATADV_ATTR_ORIG_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_TPMETER_RESULT: result of run (see
+ * batadv_tp_meter_status)
+ */
+ BATADV_ATTR_TPMETER_RESULT,
+
+ /**
+ * @BATADV_ATTR_TPMETER_TEST_TIME: time (msec) the run took
+ */
+ BATADV_ATTR_TPMETER_TEST_TIME,
+
+ /**
+ * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run
+ */
+ BATADV_ATTR_TPMETER_BYTES,
+
+ /**
+ * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session
+ */
+ BATADV_ATTR_TPMETER_COOKIE,
+
+ /**
+ * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment
+ */
+ BATADV_ATTR_PAD,
+
+ /**
+ * @BATADV_ATTR_ACTIVE: Flag indicating if the hard interface is active
+ */
+ BATADV_ATTR_ACTIVE,
+
+ /**
+ * @BATADV_ATTR_TT_ADDRESS: Client MAC address
+ */
+ BATADV_ATTR_TT_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_TT_TTVN: Translation table version
+ */
+ BATADV_ATTR_TT_TTVN,
+
+ /**
+ * @BATADV_ATTR_TT_LAST_TTVN: Previous translation table version
+ */
+ BATADV_ATTR_TT_LAST_TTVN,
+
+ /**
+ * @BATADV_ATTR_TT_CRC32: CRC32 over translation table
+ */
+ BATADV_ATTR_TT_CRC32,
+
+ /**
+ * @BATADV_ATTR_TT_VID: VLAN ID
+ */
+ BATADV_ATTR_TT_VID,
+
+ /**
+ * @BATADV_ATTR_TT_FLAGS: Translation table client flags
+ */
+ BATADV_ATTR_TT_FLAGS,
+
+ /**
+ * @BATADV_ATTR_FLAG_BEST: Flags indicating entry is the best
+ */
+ BATADV_ATTR_FLAG_BEST,
+
+ /**
+ * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen
+ */
+ BATADV_ATTR_LAST_SEEN_MSECS,
+
+ /**
+ * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address
+ */
+ BATADV_ATTR_NEIGH_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_TQ: TQ to neighbour
+ */
+ BATADV_ATTR_TQ,
+
+ /**
+ * @BATADV_ATTR_THROUGHPUT: Estimated throughput to Neighbour
+ */
+ BATADV_ATTR_THROUGHPUT,
+
+ /**
+ * @BATADV_ATTR_BANDWIDTH_UP: Reported uplink bandwidth
+ */
+ BATADV_ATTR_BANDWIDTH_UP,
+
+ /**
+ * @BATADV_ATTR_BANDWIDTH_DOWN: Reported downlink bandwidth
+ */
+ BATADV_ATTR_BANDWIDTH_DOWN,
+
+ /**
+ * @BATADV_ATTR_ROUTER: Gateway router MAC address
+ */
+ BATADV_ATTR_ROUTER,
+
+ /**
+ * @BATADV_ATTR_BLA_OWN: Flag indicating own originator
+ */
+ BATADV_ATTR_BLA_OWN,
+
+ /**
+ * @BATADV_ATTR_BLA_ADDRESS: Bridge loop avoidance claim MAC address
+ */
+ BATADV_ATTR_BLA_ADDRESS,
+
+ /**
+ * @BATADV_ATTR_BLA_VID: BLA VLAN ID
+ */
+ BATADV_ATTR_BLA_VID,
+
+ /**
+ * @BATADV_ATTR_BLA_BACKBONE: BLA gateway originator MAC address
+ */
+ BATADV_ATTR_BLA_BACKBONE,
+
+ /**
+ * @BATADV_ATTR_BLA_CRC: BLA CRC
+ */
+ BATADV_ATTR_BLA_CRC,
+
+ /**
+ * @BATADV_ATTR_DAT_CACHE_IP4ADDRESS: Client IPv4 address
+ */
+ BATADV_ATTR_DAT_CACHE_IP4ADDRESS,
+
+ /**
+ * @BATADV_ATTR_DAT_CACHE_HWADDRESS: Client MAC address
+ */
+ BATADV_ATTR_DAT_CACHE_HWADDRESS,
+
+ /**
+ * @BATADV_ATTR_DAT_CACHE_VID: VLAN ID
+ */
+ BATADV_ATTR_DAT_CACHE_VID,
+
+ /**
+ * @BATADV_ATTR_MCAST_FLAGS: Per originator multicast flags
+ */
+ BATADV_ATTR_MCAST_FLAGS,
+
+ /**
+ * @BATADV_ATTR_MCAST_FLAGS_PRIV: Private, own multicast flags
+ */
+ BATADV_ATTR_MCAST_FLAGS_PRIV,
+
+ /**
+ * @BATADV_ATTR_VLANID: VLAN id on top of soft interface
+ */
+ BATADV_ATTR_VLANID,
+
+ /**
+ * @BATADV_ATTR_AGGREGATED_OGMS_ENABLED: whether the batman protocol
+ * messages of the mesh interface shall be aggregated or not.
+ */
+ BATADV_ATTR_AGGREGATED_OGMS_ENABLED,
+
+ /**
+ * @BATADV_ATTR_AP_ISOLATION_ENABLED: whether the data traffic going
+ * from a wireless client to another wireless client will be silently
+ * dropped.
+ */
+ BATADV_ATTR_AP_ISOLATION_ENABLED,
+
+ /**
+ * @BATADV_ATTR_ISOLATION_MARK: the isolation mark which is used to
+ * classify clients as "isolated" by the Extended Isolation feature.
+ */
+ BATADV_ATTR_ISOLATION_MARK,
+
+ /**
+ * @BATADV_ATTR_ISOLATION_MASK: the isolation (bit)mask which is used to
+ * classify clients as "isolated" by the Extended Isolation feature.
+ */
+ BATADV_ATTR_ISOLATION_MASK,
+
+ /**
+ * @BATADV_ATTR_BONDING_ENABLED: whether the data traffic going through
+ * the mesh will be sent using multiple interfaces at the same time.
+ */
+ BATADV_ATTR_BONDING_ENABLED,
+
+ /**
+ * @BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED: whether the bridge loop
+ * avoidance feature is enabled. This feature detects and avoids loops
+ * between the mesh and devices bridged with the soft interface
+ */
+ BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED,
+
+ /**
+ * @BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED: whether the distributed
+ * arp table feature is enabled. This feature uses a distributed hash
+ * table to answer ARP requests without flooding the request through
+ * the whole mesh.
+ */
+ BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED,
+
+ /**
+ * @BATADV_ATTR_FRAGMENTATION_ENABLED: whether the data traffic going
+ * through the mesh will be fragmented or silently discarded if the
+ * packet size exceeds the outgoing interface MTU.
+ */
+ BATADV_ATTR_FRAGMENTATION_ENABLED,
+
+ /**
+ * @BATADV_ATTR_GW_BANDWIDTH_DOWN: defines the download bandwidth which
+ * is propagated by this node if %BATADV_ATTR_GW_BANDWIDTH_MODE was set
+ * to 'server'.
+ */
+ BATADV_ATTR_GW_BANDWIDTH_DOWN,
+
+ /**
+ * @BATADV_ATTR_GW_BANDWIDTH_UP: defines the upload bandwidth which
+ * is propagated by this node if %BATADV_ATTR_GW_BANDWIDTH_MODE was set
+ * to 'server'.
+ */
+ BATADV_ATTR_GW_BANDWIDTH_UP,
+
+ /**
+ * @BATADV_ATTR_GW_MODE: defines the state of the gateway features.
+ * Possible values are specified in enum batadv_gw_modes
+ */
+ BATADV_ATTR_GW_MODE,
+
+ /**
+ * @BATADV_ATTR_GW_SEL_CLASS: defines the selection criteria this node
+ * will use to choose a gateway if gw_mode was set to 'client'.
+ */
+ BATADV_ATTR_GW_SEL_CLASS,
+
+ /**
+ * @BATADV_ATTR_HOP_PENALTY: defines the penalty which will be applied
+ * to an originator message's tq-field on every hop and/or per
+ * hard interface
+ */
+ BATADV_ATTR_HOP_PENALTY,
+
+ /**
+ * @BATADV_ATTR_LOG_LEVEL: bitmask with to define which debug messages
+ * should be send to the debug log/trace ring buffer
+ */
+ BATADV_ATTR_LOG_LEVEL,
+
+ /**
+ * @BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED: whether multicast
+ * optimizations should be replaced by simple broadcast-like flooding
+ * of multicast packets. If set to non-zero then all nodes in the mesh
+ * are going to use classic flooding for any multicast packet with no
+ * optimizations.
+ */
+ BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED,
+
+ /**
+ * @BATADV_ATTR_NETWORK_CODING_ENABLED: whether Network Coding (using
+ * some magic to send fewer wifi packets but still the same content) is
+ * enabled or not.
+ */
+ BATADV_ATTR_NETWORK_CODING_ENABLED,
+
+ /**
+ * @BATADV_ATTR_ORIG_INTERVAL: defines the interval in milliseconds in
+ * which batman sends its protocol messages.
+ */
+ BATADV_ATTR_ORIG_INTERVAL,
+
+ /**
+ * @BATADV_ATTR_ELP_INTERVAL: defines the interval in milliseconds in
+ * which batman emits probing packets for neighbor sensing (ELP).
+ */
+ BATADV_ATTR_ELP_INTERVAL,
+
+ /**
+ * @BATADV_ATTR_THROUGHPUT_OVERRIDE: defines the throughput value to be
+ * used by B.A.T.M.A.N. V when estimating the link throughput using
+ * this interface. If the value is set to 0 then batman-adv will try to
+ * estimate the throughput by itself.
+ */
+ BATADV_ATTR_THROUGHPUT_OVERRIDE,
+
+ /**
+ * @BATADV_ATTR_MULTICAST_FANOUT: defines the maximum number of packet
+ * copies that may be generated for a multicast-to-unicast conversion.
+ * Once this limit is exceeded distribution will fall back to broadcast.
+ */
+ BATADV_ATTR_MULTICAST_FANOUT,
+
+ /* add attributes above here, update the policy in netlink.c */
+
+ /**
+ * @__BATADV_ATTR_AFTER_LAST: internal use
+ */
+ __BATADV_ATTR_AFTER_LAST,
+
+ /**
+ * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available
+ */
+ NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST,
+
+ /**
+ * @BATADV_ATTR_MAX: highest attribute number currently defined
+ */
+ BATADV_ATTR_MAX = __BATADV_ATTR_AFTER_LAST - 1
+};
+
+/**
+ * enum batadv_nl_commands - supported batman-adv netlink commands
+ */
+enum batadv_nl_commands {
+ /**
+ * @BATADV_CMD_UNSPEC: unspecified command to catch errors
+ */
+ BATADV_CMD_UNSPEC,
+
+ /**
+ * @BATADV_CMD_GET_MESH: Get attributes from softif/mesh
+ */
+ BATADV_CMD_GET_MESH,
+
+ /**
+ * @BATADV_CMD_GET_MESH_INFO: Alias for @BATADV_CMD_GET_MESH
+ */
+ BATADV_CMD_GET_MESH_INFO = BATADV_CMD_GET_MESH,
+
+ /**
+ * @BATADV_CMD_TP_METER: Start a tp meter session
+ */
+ BATADV_CMD_TP_METER,
+
+ /**
+ * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session
+ */
+ BATADV_CMD_TP_METER_CANCEL,
+
+ /**
+ * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms.
+ */
+ BATADV_CMD_GET_ROUTING_ALGOS,
+
+ /**
+ * @BATADV_CMD_GET_HARDIF: Get attributes from a hardif of the
+ * current softif
+ */
+ BATADV_CMD_GET_HARDIF,
+
+ /**
+ * @BATADV_CMD_GET_HARDIFS: Alias for @BATADV_CMD_GET_HARDIF
+ */
+ BATADV_CMD_GET_HARDIFS = BATADV_CMD_GET_HARDIF,
+
+ /**
+ * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations
+ */
+ BATADV_CMD_GET_TRANSTABLE_LOCAL,
+
+ /**
+ * @BATADV_CMD_GET_TRANSTABLE_GLOBAL: Query list of global translations
+ */
+ BATADV_CMD_GET_TRANSTABLE_GLOBAL,
+
+ /**
+ * @BATADV_CMD_GET_ORIGINATORS: Query list of originators
+ */
+ BATADV_CMD_GET_ORIGINATORS,
+
+ /**
+ * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours
+ */
+ BATADV_CMD_GET_NEIGHBORS,
+
+ /**
+ * @BATADV_CMD_GET_GATEWAYS: Query list of gateways
+ */
+ BATADV_CMD_GET_GATEWAYS,
+
+ /**
+ * @BATADV_CMD_GET_BLA_CLAIM: Query list of bridge loop avoidance claims
+ */
+ BATADV_CMD_GET_BLA_CLAIM,
+
+ /**
+ * @BATADV_CMD_GET_BLA_BACKBONE: Query list of bridge loop avoidance
+ * backbones
+ */
+ BATADV_CMD_GET_BLA_BACKBONE,
+
+ /**
+ * @BATADV_CMD_GET_DAT_CACHE: Query list of DAT cache entries
+ */
+ BATADV_CMD_GET_DAT_CACHE,
+
+ /**
+ * @BATADV_CMD_GET_MCAST_FLAGS: Query list of multicast flags
+ */
+ BATADV_CMD_GET_MCAST_FLAGS,
+
+ /**
+ * @BATADV_CMD_SET_MESH: Set attributes for softif/mesh
+ */
+ BATADV_CMD_SET_MESH,
+
+ /**
+ * @BATADV_CMD_SET_HARDIF: Set attributes for hardif of the
+ * current softif
+ */
+ BATADV_CMD_SET_HARDIF,
+
+ /**
+ * @BATADV_CMD_GET_VLAN: Get attributes from a VLAN of the
+ * current softif
+ */
+ BATADV_CMD_GET_VLAN,
+
+ /**
+ * @BATADV_CMD_SET_VLAN: Set attributes for VLAN of the
+ * current softif
+ */
+ BATADV_CMD_SET_VLAN,
+
+ /* add new commands above here */
+
+ /**
+ * @__BATADV_CMD_AFTER_LAST: internal use
+ */
+ __BATADV_CMD_AFTER_LAST,
+
+ /**
+ * @BATADV_CMD_MAX: highest used command number
+ */
+ BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1
+};
+
+/**
+ * enum batadv_tp_meter_reason - reason of a tp meter test run stop
+ */
+enum batadv_tp_meter_reason {
+ /**
+ * @BATADV_TP_REASON_COMPLETE: sender finished tp run
+ */
+ BATADV_TP_REASON_COMPLETE = 3,
+
+ /**
+ * @BATADV_TP_REASON_CANCEL: sender was stopped during run
+ */
+ BATADV_TP_REASON_CANCEL = 4,
+
+ /* error status >= 128 */
+
+ /**
+ * @BATADV_TP_REASON_DST_UNREACHABLE: receiver could not be reached or
+ * didn't answer
+ */
+ BATADV_TP_REASON_DST_UNREACHABLE = 128,
+
+ /**
+ * @BATADV_TP_REASON_RESEND_LIMIT: (unused) sender retry reached limit
+ */
+ BATADV_TP_REASON_RESEND_LIMIT = 129,
+
+ /**
+ * @BATADV_TP_REASON_ALREADY_ONGOING: test to or from the same node
+ * already ongoing
+ */
+ BATADV_TP_REASON_ALREADY_ONGOING = 130,
+
+ /**
+ * @BATADV_TP_REASON_MEMORY_ERROR: test was stopped due to low memory
+ */
+ BATADV_TP_REASON_MEMORY_ERROR = 131,
+
+ /**
+ * @BATADV_TP_REASON_CANT_SEND: failed to send via outgoing interface
+ */
+ BATADV_TP_REASON_CANT_SEND = 132,
+
+ /**
+ * @BATADV_TP_REASON_TOO_MANY: too many ongoing sessions
+ */
+ BATADV_TP_REASON_TOO_MANY = 133,
+};
+
+/**
+ * enum batadv_ifla_attrs - batman-adv ifla nested attributes
+ */
+enum batadv_ifla_attrs {
+ /**
+ * @IFLA_BATADV_UNSPEC: unspecified attribute which is not parsed by
+ * rtnetlink
+ */
+ IFLA_BATADV_UNSPEC,
+
+ /**
+ * @IFLA_BATADV_ALGO_NAME: routing algorithm (name) which should be
+ * used by the newly registered batadv net_device.
+ */
+ IFLA_BATADV_ALGO_NAME,
+
+ /* add attributes above here, update the policy in soft-interface.c */
+
+ /**
+ * @__IFLA_BATADV_MAX: internal use
+ */
+ __IFLA_BATADV_MAX,
+};
+
+#define IFLA_BATADV_MAX (__IFLA_BATADV_MAX - 1)
+
+#endif /* _LINUX_BATMAN_ADV_H_ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
new file mode 100644
index 0000000..0a2380a
--- /dev/null
+++ b/include/uapi/linux/bpf.h
@@ -0,0 +1,7368 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef __LINUX_BPF_H__
+#define __LINUX_BPF_H__
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/* Extended instruction set based on top of classic BPF */
+
+/* instruction classes */
+#define BPF_JMP32 0x06 /* jmp mode in word width */
+#define BPF_ALU64 0x07 /* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW 0x18 /* double word (64-bit) */
+#define BPF_MEMSX 0x80 /* load with sign extension */
+#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */
+#define BPF_XADD 0xc0 /* exclusive add - legacy name */
+
+/* alu/jmp fields */
+#define BPF_MOV 0xb0 /* mov reg to reg */
+#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */
+
+/* change endianness of a register */
+#define BPF_END 0xd0 /* flags for endianness conversion: */
+#define BPF_TO_LE 0x00 /* convert to little-endian */
+#define BPF_TO_BE 0x08 /* convert to big-endian */
+#define BPF_FROM_LE BPF_TO_LE
+#define BPF_FROM_BE BPF_TO_BE
+
+/* jmp encodings */
+#define BPF_JNE 0x50 /* jump != */
+#define BPF_JLT 0xa0 /* LT is unsigned, '<' */
+#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */
+#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */
+#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */
+#define BPF_JSLT 0xc0 /* SLT is signed, '<' */
+#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */
+#define BPF_CALL 0x80 /* function call */
+#define BPF_EXIT 0x90 /* function return */
+
+/* atomic op type fields (stored in immediate) */
+#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */
+#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */
+#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */
+
+/* Register numbers */
+enum {
+ BPF_REG_0 = 0,
+ BPF_REG_1,
+ BPF_REG_2,
+ BPF_REG_3,
+ BPF_REG_4,
+ BPF_REG_5,
+ BPF_REG_6,
+ BPF_REG_7,
+ BPF_REG_8,
+ BPF_REG_9,
+ BPF_REG_10,
+ __MAX_BPF_REG,
+};
+
+/* BPF has 10 general purpose 64-bit registers and stack frame. */
+#define MAX_BPF_REG __MAX_BPF_REG
+
+struct bpf_insn {
+ __u8 code; /* opcode */
+ __u8 dst_reg:4; /* dest register */
+ __u8 src_reg:4; /* source register */
+ __s16 off; /* signed offset */
+ __s32 imm; /* signed immediate constant */
+};
+
+/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
+struct bpf_lpm_trie_key {
+ __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */
+ __u8 data[0]; /* Arbitrary size */
+};
+
+struct bpf_cgroup_storage_key {
+ __u64 cgroup_inode_id; /* cgroup inode id */
+ __u32 attach_type; /* program attach type (enum bpf_attach_type) */
+};
+
+enum bpf_cgroup_iter_order {
+ BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+ BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */
+ BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */
+ BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */
+ BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */
+};
+
+union bpf_iter_link_info {
+ struct {
+ __u32 map_fd;
+ } map;
+ struct {
+ enum bpf_cgroup_iter_order order;
+
+ /* At most one of cgroup_fd and cgroup_id can be non-zero. If
+ * both are zero, the walk starts from the default cgroup v2
+ * root. For walking v1 hierarchy, one should always explicitly
+ * specify cgroup_fd.
+ */
+ __u32 cgroup_fd;
+ __u64 cgroup_id;
+ } cgroup;
+ /* Parameters of task iterators. */
+ struct {
+ __u32 tid;
+ __u32 pid;
+ __u32 pid_fd;
+ } task;
+};
+
+/* BPF syscall commands, see bpf(2) man-page for more details. */
+/**
+ * DOC: eBPF Syscall Preamble
+ *
+ * The operation to be performed by the **bpf**\ () system call is determined
+ * by the *cmd* argument. Each operation takes an accompanying argument,
+ * provided via *attr*, which is a pointer to a union of type *bpf_attr* (see
+ * below). The size argument is the size of the union pointed to by *attr*.
+ */
+/**
+ * DOC: eBPF Syscall Commands
+ *
+ * BPF_MAP_CREATE
+ * Description
+ * Create a map and return a file descriptor that refers to the
+ * map. The close-on-exec file descriptor flag (see **fcntl**\ (2))
+ * is automatically enabled for the new file descriptor.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_MAP_CREATE** will delete the map (but see NOTES).
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_MAP_LOOKUP_ELEM
+ * Description
+ * Look up an element with a given *key* in the map referred to
+ * by the file descriptor *map_fd*.
+ *
+ * The *flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_UPDATE_ELEM
+ * Description
+ * Create or update an element (key/value pair) in a specified map.
+ *
+ * The *flags* argument should be specified as one of the
+ * following:
+ *
+ * **BPF_ANY**
+ * Create a new element or update an existing element.
+ * **BPF_NOEXIST**
+ * Create a new element only if it did not exist.
+ * **BPF_EXIST**
+ * Update an existing element.
+ * **BPF_F_LOCK**
+ * Update a spin_lock-ed map element.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**,
+ * **E2BIG**, **EEXIST**, or **ENOENT**.
+ *
+ * **E2BIG**
+ * The number of elements in the map reached the
+ * *max_entries* limit specified at map creation time.
+ * **EEXIST**
+ * If *flags* specifies **BPF_NOEXIST** and the element
+ * with *key* already exists in the map.
+ * **ENOENT**
+ * If *flags* specifies **BPF_EXIST** and the element with
+ * *key* does not exist in the map.
+ *
+ * BPF_MAP_DELETE_ELEM
+ * Description
+ * Look up and delete an element by key in a specified map.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_GET_NEXT_KEY
+ * Description
+ * Look up an element by key in a specified map and return the key
+ * of the next element. Can be used to iterate over all elements
+ * in the map.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * The following cases can be used to iterate over all elements of
+ * the map:
+ *
+ * * If *key* is not found, the operation returns zero and sets
+ * the *next_key* pointer to the key of the first element.
+ * * If *key* is found, the operation returns zero and sets the
+ * *next_key* pointer to the key of the next element.
+ * * If *key* is the last element, returns -1 and *errno* is set
+ * to **ENOENT**.
+ *
+ * May set *errno* to **ENOMEM**, **EFAULT**, **EPERM**, or
+ * **EINVAL** on error.
+ *
+ * BPF_PROG_LOAD
+ * Description
+ * Verify and load an eBPF program, returning a new file
+ * descriptor associated with the program.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_PROG_LOAD** will unload the eBPF program (but see NOTES).
+ *
+ * The close-on-exec file descriptor flag (see **fcntl**\ (2)) is
+ * automatically enabled for the new file descriptor.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_OBJ_PIN
+ * Description
+ * Pin an eBPF program or map referred by the specified *bpf_fd*
+ * to the provided *pathname* on the filesystem.
+ *
+ * The *pathname* argument must not contain a dot (".").
+ *
+ * On success, *pathname* retains a reference to the eBPF object,
+ * preventing deallocation of the object when the original
+ * *bpf_fd* is closed. This allow the eBPF object to live beyond
+ * **close**\ (\ *bpf_fd*\ ), and hence the lifetime of the parent
+ * process.
+ *
+ * Applying **unlink**\ (2) or similar calls to the *pathname*
+ * unpins the object from the filesystem, removing the reference.
+ * If no other file descriptors or filesystem nodes refer to the
+ * same object, it will be deallocated (see NOTES).
+ *
+ * The filesystem type for the parent directory of *pathname* must
+ * be **BPF_FS_MAGIC**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_OBJ_GET
+ * Description
+ * Open a file descriptor for the eBPF object pinned to the
+ * specified *pathname*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_PROG_ATTACH
+ * Description
+ * Attach an eBPF program to a *target_fd* at the specified
+ * *attach_type* hook.
+ *
+ * The *attach_type* specifies the eBPF attachment point to
+ * attach the program to, and must be one of *bpf_attach_type*
+ * (see below).
+ *
+ * The *attach_bpf_fd* must be a valid file descriptor for a
+ * loaded eBPF program of a cgroup, flow dissector, LIRC, sockmap
+ * or sock_ops type corresponding to the specified *attach_type*.
+ *
+ * The *target_fd* must be a valid file descriptor for a kernel
+ * object which depends on the attach type of *attach_bpf_fd*:
+ *
+ * **BPF_PROG_TYPE_CGROUP_DEVICE**,
+ * **BPF_PROG_TYPE_CGROUP_SKB**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+ * **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
+ * **BPF_PROG_TYPE_CGROUP_SYSCTL**,
+ * **BPF_PROG_TYPE_SOCK_OPS**
+ *
+ * Control Group v2 hierarchy with the eBPF controller
+ * enabled. Requires the kernel to be compiled with
+ * **CONFIG_CGROUP_BPF**.
+ *
+ * **BPF_PROG_TYPE_FLOW_DISSECTOR**
+ *
+ * Network namespace (eg /proc/self/ns/net).
+ *
+ * **BPF_PROG_TYPE_LIRC_MODE2**
+ *
+ * LIRC device path (eg /dev/lircN). Requires the kernel
+ * to be compiled with **CONFIG_BPF_LIRC_MODE2**.
+ *
+ * **BPF_PROG_TYPE_SK_SKB**,
+ * **BPF_PROG_TYPE_SK_MSG**
+ *
+ * eBPF map of socket type (eg **BPF_MAP_TYPE_SOCKHASH**).
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_DETACH
+ * Description
+ * Detach the eBPF program associated with the *target_fd* at the
+ * hook specified by *attach_type*. The program must have been
+ * previously attached using **BPF_PROG_ATTACH**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_TEST_RUN
+ * Description
+ * Run the eBPF program associated with the *prog_fd* a *repeat*
+ * number of times against a provided program context *ctx_in* and
+ * data *data_in*, and return the modified program context
+ * *ctx_out*, *data_out* (for example, packet data), result of the
+ * execution *retval*, and *duration* of the test run.
+ *
+ * The sizes of the buffers provided as input and output
+ * parameters *ctx_in*, *ctx_out*, *data_in*, and *data_out* must
+ * be provided in the corresponding variables *ctx_size_in*,
+ * *ctx_size_out*, *data_size_in*, and/or *data_size_out*. If any
+ * of these parameters are not provided (ie set to NULL), the
+ * corresponding size field must be zero.
+ *
+ * Some program types have particular requirements:
+ *
+ * **BPF_PROG_TYPE_SK_LOOKUP**
+ * *data_in* and *data_out* must be NULL.
+ *
+ * **BPF_PROG_TYPE_RAW_TRACEPOINT**,
+ * **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE**
+ *
+ * *ctx_out*, *data_in* and *data_out* must be NULL.
+ * *repeat* must be zero.
+ *
+ * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * **ENOSPC**
+ * Either *data_size_out* or *ctx_size_out* is too small.
+ * **ENOTSUPP**
+ * This command is not supported by the program type of
+ * the program referred to by *prog_fd*.
+ *
+ * BPF_PROG_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF program currently loaded into the kernel.
+ *
+ * Looks for the eBPF program with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF programs
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_MAP_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF map currently loaded into the kernel.
+ *
+ * Looks for the eBPF map with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF maps
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_PROG_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF program corresponding to
+ * *prog_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_MAP_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF map corresponding to
+ * *map_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_OBJ_GET_INFO_BY_FD
+ * Description
+ * Obtain information about the eBPF object corresponding to
+ * *bpf_fd*.
+ *
+ * Populates up to *info_len* bytes of *info*, which will be in
+ * one of the following formats depending on the eBPF object type
+ * of *bpf_fd*:
+ *
+ * * **struct bpf_prog_info**
+ * * **struct bpf_map_info**
+ * * **struct bpf_btf_info**
+ * * **struct bpf_link_info**
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_QUERY
+ * Description
+ * Obtain information about eBPF programs associated with the
+ * specified *attach_type* hook.
+ *
+ * The *target_fd* must be a valid file descriptor for a kernel
+ * object which depends on the attach type of *attach_bpf_fd*:
+ *
+ * **BPF_PROG_TYPE_CGROUP_DEVICE**,
+ * **BPF_PROG_TYPE_CGROUP_SKB**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+ * **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
+ * **BPF_PROG_TYPE_CGROUP_SYSCTL**,
+ * **BPF_PROG_TYPE_SOCK_OPS**
+ *
+ * Control Group v2 hierarchy with the eBPF controller
+ * enabled. Requires the kernel to be compiled with
+ * **CONFIG_CGROUP_BPF**.
+ *
+ * **BPF_PROG_TYPE_FLOW_DISSECTOR**
+ *
+ * Network namespace (eg /proc/self/ns/net).
+ *
+ * **BPF_PROG_TYPE_LIRC_MODE2**
+ *
+ * LIRC device path (eg /dev/lircN). Requires the kernel
+ * to be compiled with **CONFIG_BPF_LIRC_MODE2**.
+ *
+ * **BPF_PROG_QUERY** always fetches the number of programs
+ * attached and the *attach_flags* which were used to attach those
+ * programs. Additionally, if *prog_ids* is nonzero and the number
+ * of attached programs is less than *prog_cnt*, populates
+ * *prog_ids* with the eBPF program ids of the programs attached
+ * at *target_fd*.
+ *
+ * The following flags may alter the result:
+ *
+ * **BPF_F_QUERY_EFFECTIVE**
+ * Only return information regarding programs which are
+ * currently effective at the specified *target_fd*.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_RAW_TRACEPOINT_OPEN
+ * Description
+ * Attach an eBPF program to a tracepoint *name* to access kernel
+ * internal arguments of the tracepoint in their raw form.
+ *
+ * The *prog_fd* must be a valid file descriptor associated with
+ * a loaded eBPF program of type **BPF_PROG_TYPE_RAW_TRACEPOINT**.
+ *
+ * No ABI guarantees are made about the content of tracepoint
+ * arguments exposed to the corresponding eBPF program.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_RAW_TRACEPOINT_OPEN** will delete the map (but see NOTES).
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_BTF_LOAD
+ * Description
+ * Verify and load BPF Type Format (BTF) metadata into the kernel,
+ * returning a new file descriptor associated with the metadata.
+ * BTF is described in more detail at
+ * https://www.kernel.org/doc/html/latest/bpf/btf.html.
+ *
+ * The *btf* parameter must point to valid memory providing
+ * *btf_size* bytes of BTF binary metadata.
+ *
+ * The returned file descriptor can be passed to other **bpf**\ ()
+ * subcommands such as **BPF_PROG_LOAD** or **BPF_MAP_CREATE** to
+ * associate the BTF with those objects.
+ *
+ * Similar to **BPF_PROG_LOAD**, **BPF_BTF_LOAD** has optional
+ * parameters to specify a *btf_log_buf*, *btf_log_size* and
+ * *btf_log_level* which allow the kernel to return freeform log
+ * output regarding the BTF verification process.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_BTF_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the BPF Type Format (BTF)
+ * corresponding to *btf_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_TASK_FD_QUERY
+ * Description
+ * Obtain information about eBPF programs associated with the
+ * target process identified by *pid* and *fd*.
+ *
+ * If the *pid* and *fd* are associated with a tracepoint, kprobe
+ * or uprobe perf event, then the *prog_id* and *fd_type* will
+ * be populated with the eBPF program id and file descriptor type
+ * of type **bpf_task_fd_type**. If associated with a kprobe or
+ * uprobe, the *probe_offset* and *probe_addr* will also be
+ * populated. Optionally, if *buf* is provided, then up to
+ * *buf_len* bytes of *buf* will be populated with the name of
+ * the tracepoint, kprobe or uprobe.
+ *
+ * The resulting *prog_id* may be introspected in deeper detail
+ * using **BPF_PROG_GET_FD_BY_ID** and **BPF_OBJ_GET_INFO_BY_FD**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_LOOKUP_AND_DELETE_ELEM
+ * Description
+ * Look up an element with the given *key* in the map referred to
+ * by the file descriptor *fd*, and if found, delete the element.
+ *
+ * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map
+ * types, the *flags* argument needs to be set to 0, but for other
+ * map types, it may be specified as:
+ *
+ * **BPF_F_LOCK**
+ * Look up and delete the value of a spin-locked map
+ * without returning the lock. This must be specified if
+ * the elements contain a spinlock.
+ *
+ * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types
+ * implement this command as a "pop" operation, deleting the top
+ * element rather than one corresponding to *key*.
+ * The *key* and *key_len* parameters should be zeroed when
+ * issuing this operation for these map types.
+ *
+ * This command is only valid for the following map types:
+ * * **BPF_MAP_TYPE_QUEUE**
+ * * **BPF_MAP_TYPE_STACK**
+ * * **BPF_MAP_TYPE_HASH**
+ * * **BPF_MAP_TYPE_PERCPU_HASH**
+ * * **BPF_MAP_TYPE_LRU_HASH**
+ * * **BPF_MAP_TYPE_LRU_PERCPU_HASH**
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_FREEZE
+ * Description
+ * Freeze the permissions of the specified map.
+ *
+ * Write permissions may be frozen by passing zero *flags*.
+ * Upon success, no future syscall invocations may alter the
+ * map state of *map_fd*. Write operations from eBPF programs
+ * are still possible for a frozen map.
+ *
+ * Not supported for maps of type **BPF_MAP_TYPE_STRUCT_OPS**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_BTF_GET_NEXT_ID
+ * Description
+ * Fetch the next BPF Type Format (BTF) object currently loaded
+ * into the kernel.
+ *
+ * Looks for the BTF object with an id greater than *start_id*
+ * and updates *next_id* on success. If no other BTF objects
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_MAP_LOOKUP_BATCH
+ * Description
+ * Iterate and fetch multiple elements in a map.
+ *
+ * Two opaque values are used to manage batch operations,
+ * *in_batch* and *out_batch*. Initially, *in_batch* must be set
+ * to NULL to begin the batched operation. After each subsequent
+ * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant
+ * *out_batch* as the *in_batch* for the next operation to
+ * continue iteration from the current point.
+ *
+ * The *keys* and *values* are output parameters which must point
+ * to memory large enough to hold *count* items based on the key
+ * and value size of the map *map_fd*. The *keys* buffer must be
+ * of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * The *elem_flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * On success, *count* elements from the map are copied into the
+ * user buffer, with the keys copied into *keys* and the values
+ * copied into the corresponding indices in *values*.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **ENOSPC** to indicate that *keys* or
+ * *values* is too small to dump an entire bucket during
+ * iteration of a hash-based map type.
+ *
+ * BPF_MAP_LOOKUP_AND_DELETE_BATCH
+ * Description
+ * Iterate and delete all elements in a map.
+ *
+ * This operation has the same behavior as
+ * **BPF_MAP_LOOKUP_BATCH** with two exceptions:
+ *
+ * * Every element that is successfully returned is also deleted
+ * from the map. This is at least *count* elements. Note that
+ * *count* is both an input and an output parameter.
+ * * Upon returning with *errno* set to **EFAULT**, up to
+ * *count* elements may be deleted without returning the keys
+ * and values of the deleted elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_UPDATE_BATCH
+ * Description
+ * Update multiple elements in a map by *key*.
+ *
+ * The *keys* and *values* are input parameters which must point
+ * to memory large enough to hold *count* items based on the key
+ * and value size of the map *map_fd*. The *keys* buffer must be
+ * of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * Each element specified in *keys* is sequentially updated to the
+ * value in the corresponding index in *values*. The *in_batch*
+ * and *out_batch* parameters are ignored and should be zeroed.
+ *
+ * The *elem_flags* argument should be specified as one of the
+ * following:
+ *
+ * **BPF_ANY**
+ * Create new elements or update a existing elements.
+ * **BPF_NOEXIST**
+ * Create new elements only if they do not exist.
+ * **BPF_EXIST**
+ * Update existing elements.
+ * **BPF_F_LOCK**
+ * Update spin_lock-ed map elements. This must be
+ * specified if the map value contains a spinlock.
+ *
+ * On success, *count* elements from the map are updated.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, or
+ * **E2BIG**. **E2BIG** indicates that the number of elements in
+ * the map reached the *max_entries* limit specified at map
+ * creation time.
+ *
+ * May set *errno* to one of the following error codes under
+ * specific circumstances:
+ *
+ * **EEXIST**
+ * If *flags* specifies **BPF_NOEXIST** and the element
+ * with *key* already exists in the map.
+ * **ENOENT**
+ * If *flags* specifies **BPF_EXIST** and the element with
+ * *key* does not exist in the map.
+ *
+ * BPF_MAP_DELETE_BATCH
+ * Description
+ * Delete multiple elements in a map by *key*.
+ *
+ * The *keys* parameter is an input parameter which must point
+ * to memory large enough to hold *count* items based on the key
+ * size of the map *map_fd*, that is, *key_size* * *count*.
+ *
+ * Each element specified in *keys* is sequentially deleted. The
+ * *in_batch*, *out_batch*, and *values* parameters are ignored
+ * and should be zeroed.
+ *
+ * The *elem_flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * On success, *count* elements from the map are updated.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements. If
+ * *errno* is **EFAULT**, up to *count* elements may be been
+ * deleted.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_LINK_CREATE
+ * Description
+ * Attach an eBPF program to a *target_fd* at the specified
+ * *attach_type* hook and return a file descriptor handle for
+ * managing the link.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_UPDATE
+ * Description
+ * Update the eBPF program in the specified *link_fd* to
+ * *new_prog_fd*.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_LINK_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF Link corresponding to
+ * *link_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF link currently loaded into the kernel.
+ *
+ * Looks for the eBPF link with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF links
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_ENABLE_STATS
+ * Description
+ * Enable eBPF runtime statistics gathering.
+ *
+ * Runtime statistics gathering for the eBPF runtime is disabled
+ * by default to minimize the corresponding performance overhead.
+ * This command enables statistics globally.
+ *
+ * Multiple programs may independently enable statistics.
+ * After gathering the desired statistics, eBPF runtime statistics
+ * may be disabled again by calling **close**\ (2) for the file
+ * descriptor returned by this function. Statistics will only be
+ * disabled system-wide when all outstanding file descriptors
+ * returned by prior calls for this subcommand are closed.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_ITER_CREATE
+ * Description
+ * Create an iterator on top of the specified *link_fd* (as
+ * previously created using **BPF_LINK_CREATE**) and return a
+ * file descriptor that can be used to trigger the iteration.
+ *
+ * If the resulting file descriptor is pinned to the filesystem
+ * using **BPF_OBJ_PIN**, then subsequent **read**\ (2) syscalls
+ * for that path will trigger the iterator to read kernel state
+ * using the eBPF program attached to *link_fd*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_DETACH
+ * Description
+ * Forcefully detach the specified *link_fd* from its
+ * corresponding attachment point.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_BIND_MAP
+ * Description
+ * Bind a map to the lifetime of an eBPF program.
+ *
+ * The map identified by *map_fd* is bound to the program
+ * identified by *prog_fd* and only released when *prog_fd* is
+ * released. This may be used in cases where metadata should be
+ * associated with a program which otherwise does not contain any
+ * references to the map (for example, embedded in the eBPF
+ * program instructions).
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * NOTES
+ * eBPF objects (maps and programs) can be shared between processes.
+ *
+ * * After **fork**\ (2), the child inherits file descriptors
+ * referring to the same eBPF objects.
+ * * File descriptors referring to eBPF objects can be transferred over
+ * **unix**\ (7) domain sockets.
+ * * File descriptors referring to eBPF objects can be duplicated in the
+ * usual way, using **dup**\ (2) and similar calls.
+ * * File descriptors referring to eBPF objects can be pinned to the
+ * filesystem using the **BPF_OBJ_PIN** command of **bpf**\ (2).
+ *
+ * An eBPF object is deallocated only after all file descriptors referring
+ * to the object have been closed and no references remain pinned to the
+ * filesystem or attached (for example, bound to a program or device).
+ */
+enum bpf_cmd {
+ BPF_MAP_CREATE,
+ BPF_MAP_LOOKUP_ELEM,
+ BPF_MAP_UPDATE_ELEM,
+ BPF_MAP_DELETE_ELEM,
+ BPF_MAP_GET_NEXT_KEY,
+ BPF_PROG_LOAD,
+ BPF_OBJ_PIN,
+ BPF_OBJ_GET,
+ BPF_PROG_ATTACH,
+ BPF_PROG_DETACH,
+ BPF_PROG_TEST_RUN,
+ BPF_PROG_RUN = BPF_PROG_TEST_RUN,
+ BPF_PROG_GET_NEXT_ID,
+ BPF_MAP_GET_NEXT_ID,
+ BPF_PROG_GET_FD_BY_ID,
+ BPF_MAP_GET_FD_BY_ID,
+ BPF_OBJ_GET_INFO_BY_FD,
+ BPF_PROG_QUERY,
+ BPF_RAW_TRACEPOINT_OPEN,
+ BPF_BTF_LOAD,
+ BPF_BTF_GET_FD_BY_ID,
+ BPF_TASK_FD_QUERY,
+ BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+ BPF_MAP_FREEZE,
+ BPF_BTF_GET_NEXT_ID,
+ BPF_MAP_LOOKUP_BATCH,
+ BPF_MAP_LOOKUP_AND_DELETE_BATCH,
+ BPF_MAP_UPDATE_BATCH,
+ BPF_MAP_DELETE_BATCH,
+ BPF_LINK_CREATE,
+ BPF_LINK_UPDATE,
+ BPF_LINK_GET_FD_BY_ID,
+ BPF_LINK_GET_NEXT_ID,
+ BPF_ENABLE_STATS,
+ BPF_ITER_CREATE,
+ BPF_LINK_DETACH,
+ BPF_PROG_BIND_MAP,
+};
+
+enum bpf_map_type {
+ BPF_MAP_TYPE_UNSPEC,
+ BPF_MAP_TYPE_HASH,
+ BPF_MAP_TYPE_ARRAY,
+ BPF_MAP_TYPE_PROG_ARRAY,
+ BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ BPF_MAP_TYPE_PERCPU_HASH,
+ BPF_MAP_TYPE_PERCPU_ARRAY,
+ BPF_MAP_TYPE_STACK_TRACE,
+ BPF_MAP_TYPE_CGROUP_ARRAY,
+ BPF_MAP_TYPE_LRU_HASH,
+ BPF_MAP_TYPE_LRU_PERCPU_HASH,
+ BPF_MAP_TYPE_LPM_TRIE,
+ BPF_MAP_TYPE_ARRAY_OF_MAPS,
+ BPF_MAP_TYPE_HASH_OF_MAPS,
+ BPF_MAP_TYPE_DEVMAP,
+ BPF_MAP_TYPE_SOCKMAP,
+ BPF_MAP_TYPE_CPUMAP,
+ BPF_MAP_TYPE_XSKMAP,
+ BPF_MAP_TYPE_SOCKHASH,
+ BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
+ /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching
+ * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to
+ * both cgroup-attached and other progs and supports all functionality
+ * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark
+ * BPF_MAP_TYPE_CGROUP_STORAGE deprecated.
+ */
+ BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
+ BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+ BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
+ /* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs
+ * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE +
+ * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+ * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+ * deprecated.
+ */
+ BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
+ BPF_MAP_TYPE_QUEUE,
+ BPF_MAP_TYPE_STACK,
+ BPF_MAP_TYPE_SK_STORAGE,
+ BPF_MAP_TYPE_DEVMAP_HASH,
+ BPF_MAP_TYPE_STRUCT_OPS,
+ BPF_MAP_TYPE_RINGBUF,
+ BPF_MAP_TYPE_INODE_STORAGE,
+ BPF_MAP_TYPE_TASK_STORAGE,
+ BPF_MAP_TYPE_BLOOM_FILTER,
+ BPF_MAP_TYPE_USER_RINGBUF,
+ BPF_MAP_TYPE_CGRP_STORAGE,
+};
+
+/* Note that tracing related programs such as
+ * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT}
+ * are not subject to a stable API since kernel internal data
+ * structures can change from release to release and may
+ * therefore break existing tracing BPF programs. Tracing BPF
+ * programs correspond to /a/ specific kernel which is to be
+ * analyzed, and not /a/ specific kernel /and/ all future ones.
+ */
+enum bpf_prog_type {
+ BPF_PROG_TYPE_UNSPEC,
+ BPF_PROG_TYPE_SOCKET_FILTER,
+ BPF_PROG_TYPE_KPROBE,
+ BPF_PROG_TYPE_SCHED_CLS,
+ BPF_PROG_TYPE_SCHED_ACT,
+ BPF_PROG_TYPE_TRACEPOINT,
+ BPF_PROG_TYPE_XDP,
+ BPF_PROG_TYPE_PERF_EVENT,
+ BPF_PROG_TYPE_CGROUP_SKB,
+ BPF_PROG_TYPE_CGROUP_SOCK,
+ BPF_PROG_TYPE_LWT_IN,
+ BPF_PROG_TYPE_LWT_OUT,
+ BPF_PROG_TYPE_LWT_XMIT,
+ BPF_PROG_TYPE_SOCK_OPS,
+ BPF_PROG_TYPE_SK_SKB,
+ BPF_PROG_TYPE_CGROUP_DEVICE,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_RAW_TRACEPOINT,
+ BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ BPF_PROG_TYPE_LWT_SEG6LOCAL,
+ BPF_PROG_TYPE_LIRC_MODE2,
+ BPF_PROG_TYPE_SK_REUSEPORT,
+ BPF_PROG_TYPE_FLOW_DISSECTOR,
+ BPF_PROG_TYPE_CGROUP_SYSCTL,
+ BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+ BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_PROG_TYPE_TRACING,
+ BPF_PROG_TYPE_STRUCT_OPS,
+ BPF_PROG_TYPE_EXT,
+ BPF_PROG_TYPE_LSM,
+ BPF_PROG_TYPE_SK_LOOKUP,
+ BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
+ BPF_PROG_TYPE_NETFILTER,
+};
+
+enum bpf_attach_type {
+ BPF_CGROUP_INET_INGRESS,
+ BPF_CGROUP_INET_EGRESS,
+ BPF_CGROUP_INET_SOCK_CREATE,
+ BPF_CGROUP_SOCK_OPS,
+ BPF_SK_SKB_STREAM_PARSER,
+ BPF_SK_SKB_STREAM_VERDICT,
+ BPF_CGROUP_DEVICE,
+ BPF_SK_MSG_VERDICT,
+ BPF_CGROUP_INET4_BIND,
+ BPF_CGROUP_INET6_BIND,
+ BPF_CGROUP_INET4_CONNECT,
+ BPF_CGROUP_INET6_CONNECT,
+ BPF_CGROUP_INET4_POST_BIND,
+ BPF_CGROUP_INET6_POST_BIND,
+ BPF_CGROUP_UDP4_SENDMSG,
+ BPF_CGROUP_UDP6_SENDMSG,
+ BPF_LIRC_MODE2,
+ BPF_FLOW_DISSECTOR,
+ BPF_CGROUP_SYSCTL,
+ BPF_CGROUP_UDP4_RECVMSG,
+ BPF_CGROUP_UDP6_RECVMSG,
+ BPF_CGROUP_GETSOCKOPT,
+ BPF_CGROUP_SETSOCKOPT,
+ BPF_TRACE_RAW_TP,
+ BPF_TRACE_FENTRY,
+ BPF_TRACE_FEXIT,
+ BPF_MODIFY_RETURN,
+ BPF_LSM_MAC,
+ BPF_TRACE_ITER,
+ BPF_CGROUP_INET4_GETPEERNAME,
+ BPF_CGROUP_INET6_GETPEERNAME,
+ BPF_CGROUP_INET4_GETSOCKNAME,
+ BPF_CGROUP_INET6_GETSOCKNAME,
+ BPF_XDP_DEVMAP,
+ BPF_CGROUP_INET_SOCK_RELEASE,
+ BPF_XDP_CPUMAP,
+ BPF_SK_LOOKUP,
+ BPF_XDP,
+ BPF_SK_SKB_VERDICT,
+ BPF_SK_REUSEPORT_SELECT,
+ BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
+ BPF_PERF_EVENT,
+ BPF_TRACE_KPROBE_MULTI,
+ BPF_LSM_CGROUP,
+ BPF_STRUCT_OPS,
+ BPF_NETFILTER,
+ BPF_TCX_INGRESS,
+ BPF_TCX_EGRESS,
+ BPF_TRACE_UPROBE_MULTI,
+ BPF_CGROUP_UNIX_CONNECT,
+ BPF_CGROUP_UNIX_SENDMSG,
+ BPF_CGROUP_UNIX_RECVMSG,
+ BPF_CGROUP_UNIX_GETPEERNAME,
+ BPF_CGROUP_UNIX_GETSOCKNAME,
+ BPF_NETKIT_PRIMARY,
+ BPF_NETKIT_PEER,
+ __MAX_BPF_ATTACH_TYPE
+};
+
+#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+
+enum bpf_link_type {
+ BPF_LINK_TYPE_UNSPEC = 0,
+ BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
+ BPF_LINK_TYPE_TRACING = 2,
+ BPF_LINK_TYPE_CGROUP = 3,
+ BPF_LINK_TYPE_ITER = 4,
+ BPF_LINK_TYPE_NETNS = 5,
+ BPF_LINK_TYPE_XDP = 6,
+ BPF_LINK_TYPE_PERF_EVENT = 7,
+ BPF_LINK_TYPE_KPROBE_MULTI = 8,
+ BPF_LINK_TYPE_STRUCT_OPS = 9,
+ BPF_LINK_TYPE_NETFILTER = 10,
+ BPF_LINK_TYPE_TCX = 11,
+ BPF_LINK_TYPE_UPROBE_MULTI = 12,
+ BPF_LINK_TYPE_NETKIT = 13,
+ __MAX_BPF_LINK_TYPE,
+};
+
+#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE
+
+enum bpf_perf_event_type {
+ BPF_PERF_EVENT_UNSPEC = 0,
+ BPF_PERF_EVENT_UPROBE = 1,
+ BPF_PERF_EVENT_URETPROBE = 2,
+ BPF_PERF_EVENT_KPROBE = 3,
+ BPF_PERF_EVENT_KRETPROBE = 4,
+ BPF_PERF_EVENT_TRACEPOINT = 5,
+ BPF_PERF_EVENT_EVENT = 6,
+};
+
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of
+ * programs for a cgroup. Though it's possible to replace an old program at
+ * any position by also specifying BPF_F_REPLACE flag and position itself in
+ * replace_bpf_fd attribute. Old program at this position will be released.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ * cgrp2 (OVERRIDE prog C) ->
+ * cgrp3 (MULTI prog D) ->
+ * cgrp4 (OVERRIDE prog E) ->
+ * cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
+ */
+#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+#define BPF_F_ALLOW_MULTI (1U << 1)
+/* Generic attachment flags. */
+#define BPF_F_REPLACE (1U << 2)
+#define BPF_F_BEFORE (1U << 3)
+#define BPF_F_AFTER (1U << 4)
+#define BPF_F_ID (1U << 5)
+#define BPF_F_LINK BPF_F_LINK /* 1 << 13 */
+
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT (1U << 0)
+
+/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will allow any alignment whatsoever. On platforms
+ * with strict alignment requirements for loads ands stores (such
+ * as sparc and mips) the verifier validates that all loads and
+ * stores provably follow this requirement. This flag turns that
+ * checking and enforcement off.
+ *
+ * It is mostly used for testing when we want to validate the
+ * context and memory access aspects of the verifier, but because
+ * of an unaligned access the alignment check would trigger before
+ * the one we are interested in.
+ */
+#define BPF_F_ANY_ALIGNMENT (1U << 1)
+
+/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose.
+ * Verifier does sub-register def/use analysis and identifies instructions whose
+ * def only matters for low 32-bit, high 32-bit is never referenced later
+ * through implicit zero extension. Therefore verifier notifies JIT back-ends
+ * that it is safe to ignore clearing high 32-bit for these instructions. This
+ * saves some back-ends a lot of code-gen. However such optimization is not
+ * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends
+ * hence hasn't used verifier's analysis result. But, we really want to have a
+ * way to be able to verify the correctness of the described optimization on
+ * x86_64 on which testsuites are frequently exercised.
+ *
+ * So, this flag is introduced. Once it is set, verifier will randomize high
+ * 32-bit for those instructions who has been identified as safe to ignore them.
+ * Then, if verifier is not doing correct analysis, such randomization will
+ * regress tests to expose bugs.
+ */
+#define BPF_F_TEST_RND_HI32 (1U << 2)
+
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_STATE_FREQ (1U << 3)
+
+/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will
+ * restrict map and helper usage for such programs. Sleepable BPF programs can
+ * only be attached to hooks where kernel execution context allows sleeping.
+ * Such programs are allowed to use helpers that may sleep like
+ * bpf_copy_from_user().
+ */
+#define BPF_F_SLEEPABLE (1U << 4)
+
+/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp frags.
+ */
+#define BPF_F_XDP_HAS_FRAGS (1U << 5)
+
+/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded
+ * program becomes device-bound but can access XDP metadata.
+ */
+#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6)
+
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_REG_INVARIANTS (1U << 7)
+
+/* link_create.kprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
+ */
+enum {
+ BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
+};
+
+/* link_create.uprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_UPROBE_MULTI attach type to create return probe.
+ */
+enum {
+ BPF_F_UPROBE_MULTI_RETURN = (1U << 0)
+};
+
+/* link_create.netfilter.flags used in LINK_CREATE command for
+ * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
+ */
+#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * the following extensions:
+ *
+ * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX]
+ * insn[0].imm: map fd or fd_idx
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of map
+ * verifier type: CONST_PTR_TO_MAP
+ */
+#define BPF_PSEUDO_MAP_FD 1
+#define BPF_PSEUDO_MAP_IDX 5
+
+/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE
+ * insn[0].imm: map fd or fd_idx
+ * insn[1].imm: offset into value
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of map[0]+offset
+ * verifier type: PTR_TO_MAP_VALUE
+ */
+#define BPF_PSEUDO_MAP_VALUE 2
+#define BPF_PSEUDO_MAP_IDX_VALUE 6
+
+/* insn[0].src_reg: BPF_PSEUDO_BTF_ID
+ * insn[0].imm: kernel btd id of VAR
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of the kernel variable
+ * verifier type: PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ * is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID 3
+/* insn[0].src_reg: BPF_PSEUDO_FUNC
+ * insn[0].imm: insn offset to the func
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of the function
+ * verifier type: PTR_TO_FUNC.
+ */
+#define BPF_PSEUDO_FUNC 4
+
+/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
+ * offset to another bpf function
+ */
+#define BPF_PSEUDO_CALL 1
+/* when bpf_call->src_reg == BPF_PSEUDO_KFUNC_CALL,
+ * bpf_call->imm == btf_id of a BTF_KIND_FUNC in the running kernel
+ */
+#define BPF_PSEUDO_KFUNC_CALL 2
+
+/* flags for BPF_MAP_UPDATE_ELEM command */
+enum {
+ BPF_ANY = 0, /* create new element or update existing */
+ BPF_NOEXIST = 1, /* create new element if it didn't exist */
+ BPF_EXIST = 2, /* update existing element */
+ BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */
+};
+
+/* flags for BPF_MAP_CREATE command */
+enum {
+ BPF_F_NO_PREALLOC = (1U << 0),
+/* Instead of having one common LRU list in the
+ * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
+ * which can scale and perform better.
+ * Note, the LRU nodes (including free nodes) cannot be moved
+ * across different LRU lists.
+ */
+ BPF_F_NO_COMMON_LRU = (1U << 1),
+/* Specify numa node during map creation */
+ BPF_F_NUMA_NODE = (1U << 2),
+
+/* Flags for accessing BPF object from syscall side. */
+ BPF_F_RDONLY = (1U << 3),
+ BPF_F_WRONLY = (1U << 4),
+
+/* Flag for stack_map, store build_id+offset instead of pointer */
+ BPF_F_STACK_BUILD_ID = (1U << 5),
+
+/* Zero-initialize hash function seed. This should only be used for testing. */
+ BPF_F_ZERO_SEED = (1U << 6),
+
+/* Flags for accessing BPF object from program side. */
+ BPF_F_RDONLY_PROG = (1U << 7),
+ BPF_F_WRONLY_PROG = (1U << 8),
+
+/* Clone map from listener for newly accepted socket */
+ BPF_F_CLONE = (1U << 9),
+
+/* Enable memory-mapping BPF map */
+ BPF_F_MMAPABLE = (1U << 10),
+
+/* Share perf_event among processes */
+ BPF_F_PRESERVE_ELEMS = (1U << 11),
+
+/* Create a map that is suitable to be an inner map with dynamic max entries */
+ BPF_F_INNER_MAP = (1U << 12),
+
+/* Create a map that will be registered/unregesitered by the backed bpf_link */
+ BPF_F_LINK = (1U << 13),
+
+/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */
+ BPF_F_PATH_FD = (1U << 14),
+};
+
+/* Flags for BPF_PROG_QUERY. */
+
+/* Query effective (directly attached + inherited from ancestor cgroups)
+ * programs that will be executed for events within a cgroup.
+ * attach_flags with this flag are always returned 0.
+ */
+#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU (1U << 0)
+/* If set, XDP frames will be transmitted after processing */
+#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1)
+
+/* type for BPF_ENABLE_STATS */
+enum bpf_stats_type {
+ /* enabled run_time_ns and run_cnt */
+ BPF_STATS_RUN_TIME = 0,
+};
+
+enum bpf_stack_build_id_status {
+ /* user space need an empty entry to identify end of a trace */
+ BPF_STACK_BUILD_ID_EMPTY = 0,
+ /* with valid build_id and offset */
+ BPF_STACK_BUILD_ID_VALID = 1,
+ /* couldn't get build_id, fallback to ip */
+ BPF_STACK_BUILD_ID_IP = 2,
+};
+
+#define BPF_BUILD_ID_SIZE 20
+struct bpf_stack_build_id {
+ __s32 status;
+ unsigned char build_id[BPF_BUILD_ID_SIZE];
+ union {
+ __u64 offset;
+ __u64 ip;
+ };
+};
+
+#define BPF_OBJ_NAME_LEN 16U
+
+union bpf_attr {
+ struct { /* anonymous struct used by BPF_MAP_CREATE command */
+ __u32 map_type; /* one of enum bpf_map_type */
+ __u32 key_size; /* size of key in bytes */
+ __u32 value_size; /* size of value in bytes */
+ __u32 max_entries; /* max number of entries in a map */
+ __u32 map_flags; /* BPF_MAP_CREATE related
+ * flags defined above.
+ */
+ __u32 inner_map_fd; /* fd pointing to the inner map */
+ __u32 numa_node; /* numa node (effective only if
+ * BPF_F_NUMA_NODE is set).
+ */
+ char map_name[BPF_OBJ_NAME_LEN];
+ __u32 map_ifindex; /* ifindex of netdev to create on */
+ __u32 btf_fd; /* fd pointing to a BTF type data */
+ __u32 btf_key_type_id; /* BTF type_id of the key */
+ __u32 btf_value_type_id; /* BTF type_id of the value */
+ __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel-
+ * struct stored as the
+ * map value
+ */
+ /* Any per-map-type extra fields
+ *
+ * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
+ * number of hash functions (if 0, the bloom filter will default
+ * to using 5 hash functions).
+ */
+ __u64 map_extra;
+ };
+
+ struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
+ __u32 map_fd;
+ __aligned_u64 key;
+ union {
+ __aligned_u64 value;
+ __aligned_u64 next_key;
+ };
+ __u64 flags;
+ };
+
+ struct { /* struct used by BPF_MAP_*_BATCH commands */
+ __aligned_u64 in_batch; /* start batch,
+ * NULL to start from beginning
+ */
+ __aligned_u64 out_batch; /* output: next start batch */
+ __aligned_u64 keys;
+ __aligned_u64 values;
+ __u32 count; /* input/output:
+ * input: # of key/value
+ * elements
+ * output: # of filled elements
+ */
+ __u32 map_fd;
+ __u64 elem_flags;
+ __u64 flags;
+ } batch;
+
+ struct { /* anonymous struct used by BPF_PROG_LOAD command */
+ __u32 prog_type; /* one of enum bpf_prog_type */
+ __u32 insn_cnt;
+ __aligned_u64 insns;
+ __aligned_u64 license;
+ __u32 log_level; /* verbosity level of verifier */
+ __u32 log_size; /* size of user buffer */
+ __aligned_u64 log_buf; /* user supplied buffer */
+ __u32 kern_version; /* not used */
+ __u32 prog_flags;
+ char prog_name[BPF_OBJ_NAME_LEN];
+ __u32 prog_ifindex; /* ifindex of netdev to prep for */
+ /* For some prog types expected attach type must be known at
+ * load time to verify attach type specific parts of prog
+ * (context accesses, allowed helpers, etc).
+ */
+ __u32 expected_attach_type;
+ __u32 prog_btf_fd; /* fd pointing to BTF type data */
+ __u32 func_info_rec_size; /* userspace bpf_func_info size */
+ __aligned_u64 func_info; /* func info */
+ __u32 func_info_cnt; /* number of bpf_func_info records */
+ __u32 line_info_rec_size; /* userspace bpf_line_info size */
+ __aligned_u64 line_info; /* line info */
+ __u32 line_info_cnt; /* number of bpf_line_info records */
+ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */
+ union {
+ /* valid prog_fd to attach to bpf prog */
+ __u32 attach_prog_fd;
+ /* or valid module BTF object fd or 0 to attach to vmlinux */
+ __u32 attach_btf_obj_fd;
+ };
+ __u32 core_relo_cnt; /* number of bpf_core_relo */
+ __aligned_u64 fd_array; /* array of FDs */
+ __aligned_u64 core_relos;
+ __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */
+ /* output: actual total log contents size (including termintaing zero).
+ * It could be both larger than original log_size (if log was
+ * truncated), or smaller (if log buffer wasn't filled completely).
+ */
+ __u32 log_true_size;
+ };
+
+ struct { /* anonymous struct used by BPF_OBJ_* commands */
+ __aligned_u64 pathname;
+ __u32 bpf_fd;
+ __u32 file_flags;
+ /* Same as dirfd in openat() syscall; see openat(2)
+ * manpage for details of path FD and pathname semantics;
+ * path_fd should accompanied by BPF_F_PATH_FD flag set in
+ * file_flags field, otherwise it should be set to zero;
+ * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed.
+ */
+ __s32 path_fd;
+ };
+
+ struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
+ union {
+ __u32 target_fd; /* target object to attach to or ... */
+ __u32 target_ifindex; /* target ifindex */
+ };
+ __u32 attach_bpf_fd;
+ __u32 attach_type;
+ __u32 attach_flags;
+ __u32 replace_bpf_fd;
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
+ };
+
+ struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
+ __u32 prog_fd;
+ __u32 retval;
+ __u32 data_size_in; /* input: len of data_in */
+ __u32 data_size_out; /* input/output: len of data_out
+ * returns ENOSPC if data_out
+ * is too small.
+ */
+ __aligned_u64 data_in;
+ __aligned_u64 data_out;
+ __u32 repeat;
+ __u32 duration;
+ __u32 ctx_size_in; /* input: len of ctx_in */
+ __u32 ctx_size_out; /* input/output: len of ctx_out
+ * returns ENOSPC if ctx_out
+ * is too small.
+ */
+ __aligned_u64 ctx_in;
+ __aligned_u64 ctx_out;
+ __u32 flags;
+ __u32 cpu;
+ __u32 batch_size;
+ } test;
+
+ struct { /* anonymous struct used by BPF_*_GET_*_ID */
+ union {
+ __u32 start_id;
+ __u32 prog_id;
+ __u32 map_id;
+ __u32 btf_id;
+ __u32 link_id;
+ };
+ __u32 next_id;
+ __u32 open_flags;
+ };
+
+ struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
+ __u32 bpf_fd;
+ __u32 info_len;
+ __aligned_u64 info;
+ } info;
+
+ struct { /* anonymous struct used by BPF_PROG_QUERY command */
+ union {
+ __u32 target_fd; /* target object to query or ... */
+ __u32 target_ifindex; /* target ifindex */
+ };
+ __u32 attach_type;
+ __u32 query_flags;
+ __u32 attach_flags;
+ __aligned_u64 prog_ids;
+ union {
+ __u32 prog_cnt;
+ __u32 count;
+ };
+ __u32 :32;
+ /* output: per-program attach_flags.
+ * not allowed to be set during effective query.
+ */
+ __aligned_u64 prog_attach_flags;
+ __aligned_u64 link_ids;
+ __aligned_u64 link_attach_flags;
+ __u64 revision;
+ } query;
+
+ struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
+ __u64 name;
+ __u32 prog_fd;
+ } raw_tracepoint;
+
+ struct { /* anonymous struct for BPF_BTF_LOAD */
+ __aligned_u64 btf;
+ __aligned_u64 btf_log_buf;
+ __u32 btf_size;
+ __u32 btf_log_size;
+ __u32 btf_log_level;
+ /* output: actual total log contents size (including termintaing zero).
+ * It could be both larger than original log_size (if log was
+ * truncated), or smaller (if log buffer wasn't filled completely).
+ */
+ __u32 btf_log_true_size;
+ };
+
+ struct {
+ __u32 pid; /* input: pid */
+ __u32 fd; /* input: fd */
+ __u32 flags; /* input: flags */
+ __u32 buf_len; /* input/output: buf len */
+ __aligned_u64 buf; /* input/output:
+ * tp_name for tracepoint
+ * symbol for kprobe
+ * filename for uprobe
+ */
+ __u32 prog_id; /* output: prod_id */
+ __u32 fd_type; /* output: BPF_FD_TYPE_* */
+ __u64 probe_offset; /* output: probe_offset */
+ __u64 probe_addr; /* output: probe_addr */
+ } task_fd_query;
+
+ struct { /* struct used by BPF_LINK_CREATE command */
+ union {
+ __u32 prog_fd; /* eBPF program to attach */
+ __u32 map_fd; /* struct_ops to attach */
+ };
+ union {
+ __u32 target_fd; /* target object to attach to or ... */
+ __u32 target_ifindex; /* target ifindex */
+ };
+ __u32 attach_type; /* attach type */
+ __u32 flags; /* extra flags */
+ union {
+ __u32 target_btf_id; /* btf_id of target to attach to */
+ struct {
+ __aligned_u64 iter_info; /* extra bpf_iter_link_info */
+ __u32 iter_info_len; /* iter_info length */
+ };
+ struct {
+ /* black box user-provided value passed through
+ * to BPF program at the execution time and
+ * accessible through bpf_get_attach_cookie() BPF helper
+ */
+ __u64 bpf_cookie;
+ } perf_event;
+ struct {
+ __u32 flags;
+ __u32 cnt;
+ __aligned_u64 syms;
+ __aligned_u64 addrs;
+ __aligned_u64 cookies;
+ } kprobe_multi;
+ struct {
+ /* this is overlaid with the target_btf_id above. */
+ __u32 target_btf_id;
+ /* black box user-provided value passed through
+ * to BPF program at the execution time and
+ * accessible through bpf_get_attach_cookie() BPF helper
+ */
+ __u64 cookie;
+ } tracing;
+ struct {
+ __u32 pf;
+ __u32 hooknum;
+ __s32 priority;
+ __u32 flags;
+ } netfilter;
+ struct {
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
+ } tcx;
+ struct {
+ __aligned_u64 path;
+ __aligned_u64 offsets;
+ __aligned_u64 ref_ctr_offsets;
+ __aligned_u64 cookies;
+ __u32 cnt;
+ __u32 flags;
+ __u32 pid;
+ } uprobe_multi;
+ struct {
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
+ } netkit;
+ };
+ } link_create;
+
+ struct { /* struct used by BPF_LINK_UPDATE command */
+ __u32 link_fd; /* link fd */
+ union {
+ /* new program fd to update link with */
+ __u32 new_prog_fd;
+ /* new struct_ops map fd to update link with */
+ __u32 new_map_fd;
+ };
+ __u32 flags; /* extra flags */
+ union {
+ /* expected link's program fd; is specified only if
+ * BPF_F_REPLACE flag is set in flags.
+ */
+ __u32 old_prog_fd;
+ /* expected link's map fd; is specified only
+ * if BPF_F_REPLACE flag is set.
+ */
+ __u32 old_map_fd;
+ };
+ } link_update;
+
+ struct {
+ __u32 link_fd;
+ } link_detach;
+
+ struct { /* struct used by BPF_ENABLE_STATS command */
+ __u32 type;
+ } enable_stats;
+
+ struct { /* struct used by BPF_ITER_CREATE command */
+ __u32 link_fd;
+ __u32 flags;
+ } iter_create;
+
+ struct { /* struct used by BPF_PROG_BIND_MAP command */
+ __u32 prog_fd;
+ __u32 map_fd;
+ __u32 flags; /* extra flags */
+ } prog_bind_map;
+
+} __attribute__((aligned(8)));
+
+/* The description below is an attempt at providing documentation to eBPF
+ * developers about the multiple available eBPF helper functions. It can be
+ * parsed and used to produce a manual page. The workflow is the following,
+ * and requires the rst2man utility:
+ *
+ * $ ./scripts/bpf_doc.py \
+ * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst
+ * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7
+ * $ man /tmp/bpf-helpers.7
+ *
+ * Note that in order to produce this external documentation, some RST
+ * formatting is used in the descriptions to get "bold" and "italics" in
+ * manual pages. Also note that the few trailing white spaces are
+ * intentional, removing them would break paragraphs for rst2man.
+ *
+ * Start of BPF helper function descriptions:
+ *
+ * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key)
+ * Description
+ * Perform a lookup in *map* for an entry associated to *key*.
+ * Return
+ * Map value associated to *key*, or **NULL** if no entry was
+ * found.
+ *
+ * long bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags)
+ * Description
+ * Add or update the value of the entry associated to *key* in
+ * *map* with *value*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * Flag value **BPF_NOEXIST** cannot be used for maps of types
+ * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all
+ * elements always exist), the helper would return an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_map_delete_elem(struct bpf_map *map, const void *key)
+ * Description
+ * Delete entry with *key* from *map*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * For tracing programs, safely attempt to read *size* bytes from
+ * kernel space address *unsafe_ptr* and store the data in *dst*.
+ *
+ * Generally, use **bpf_probe_read_user**\ () or
+ * **bpf_probe_read_kernel**\ () instead.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_ktime_get_ns(void)
+ * Description
+ * Return the time elapsed since system boot, in nanoseconds.
+ * Does not include time the system was suspended.
+ * See: **clock_gettime**\ (**CLOCK_MONOTONIC**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_trace_printk(const char *fmt, u32 fmt_size, ...)
+ * Description
+ * This helper is a "printk()-like" facility for debugging. It
+ * prints a message defined by format *fmt* (of size *fmt_size*)
+ * to file *\/sys/kernel/tracing/trace* from TraceFS, if
+ * available. It can take up to three additional **u64**
+ * arguments (as an eBPF helpers, the total number of arguments is
+ * limited to five).
+ *
+ * Each time the helper is called, it appends a line to the trace.
+ * Lines are discarded while *\/sys/kernel/tracing/trace* is
+ * open, use *\/sys/kernel/tracing/trace_pipe* to avoid this.
+ * The format of the trace is customizable, and the exact output
+ * one will get depends on the options set in
+ * *\/sys/kernel/tracing/trace_options* (see also the
+ * *README* file under the same directory). However, it usually
+ * defaults to something like:
+ *
+ * ::
+ *
+ * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg>
+ *
+ * In the above:
+ *
+ * * ``telnet`` is the name of the current task.
+ * * ``470`` is the PID of the current task.
+ * * ``001`` is the CPU number on which the task is
+ * running.
+ * * In ``.N..``, each character refers to a set of
+ * options (whether irqs are enabled, scheduling
+ * options, whether hard/softirqs are running, level of
+ * preempt_disabled respectively). **N** means that
+ * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED**
+ * are set.
+ * * ``419421.045894`` is a timestamp.
+ * * ``0x00000001`` is a fake value used by BPF for the
+ * instruction pointer register.
+ * * ``<formatted msg>`` is the message formatted with
+ * *fmt*.
+ *
+ * The conversion specifiers supported by *fmt* are similar, but
+ * more limited than for printk(). They are **%d**, **%i**,
+ * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**,
+ * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size
+ * of field, padding with zeroes, etc.) is available, and the
+ * helper will return **-EINVAL** (but print nothing) if it
+ * encounters an unknown specifier.
+ *
+ * Also, note that **bpf_trace_printk**\ () is slow, and should
+ * only be used for debugging purposes. For this reason, a notice
+ * block (spanning several lines) is printed to kernel logs and
+ * states that the helper should not be used "for production use"
+ * the first time this helper is used (or more precisely, when
+ * **trace_printk**\ () buffers are allocated). For passing values
+ * to user space, perf events should be preferred.
+ * Return
+ * The number of bytes written to the buffer, or a negative error
+ * in case of failure.
+ *
+ * u32 bpf_get_prandom_u32(void)
+ * Description
+ * Get a pseudo-random number.
+ *
+ * From a security point of view, this helper uses its own
+ * pseudo-random internal state, and cannot be used to infer the
+ * seed of other random functions in the kernel. However, it is
+ * essential to note that the generator used by the helper is not
+ * cryptographically secure.
+ * Return
+ * A random 32-bit unsigned value.
+ *
+ * u32 bpf_get_smp_processor_id(void)
+ * Description
+ * Get the SMP (symmetric multiprocessing) processor id. Note that
+ * all programs run with migration disabled, which means that the
+ * SMP processor id is stable during all the execution of the
+ * program.
+ * Return
+ * The SMP id of the processor running the program.
+ *
+ * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
+ * Description
+ * Store *len* bytes from address *from* into the packet
+ * associated to *skb*, at *offset*. *flags* are a combination of
+ * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the
+ * checksum for the packet after storing the bytes) and
+ * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\
+ * **->swhash** and *skb*\ **->l4hash** to 0).
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size)
+ * Description
+ * Recompute the layer 3 (e.g. IP) checksum for the packet
+ * associated to *skb*. Computation is incremental, so the helper
+ * must know the former value of the header field that was
+ * modified (*from*), the new value of this field (*to*), and the
+ * number of bytes (2 or 4) for this field, stored in *size*.
+ * Alternatively, it is possible to store the difference between
+ * the previous and the new values of the header field in *to*, by
+ * setting *from* and *size* to 0. For both methods, *offset*
+ * indicates the location of the IP checksum within the packet.
+ *
+ * This helper works in combination with **bpf_csum_diff**\ (),
+ * which does not update the checksum in-place, but offers more
+ * flexibility and can handle sizes larger than 2 or 4 for the
+ * checksum to update.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags)
+ * Description
+ * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the
+ * packet associated to *skb*. Computation is incremental, so the
+ * helper must know the former value of the header field that was
+ * modified (*from*), the new value of this field (*to*), and the
+ * number of bytes (2 or 4) for this field, stored on the lowest
+ * four bits of *flags*. Alternatively, it is possible to store
+ * the difference between the previous and the new values of the
+ * header field in *to*, by setting *from* and the four lowest
+ * bits of *flags* to 0. For both methods, *offset* indicates the
+ * location of the IP checksum within the packet. In addition to
+ * the size of the field, *flags* can be added (bitwise OR) actual
+ * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left
+ * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and
+ * for updates resulting in a null checksum the value is set to
+ * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
+ * the checksum is to be computed against a pseudo-header.
+ *
+ * This helper works in combination with **bpf_csum_diff**\ (),
+ * which does not update the checksum in-place, but offers more
+ * flexibility and can handle sizes larger than 2 or 4 for the
+ * checksum to update.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index)
+ * Description
+ * This special helper is used to trigger a "tail call", or in
+ * other words, to jump into another eBPF program. The same stack
+ * frame is used (but values on stack and in registers for the
+ * caller are not accessible to the callee). This mechanism allows
+ * for program chaining, either for raising the maximum number of
+ * available eBPF instructions, or to execute given programs in
+ * conditional blocks. For security reasons, there is an upper
+ * limit to the number of successive tail calls that can be
+ * performed.
+ *
+ * Upon call of this helper, the program attempts to jump into a
+ * program referenced at index *index* in *prog_array_map*, a
+ * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes
+ * *ctx*, a pointer to the context.
+ *
+ * If the call succeeds, the kernel immediately runs the first
+ * instruction of the new program. This is not a function call,
+ * and it never returns to the previous program. If the call
+ * fails, then the helper has no effect, and the caller continues
+ * to run its subsequent instructions. A call can fail if the
+ * destination program for the jump does not exist (i.e. *index*
+ * is superior to the number of entries in *prog_array_map*), or
+ * if the maximum number of tail calls has been reached for this
+ * chain of programs. This limit is defined in the kernel by the
+ * macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
+ * which is currently set to 33.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags)
+ * Description
+ * Clone and redirect the packet associated to *skb* to another
+ * net device of index *ifindex*. Both ingress and egress
+ * interfaces can be used for redirection. The **BPF_F_INGRESS**
+ * value in *flags* is used to make the distinction (ingress path
+ * is selected if the flag is present, egress path otherwise).
+ * This is the only flag supported for now.
+ *
+ * In comparison with **bpf_redirect**\ () helper,
+ * **bpf_clone_redirect**\ () has the associated cost of
+ * duplicating the packet buffer, but this can be executed out of
+ * the eBPF program. Conversely, **bpf_redirect**\ () is more
+ * efficient, but it is handled through an action code where the
+ * redirection happens only after the eBPF program has returned.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure. Positive
+ * error indicates a potential drop or congestion in the target
+ * device. The particular positive error codes are not defined.
+ *
+ * u64 bpf_get_current_pid_tgid(void)
+ * Description
+ * Get the current pid and tgid.
+ * Return
+ * A 64-bit integer containing the current tgid and pid, and
+ * created as such:
+ * *current_task*\ **->tgid << 32 \|**
+ * *current_task*\ **->pid**.
+ *
+ * u64 bpf_get_current_uid_gid(void)
+ * Description
+ * Get the current uid and gid.
+ * Return
+ * A 64-bit integer containing the current GID and UID, and
+ * created as such: *current_gid* **<< 32 \|** *current_uid*.
+ *
+ * long bpf_get_current_comm(void *buf, u32 size_of_buf)
+ * Description
+ * Copy the **comm** attribute of the current task into *buf* of
+ * *size_of_buf*. The **comm** attribute contains the name of
+ * the executable (excluding the path) for the current task. The
+ * *size_of_buf* must be strictly positive. On success, the
+ * helper makes sure that the *buf* is NUL-terminated. On failure,
+ * it is filled with zeroes.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u32 bpf_get_cgroup_classid(struct sk_buff *skb)
+ * Description
+ * Retrieve the classid for the current task, i.e. for the net_cls
+ * cgroup to which *skb* belongs.
+ *
+ * This helper can be used on TC egress path, but not on ingress.
+ *
+ * The net_cls cgroup provides an interface to tag network packets
+ * based on a user-provided identifier for all traffic coming from
+ * the tasks belonging to the related cgroup. See also the related
+ * kernel documentation, available from the Linux sources in file
+ * *Documentation/admin-guide/cgroup-v1/net_cls.rst*.
+ *
+ * The Linux kernel has two versions for cgroups: there are
+ * cgroups v1 and cgroups v2. Both are available to users, who can
+ * use a mixture of them, but note that the net_cls cgroup is for
+ * cgroup v1 only. This makes it incompatible with BPF programs
+ * run on cgroups, which is a cgroup-v2-only feature (a socket can
+ * only hold data for one version of cgroups at a time).
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to
+ * "**y**" or to "**m**".
+ * Return
+ * The classid, or 0 for the default unconfigured classid.
+ *
+ * long bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
+ * Description
+ * Push a *vlan_tci* (VLAN tag control information) of protocol
+ * *vlan_proto* to the packet associated to *skb*, then update
+ * the checksum. Note that if *vlan_proto* is different from
+ * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to
+ * be **ETH_P_8021Q**.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_vlan_pop(struct sk_buff *skb)
+ * Description
+ * Pop a VLAN header from the packet associated to *skb*.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * Description
+ * Get tunnel metadata. This helper takes a pointer *key* to an
+ * empty **struct bpf_tunnel_key** of **size**, that will be
+ * filled with tunnel metadata for the packet associated to *skb*.
+ * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which
+ * indicates that the tunnel is based on IPv6 protocol instead of
+ * IPv4.
+ *
+ * The **struct bpf_tunnel_key** is an object that generalizes the
+ * principal parameters used by various tunneling protocols into a
+ * single struct. This way, it can be used to easily make a
+ * decision based on the contents of the encapsulation header,
+ * "summarized" in this struct. In particular, it holds the IP
+ * address of the remote end (IPv4 or IPv6, depending on the case)
+ * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also,
+ * this struct exposes the *key*\ **->tunnel_id**, which is
+ * generally mapped to a VNI (Virtual Network Identifier), making
+ * it programmable together with the **bpf_skb_set_tunnel_key**\
+ * () helper.
+ *
+ * Let's imagine that the following code is part of a program
+ * attached to the TC ingress interface, on one end of a GRE
+ * tunnel, and is supposed to filter out all messages coming from
+ * remote ends with IPv4 address other than 10.0.0.1:
+ *
+ * ::
+ *
+ * int ret;
+ * struct bpf_tunnel_key key = {};
+ *
+ * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ * if (ret < 0)
+ * return TC_ACT_SHOT; // drop packet
+ *
+ * if (key.remote_ipv4 != 0x0a000001)
+ * return TC_ACT_SHOT; // drop packet
+ *
+ * return TC_ACT_OK; // accept packet
+ *
+ * This interface can also be used with all encapsulation devices
+ * that can operate in "collect metadata" mode: instead of having
+ * one network device per specific configuration, the "collect
+ * metadata" mode only requires a single device where the
+ * configuration can be extracted from this helper.
+ *
+ * This can be used together with various tunnels such as VXLan,
+ * Geneve, GRE or IP in IP (IPIP).
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
+ * Description
+ * Populate tunnel metadata for packet associated to *skb.* The
+ * tunnel metadata is set to the contents of *key*, of *size*. The
+ * *flags* can be set to a combination of the following values:
+ *
+ * **BPF_F_TUNINFO_IPV6**
+ * Indicate that the tunnel is based on IPv6 protocol
+ * instead of IPv4.
+ * **BPF_F_ZERO_CSUM_TX**
+ * For IPv4 packets, add a flag to tunnel metadata
+ * indicating that checksum computation should be skipped
+ * and checksum set to zeroes.
+ * **BPF_F_DONT_FRAGMENT**
+ * Add a flag to tunnel metadata indicating that the
+ * packet should not be fragmented.
+ * **BPF_F_SEQ_NUMBER**
+ * Add a flag to tunnel metadata indicating that a
+ * sequence number should be added to tunnel header before
+ * sending the packet. This flag was added for GRE
+ * encapsulation, but might be used with other protocols
+ * as well in the future.
+ * **BPF_F_NO_TUNNEL_KEY**
+ * Add a flag to tunnel metadata indicating that no tunnel
+ * key should be set in the resulting tunnel header.
+ *
+ * Here is a typical usage on the transmit path:
+ *
+ * ::
+ *
+ * struct bpf_tunnel_key key;
+ * populate key ...
+ * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+ * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0);
+ *
+ * See also the description of the **bpf_skb_get_tunnel_key**\ ()
+ * helper for additional information.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags)
+ * Description
+ * Read the value of a perf event counter. This helper relies on a
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of
+ * the perf event counter is selected when *map* is updated with
+ * perf event file descriptors. The *map* is an array whose size
+ * is the number of available CPUs, and each cell contains a value
+ * relative to one CPU. The value to retrieve is indicated by
+ * *flags*, that contains the index of the CPU to look up, masked
+ * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to
+ * **BPF_F_CURRENT_CPU** to indicate that the value for the
+ * current CPU should be retrieved.
+ *
+ * Note that before Linux 4.13, only hardware perf event can be
+ * retrieved.
+ *
+ * Also, be aware that the newer helper
+ * **bpf_perf_event_read_value**\ () is recommended over
+ * **bpf_perf_event_read**\ () in general. The latter has some ABI
+ * quirks where error and counter value are used as a return code
+ * (which is wrong to do since ranges may overlap). This issue is
+ * fixed with **bpf_perf_event_read_value**\ (), which at the same
+ * time provides more features over the **bpf_perf_event_read**\
+ * () interface. Please refer to the description of
+ * **bpf_perf_event_read_value**\ () for details.
+ * Return
+ * The value of the perf event counter read from the map, or a
+ * negative error code in case of failure.
+ *
+ * long bpf_redirect(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_clone_redirect**\
+ * (), except that the packet is not cloned, which provides
+ * increased performance.
+ *
+ * Except for XDP, both ingress and egress interfaces can be used
+ * for redirection. The **BPF_F_INGRESS** value in *flags* is used
+ * to make the distinction (ingress path is selected if the flag
+ * is present, egress path otherwise). Currently, XDP only
+ * supports redirection to the egress interface, and accepts no
+ * flag at all.
+ *
+ * The same effect can also be attained with the more generic
+ * **bpf_redirect_map**\ (), which uses a BPF map to store the
+ * redirect target instead of providing it directly to the helper.
+ * Return
+ * For XDP, the helper returns **XDP_REDIRECT** on success or
+ * **XDP_ABORTED** on error. For other program types, the values
+ * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on
+ * error.
+ *
+ * u32 bpf_get_route_realm(struct sk_buff *skb)
+ * Description
+ * Retrieve the realm or the route, that is to say the
+ * **tclassid** field of the destination for the *skb*. The
+ * identifier retrieved is a user-provided tag, similar to the
+ * one used with the net_cls cgroup (see description for
+ * **bpf_get_cgroup_classid**\ () helper), but here this tag is
+ * held by a route (a destination entry), not by a task.
+ *
+ * Retrieving this identifier works with the clsact TC egress hook
+ * (see also **tc-bpf(8)**), or alternatively on conventional
+ * classful egress qdiscs, but not on TC ingress path. In case of
+ * clsact TC egress hook, this has the advantage that, internally,
+ * the destination entry has not been dropped yet in the transmit
+ * path. Therefore, the destination entry does not need to be
+ * artificially held via **netif_keep_dst**\ () for a classful
+ * qdisc until the *skb* is freed.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_IP_ROUTE_CLASSID** configuration option.
+ * Return
+ * The realm of the route for the packet associated to *skb*, or 0
+ * if none was found.
+ *
+ * long bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * Description
+ * Write raw *data* blob into a special BPF perf event held by
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * event must have the following attributes: **PERF_SAMPLE_RAW**
+ * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * **PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * The *flags* are used to indicate the index in *map* for which
+ * the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * to indicate that the index of the current CPU core should be
+ * used.
+ *
+ * The value to write, of *size*, is passed through eBPF stack and
+ * pointed by *data*.
+ *
+ * The context of the program *ctx* needs also be passed to the
+ * helper.
+ *
+ * On user space, a program willing to read the values needs to
+ * call **perf_event_open**\ () on the perf event (either for
+ * one or for all CPUs) and to store the file descriptor into the
+ * *map*. This must be done before the eBPF program can send data
+ * into it. An example is available in file
+ * *samples/bpf/trace_output_user.c* in the Linux kernel source
+ * tree (the eBPF program counterpart is in
+ * *samples/bpf/trace_output_kern.c*).
+ *
+ * **bpf_perf_event_output**\ () achieves better performance
+ * than **bpf_trace_printk**\ () for sharing data with user
+ * space, and is much better suitable for streaming data from eBPF
+ * programs.
+ *
+ * Note that this helper is not restricted to tracing use cases
+ * and can be used with programs attached to TC or XDP as well,
+ * where it allows for passing data to user space listeners. Data
+ * can be:
+ *
+ * * Only custom structs,
+ * * Only the packet payload, or
+ * * A combination of both.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len)
+ * Description
+ * This helper was provided as an easy way to load data from a
+ * packet. It can be used to load *len* bytes from *offset* from
+ * the packet associated to *skb*, into the buffer pointed by
+ * *to*.
+ *
+ * Since Linux 4.7, usage of this helper has mostly been replaced
+ * by "direct packet access", enabling packet data to be
+ * manipulated with *skb*\ **->data** and *skb*\ **->data_end**
+ * pointing respectively to the first byte of packet data and to
+ * the byte after the last byte of packet data. However, it
+ * remains useful if one wishes to read large quantities of data
+ * at once from a packet into the eBPF stack.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags)
+ * Description
+ * Walk a user or a kernel stack and return its id. To achieve
+ * this, the helper needs *ctx*, which is a pointer to the context
+ * on which the tracing program is executed, and a pointer to a
+ * *map* of type **BPF_MAP_TYPE_STACK_TRACE**.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * a combination of the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * **BPF_F_FAST_STACK_CMP**
+ * Compare stacks by hash only.
+ * **BPF_F_REUSE_STACKID**
+ * If two different stacks hash into the same *stackid*,
+ * discard the old one.
+ *
+ * The stack id retrieved is a 32 bit long integer handle which
+ * can be further combined with other data (including other stack
+ * ids) and used as a key into maps. This can be useful for
+ * generating a variety of graphs (such as flame graphs or off-cpu
+ * graphs).
+ *
+ * For walking a stack, this helper is an improvement over
+ * **bpf_probe_read**\ (), which can be used with unrolled loops
+ * but is not efficient and consumes a lot of eBPF instructions.
+ * Instead, **bpf_get_stackid**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ * Return
+ * The positive or null stack id on success, or a negative error
+ * in case of failure.
+ *
+ * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed)
+ * Description
+ * Compute a checksum difference, from the raw buffer pointed by
+ * *from*, of length *from_size* (that must be a multiple of 4),
+ * towards the raw buffer pointed by *to*, of size *to_size*
+ * (same remark). An optional *seed* can be added to the value
+ * (this can be cascaded, the seed may come from a previous call
+ * to the helper).
+ *
+ * This is flexible enough to be used in several ways:
+ *
+ * * With *from_size* == 0, *to_size* > 0 and *seed* set to
+ * checksum, it can be used when pushing new data.
+ * * With *from_size* > 0, *to_size* == 0 and *seed* set to
+ * checksum, it can be used when removing data from a packet.
+ * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it
+ * can be used to compute a diff. Note that *from_size* and
+ * *to_size* do not need to be equal.
+ *
+ * This helper can be used in combination with
+ * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to
+ * which one can feed in the difference computed with
+ * **bpf_csum_diff**\ ().
+ * Return
+ * The checksum result, or a negative error code in case of
+ * failure.
+ *
+ * long bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
+ * Description
+ * Retrieve tunnel options metadata for the packet associated to
+ * *skb*, and store the raw tunnel option data to the buffer *opt*
+ * of *size*.
+ *
+ * This helper can be used with encapsulation devices that can
+ * operate in "collect metadata" mode (please refer to the related
+ * note in the description of **bpf_skb_get_tunnel_key**\ () for
+ * more details). A particular example where this can be used is
+ * in combination with the Geneve encapsulation protocol, where it
+ * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper)
+ * and retrieving arbitrary TLVs (Type-Length-Value headers) from
+ * the eBPF program. This allows for full customization of these
+ * headers.
+ * Return
+ * The size of the option data retrieved.
+ *
+ * long bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
+ * Description
+ * Set tunnel options metadata for the packet associated to *skb*
+ * to the option data contained in the raw buffer *opt* of *size*.
+ *
+ * See also the description of the **bpf_skb_get_tunnel_opt**\ ()
+ * helper for additional information.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags)
+ * Description
+ * Change the protocol of the *skb* to *proto*. Currently
+ * supported are transition from IPv4 to IPv6, and from IPv6 to
+ * IPv4. The helper takes care of the groundwork for the
+ * transition, including resizing the socket buffer. The eBPF
+ * program is expected to fill the new headers, if any, via
+ * **skb_store_bytes**\ () and to recompute the checksums with
+ * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\
+ * (). The main case for this helper is to perform NAT64
+ * operations out of an eBPF program.
+ *
+ * Internally, the GSO type is marked as dodgy so that headers are
+ * checked and segments are recalculated by the GSO/GRO engine.
+ * The size for GSO target is adapted as well.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_change_type(struct sk_buff *skb, u32 type)
+ * Description
+ * Change the packet type for the packet associated to *skb*. This
+ * comes down to setting *skb*\ **->pkt_type** to *type*, except
+ * the eBPF program does not have a write access to *skb*\
+ * **->pkt_type** beside this helper. Using a helper here allows
+ * for graceful handling of errors.
+ *
+ * The major use case is to change incoming *skb*s to
+ * **PACKET_HOST** in a programmatic way instead of having to
+ * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for
+ * example.
+ *
+ * Note that *type* only allows certain values. At this time, they
+ * are:
+ *
+ * **PACKET_HOST**
+ * Packet is for us.
+ * **PACKET_BROADCAST**
+ * Send packet to all.
+ * **PACKET_MULTICAST**
+ * Send packet to group.
+ * **PACKET_OTHERHOST**
+ * Send packet to someone else.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index)
+ * Description
+ * Check whether *skb* is a descendant of the cgroup2 held by
+ * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*.
+ * Return
+ * The return value depends on the result of the test, and can be:
+ *
+ * * 0, if the *skb* failed the cgroup2 descendant test.
+ * * 1, if the *skb* succeeded the cgroup2 descendant test.
+ * * A negative error code, if an error occurred.
+ *
+ * u32 bpf_get_hash_recalc(struct sk_buff *skb)
+ * Description
+ * Retrieve the hash of the packet, *skb*\ **->hash**. If it is
+ * not set, in particular if the hash was cleared due to mangling,
+ * recompute this hash. Later accesses to the hash can be done
+ * directly with *skb*\ **->hash**.
+ *
+ * Calling **bpf_set_hash_invalid**\ (), changing a packet
+ * prototype with **bpf_skb_change_proto**\ (), or calling
+ * **bpf_skb_store_bytes**\ () with the
+ * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear
+ * the hash and to trigger a new computation for the next call to
+ * **bpf_get_hash_recalc**\ ().
+ * Return
+ * The 32-bit hash.
+ *
+ * u64 bpf_get_current_task(void)
+ * Description
+ * Get the current task.
+ * Return
+ * A pointer to the current task struct.
+ *
+ * long bpf_probe_write_user(void *dst, const void *src, u32 len)
+ * Description
+ * Attempt in a safe way to write *len* bytes from the buffer
+ * *src* to *dst* in memory. It only works for threads that are in
+ * user context, and *dst* must be a valid user space address.
+ *
+ * This helper should not be used to implement any kind of
+ * security mechanism because of TOC-TOU attacks, but rather to
+ * debug, divert, and manipulate execution of semi-cooperative
+ * processes.
+ *
+ * Keep in mind that this feature is meant for experiments, and it
+ * has a risk of crashing the system and running programs.
+ * Therefore, when an eBPF program using this helper is attached,
+ * a warning including PID and process name is printed to kernel
+ * logs.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_current_task_under_cgroup(struct bpf_map *map, u32 index)
+ * Description
+ * Check whether the probe is being run is the context of a given
+ * subset of the cgroup2 hierarchy. The cgroup2 to test is held by
+ * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*.
+ * Return
+ * The return value depends on the result of the test, and can be:
+ *
+ * * 1, if current task belongs to the cgroup2.
+ * * 0, if current task does not belong to the cgroup2.
+ * * A negative error code, if an error occurred.
+ *
+ * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
+ * Description
+ * Resize (trim or grow) the packet associated to *skb* to the
+ * new *len*. The *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * The basic idea is that the helper performs the needed work to
+ * change the size of the packet, then the eBPF program rewrites
+ * the rest via helpers like **bpf_skb_store_bytes**\ (),
+ * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ ()
+ * and others. This helper is a slow path utility intended for
+ * replies with control messages. And because it is targeted for
+ * slow path, the helper itself can afford to be slow: it
+ * implicitly linearizes, unclones and drops offloads from the
+ * *skb*.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_pull_data(struct sk_buff *skb, u32 len)
+ * Description
+ * Pull in non-linear data in case the *skb* is non-linear and not
+ * all of *len* are part of the linear section. Make *len* bytes
+ * from *skb* readable and writable. If a zero value is passed for
+ * *len*, then all bytes in the linear part of *skb* will be made
+ * readable and writable.
+ *
+ * This helper is only needed for reading and writing with direct
+ * packet access.
+ *
+ * For direct packet access, testing that offsets to access
+ * are within packet boundaries (test on *skb*\ **->data_end**) is
+ * susceptible to fail if offsets are invalid, or if the requested
+ * data is in non-linear parts of the *skb*. On failure the
+ * program can just bail out, or in the case of a non-linear
+ * buffer, use a helper to make the data available. The
+ * **bpf_skb_load_bytes**\ () helper is a first solution to access
+ * the data. Another one consists in using **bpf_skb_pull_data**
+ * to pull in once the non-linear parts, then retesting and
+ * eventually access the data.
+ *
+ * At the same time, this also makes sure the *skb* is uncloned,
+ * which is a necessary condition for direct write. As this needs
+ * to be an invariant for the write part only, the verifier
+ * detects writes and adds a prologue that is calling
+ * **bpf_skb_pull_data()** to effectively unclone the *skb* from
+ * the very beginning in case it is indeed cloned.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum)
+ * Description
+ * Add the checksum *csum* into *skb*\ **->csum** in case the
+ * driver has supplied a checksum for the entire packet into that
+ * field. Return an error otherwise. This helper is intended to be
+ * used in combination with **bpf_csum_diff**\ (), in particular
+ * when the checksum needs to be updated after data has been
+ * written into the packet through direct packet access.
+ * Return
+ * The checksum on success, or a negative error code in case of
+ * failure.
+ *
+ * void bpf_set_hash_invalid(struct sk_buff *skb)
+ * Description
+ * Invalidate the current *skb*\ **->hash**. It can be used after
+ * mangling on headers through direct packet access, in order to
+ * indicate that the hash is outdated and to trigger a
+ * recalculation the next time the kernel tries to access this
+ * hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ * Return
+ * void.
+ *
+ * long bpf_get_numa_node_id(void)
+ * Description
+ * Return the id of the current NUMA node. The primary use case
+ * for this helper is the selection of sockets for the local NUMA
+ * node, when the program is attached to sockets using the
+ * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**),
+ * but the helper is also available to other eBPF program types,
+ * similarly to **bpf_get_smp_processor_id**\ ().
+ * Return
+ * The id of current NUMA node.
+ *
+ * long bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags)
+ * Description
+ * Grows headroom of packet associated to *skb* and adjusts the
+ * offset of the MAC header accordingly, adding *len* bytes of
+ * space. It automatically extends and reallocates memory as
+ * required.
+ *
+ * This helper can be used on a layer 3 *skb* to push a MAC header
+ * for redirection into a layer 2 device.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that
+ * it is possible to use a negative value for *delta*. This helper
+ * can be used to prepare the packet for pushing or popping
+ * headers.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe kernel address
+ * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for
+ * more details.
+ *
+ * Generally, use **bpf_probe_read_user_str**\ () or
+ * **bpf_probe_read_kernel_str**\ () instead.
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * u64 bpf_get_socket_cookie(struct sk_buff *skb)
+ * Description
+ * If the **struct sk_buff** pointed by *skb* has a known socket,
+ * retrieve the cookie (generated by the kernel) of this socket.
+ * If no cookie has been set yet, generate a new cookie. Once
+ * generated, the socket cookie remains stable for the life of the
+ * socket. This helper can be useful for monitoring per socket
+ * networking traffic statistics as it provides a global socket
+ * identifier that can be assumed unique.
+ * Return
+ * A 8-byte long unique number on success, or 0 if the socket
+ * field is missing inside *skb*.
+ *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
+ * Description
+ * Equivalent to bpf_get_socket_cookie() helper that accepts
+ * *skb*, but gets socket from **struct bpf_sock_addr** context.
+ * Return
+ * A 8-byte long unique number.
+ *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
+ * Description
+ * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
+ * *skb*, but gets socket from **struct bpf_sock_ops** context.
+ * Return
+ * A 8-byte long unique number.
+ *
+ * u64 bpf_get_socket_cookie(struct sock *sk)
+ * Description
+ * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
+ * *sk*, but gets socket from a BTF **struct sock**. This helper
+ * also works for sleepable programs.
+ * Return
+ * A 8-byte long unique number or 0 if *sk* is NULL.
+ *
+ * u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * Description
+ * Get the owner UID of the socked associated to *skb*.
+ * Return
+ * The owner UID of the socket associated to *skb*. If the socket
+ * is **NULL**, or if it is not a full socket (i.e. if it is a
+ * time-wait or a request socket instead), **overflowuid** value
+ * is returned (note that **overflowuid** might also be the actual
+ * UID value for the socket).
+ *
+ * long bpf_set_hash(struct sk_buff *skb, u32 hash)
+ * Description
+ * Set the full hash for *skb* (set the field *skb*\ **->hash**)
+ * to value *hash*.
+ * Return
+ * 0
+ *
+ * long bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
+ * Description
+ * Emulate a call to **setsockopt()** on the socket associated to
+ * *bpf_socket*, which must be a full socket. The *level* at
+ * which the option resides and the name *optname* of the option
+ * must be specified, see **setsockopt(2)** for more information.
+ * The option value of length *optlen* is pointed by *optval*.
+ *
+ * *bpf_socket* should be one of the following:
+ *
+ * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
+ *
+ * This helper actually implements a subset of **setsockopt()**.
+ * It supports the following *level*\ s:
+ *
+ * * **SOL_SOCKET**, which supports the following *optname*\ s:
+ * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**,
+ * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**,
+ * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**,
+ * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**.
+ * * **IPPROTO_TCP**, which supports the following *optname*\ s:
+ * **TCP_CONGESTION**, **TCP_BPF_IW**,
+ * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
+ * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
+ * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**,
+ * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**,
+ * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**,
+ * **TCP_BPF_RTO_MIN**.
+ * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
+ * * **IPPROTO_IPV6**, which supports the following *optname*\ s:
+ * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
+ * Description
+ * Grow or shrink the room for data in the packet associated to
+ * *skb* by *len_diff*, and according to the selected *mode*.
+ *
+ * By default, the helper will reset any offloaded checksum
+ * indicator of the skb to CHECKSUM_NONE. This can be avoided
+ * by the following flag:
+ *
+ * * **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded
+ * checksum data of the skb to CHECKSUM_NONE.
+ *
+ * There are two supported modes at this time:
+ *
+ * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
+ * (room space is added or removed between the layer 2 and
+ * layer 3 headers).
+ *
+ * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
+ * (room space is added or removed between the layer 3 and
+ * layer 4 headers).
+ *
+ * The following flags are supported at this time:
+ *
+ * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size.
+ * Adjusting mss in this way is not allowed for datagrams.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**,
+ * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**:
+ * Any new space is reserved to hold a tunnel header.
+ * Configure skb offsets and other fields accordingly.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**,
+ * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**:
+ * Use with ENCAP_L3 flags to further specify the tunnel type.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*):
+ * Use with ENCAP_L3/L4 flags to further specify the tunnel
+ * type; *len* is the length of the inner MAC header.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**:
+ * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
+ * L2 type as Ethernet.
+ *
+ * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
+ * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
+ * Indicate the new IP header version after decapsulating the outer
+ * IP header. Used when the inner and outer IP versions are different.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags)
+ * Description
+ * Redirect the packet to the endpoint referenced by *map* at
+ * index *key*. Depending on its type, this *map* can contain
+ * references to net devices (for forwarding packets through other
+ * ports), or to CPUs (for redirecting XDP frames to another CPU;
+ * but this is only implemented for native XDP (with driver
+ * support) as of this writing).
+ *
+ * The lower two bits of *flags* are used as the return code if
+ * the map lookup fails. This is so that the return value can be
+ * one of the XDP program return codes up to **XDP_TX**, as chosen
+ * by the caller. The higher bits of *flags* can be set to
+ * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress
+ * interface will be excluded when do broadcasting.
+ *
+ * See also **bpf_redirect**\ (), which only supports redirecting
+ * to an ifindex, but doesn't require a map to do so.
+ * Return
+ * **XDP_REDIRECT** on success, or the value of the two lower bits
+ * of the *flags* argument on error.
+ *
+ * long bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * Redirect the packet to the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * long bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Add an entry to, or update a *map* referencing sockets. The
+ * *skops* is used as a new value for the entry associated to
+ * *key*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * If the *map* has eBPF programs (parser and verdict), those will
+ * be inherited by the socket being added. If the socket is
+ * already attached to eBPF programs, this results in an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust the address pointed by *xdp_md*\ **->data_meta** by
+ * *delta* (which can be positive or negative). Note that this
+ * operation modifies the address stored in *xdp_md*\ **->data**,
+ * so the latter must be loaded only after the helper has been
+ * called.
+ *
+ * The use of *xdp_md*\ **->data_meta** is optional and programs
+ * are not required to use it. The rationale is that when the
+ * packet is processed with XDP (e.g. as DoS filter), it is
+ * possible to push further meta data along with it before passing
+ * to the stack, and to give the guarantee that an ingress eBPF
+ * program attached as a TC classifier on the same device can pick
+ * this up for further post-processing. Since TC works with socket
+ * buffers, it remains possible to set from XDP the **mark** or
+ * **priority** pointers, or other pointers for the socket buffer.
+ * Having this scratch space generic and programmable allows for
+ * more flexibility as the user is free to store whatever meta
+ * data they need.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size)
+ * Description
+ * Read the value of a perf event counter, and store it into *buf*
+ * of size *buf_size*. This helper relies on a *map* of type
+ * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event
+ * counter is selected when *map* is updated with perf event file
+ * descriptors. The *map* is an array whose size is the number of
+ * available CPUs, and each cell contains a value relative to one
+ * CPU. The value to retrieve is indicated by *flags*, that
+ * contains the index of the CPU to look up, masked with
+ * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to
+ * **BPF_F_CURRENT_CPU** to indicate that the value for the
+ * current CPU should be retrieved.
+ *
+ * This helper behaves in a way close to
+ * **bpf_perf_event_read**\ () helper, save that instead of
+ * just returning the value observed, it fills the *buf*
+ * structure. This allows for additional data to be retrieved: in
+ * particular, the enabled and running times (in *buf*\
+ * **->enabled** and *buf*\ **->running**, respectively) are
+ * copied. In general, **bpf_perf_event_read_value**\ () is
+ * recommended over **bpf_perf_event_read**\ (), which has some
+ * ABI issues and provides fewer functionalities.
+ *
+ * These values are interesting, because hardware PMU (Performance
+ * Monitoring Unit) counters are limited resources. When there are
+ * more PMU based perf events opened than available counters,
+ * kernel will multiplex these events so each event gets certain
+ * percentage (but not all) of the PMU time. In case that
+ * multiplexing happens, the number of samples or counter value
+ * will not reflect the case compared to when no multiplexing
+ * occurs. This makes comparison between different runs difficult.
+ * Typically, the counter value should be normalized before
+ * comparing to other experiments. The usual normalization is done
+ * as follows.
+ *
+ * ::
+ *
+ * normalized_counter = counter * t_enabled / t_running
+ *
+ * Where t_enabled is the time enabled for event and t_running is
+ * the time running for event since last normalization. The
+ * enabled and running times are accumulated since the perf event
+ * open. To achieve scaling factor between two invocations of an
+ * eBPF program, users can use CPU id as the key (which is
+ * typical for perf array usage model) to remember the previous
+ * value and do the calculation inside the eBPF program.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
+ * Description
+ * For an eBPF program attached to a perf event, retrieve the
+ * value of the event counter associated to *ctx* and store it in
+ * the structure pointed by *buf* and of size *buf_size*. Enabled
+ * and running times are also stored in the structure (see
+ * description of helper **bpf_perf_event_read_value**\ () for
+ * more details).
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
+ * Description
+ * Emulate a call to **getsockopt()** on the socket associated to
+ * *bpf_socket*, which must be a full socket. The *level* at
+ * which the option resides and the name *optname* of the option
+ * must be specified, see **getsockopt(2)** for more information.
+ * The retrieved value is stored in the structure pointed by
+ * *opval* and of length *optlen*.
+ *
+ * *bpf_socket* should be one of the following:
+ *
+ * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
+ *
+ * This helper actually implements a subset of **getsockopt()**.
+ * It supports the same set of *optname*\ s that is supported by
+ * the **bpf_setsockopt**\ () helper. The exceptions are
+ * **TCP_BPF_*** is **bpf_setsockopt**\ () only and
+ * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_override_return(struct pt_regs *regs, u64 rc)
+ * Description
+ * Used for error injection, this helper uses kprobes to override
+ * the return value of the probed function, and to set it to *rc*.
+ * The first argument is the context *regs* on which the kprobe
+ * works.
+ *
+ * This helper works by setting the PC (program counter)
+ * to an override function which is run in place of the original
+ * probed function. This means the probed function is not run at
+ * all. The replacement function just returns with the required
+ * value.
+ *
+ * This helper has security implications, and thus is subject to
+ * restrictions. It is only available if the kernel was compiled
+ * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration
+ * option, and in this case it only works on functions tagged with
+ * **ALLOW_ERROR_INJECTION** in the kernel code.
+ *
+ * Also, the helper is only available for the architectures having
+ * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing,
+ * x86 architecture is the only one to support this feature.
+ * Return
+ * 0
+ *
+ * long bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval)
+ * Description
+ * Attempt to set the value of the **bpf_sock_ops_cb_flags** field
+ * for the full TCP socket associated to *bpf_sock_ops* to
+ * *argval*.
+ *
+ * The primary use of this field is to determine if there should
+ * be calls to eBPF programs of type
+ * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP
+ * code. A program of the same type can change its value, per
+ * connection and as necessary, when the connection is
+ * established. This field is directly accessible for reading, but
+ * this helper must be used for updates in order to return an
+ * error if an eBPF program tries to set a callback that is not
+ * supported in the current kernel.
+ *
+ * *argval* is a flag array which can combine these flags:
+ *
+ * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
+ * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
+ * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
+ * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT)
+ *
+ * Therefore, this function can be used to clear a callback flag by
+ * setting the appropriate bit to zero. e.g. to disable the RTO
+ * callback:
+ *
+ * **bpf_sock_ops_cb_flags_set(bpf_sock,**
+ * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)**
+ *
+ * Here are some examples of where one could call such eBPF
+ * program:
+ *
+ * * When RTO fires.
+ * * When a packet is retransmitted.
+ * * When the connection terminates.
+ * * When a packet is sent.
+ * * When a packet is received.
+ * Return
+ * Code **-EINVAL** if the socket is not a full TCP socket;
+ * otherwise, a positive number containing the bits that could not
+ * be set is returned (which comes down to 0 if all bits were set
+ * as required).
+ *
+ * long bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * socket level. If the message *msg* is allowed to pass (i.e. if
+ * the verdict eBPF program returns **SK_PASS**), redirect it to
+ * the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * long bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * Description
+ * For socket policies, apply the verdict of the eBPF program to
+ * the next *bytes* (number of bytes) of message *msg*.
+ *
+ * For example, this helper can be used in the following cases:
+ *
+ * * A single **sendmsg**\ () or **sendfile**\ () system call
+ * contains multiple logical messages that the eBPF program is
+ * supposed to read and for which it should apply a verdict.
+ * * An eBPF program only cares to read the first *bytes* of a
+ * *msg*. If the message has a large payload, then setting up
+ * and calling the eBPF program repeatedly for all bytes, even
+ * though the verdict is already known, would create unnecessary
+ * overhead.
+ *
+ * When called from within an eBPF program, the helper sets a
+ * counter internal to the BPF infrastructure, that is used to
+ * apply the last verdict to the next *bytes*. If *bytes* is
+ * smaller than the current data being processed from a
+ * **sendmsg**\ () or **sendfile**\ () system call, the first
+ * *bytes* will be sent and the eBPF program will be re-run with
+ * the pointer for start of data pointing to byte number *bytes*
+ * **+ 1**. If *bytes* is larger than the current data being
+ * processed, then the eBPF verdict will be applied to multiple
+ * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are
+ * consumed.
+ *
+ * Note that if a socket closes with the internal counter holding
+ * a non-zero value, this is not a problem because data is not
+ * being buffered for *bytes* and is sent as it is received.
+ * Return
+ * 0
+ *
+ * long bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes)
+ * Description
+ * For socket policies, prevent the execution of the verdict eBPF
+ * program for message *msg* until *bytes* (byte number) have been
+ * accumulated.
+ *
+ * This can be used when one needs a specific number of bytes
+ * before a verdict can be assigned, even if the data spans
+ * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme
+ * case would be a user calling **sendmsg**\ () repeatedly with
+ * 1-byte long message segments. Obviously, this is bad for
+ * performance, but it is still valid. If the eBPF program needs
+ * *bytes* bytes to validate a header, this helper can be used to
+ * prevent the eBPF program to be called again until *bytes* have
+ * been accumulated.
+ * Return
+ * 0
+ *
+ * long bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags)
+ * Description
+ * For socket policies, pull in non-linear data from user space
+ * for *msg* and set pointers *msg*\ **->data** and *msg*\
+ * **->data_end** to *start* and *end* bytes offsets into *msg*,
+ * respectively.
+ *
+ * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ * *msg* it can only parse data that the (**data**, **data_end**)
+ * pointers have already consumed. For **sendmsg**\ () hooks this
+ * is likely the first scatterlist element. But for calls relying
+ * on the **sendpage** handler (e.g. **sendfile**\ ()) this will
+ * be the range (**0**, **0**) because the data is shared with
+ * user space and by default the objective is to avoid allowing
+ * user space to modify data while (or after) eBPF verdict is
+ * being decided. This helper can be used to pull in data and to
+ * set the start and end pointer to given values. Data will be
+ * copied if necessary (i.e. if data was not linear and if start
+ * and end pointers do not point to the same chunk).
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len)
+ * Description
+ * Bind the socket associated to *ctx* to the address pointed by
+ * *addr*, of length *addr_len*. This allows for making outgoing
+ * connection from the desired IP address, which can be useful for
+ * example when all processes inside a cgroup should use one
+ * single IP address on a host that has multiple IP configured.
+ *
+ * This helper works for IPv4 and IPv6, TCP and UDP sockets. The
+ * domain (*addr*\ **->sa_family**) must be **AF_INET** (or
+ * **AF_INET6**). It's advised to pass zero port (**sin_port**
+ * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like
+ * behavior and lets the kernel efficiently pick up an unused
+ * port as long as 4-tuple is unique. Passing non-zero port might
+ * lead to degraded performance.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
+ * possible to both shrink and grow the packet tail.
+ * Shrink done via *delta* being a negative integer.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags)
+ * Description
+ * Retrieve the XFRM state (IP transform framework, see also
+ * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*.
+ *
+ * The retrieved value is stored in the **struct bpf_xfrm_state**
+ * pointed by *xfrm_state* and of length *size*.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_XFRM** configuration option.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags)
+ * Description
+ * Return a user or a kernel stack in bpf program provided buffer.
+ * To achieve this, the helper needs *ctx*, which is a pointer
+ * to the context on which the tracing program is executed.
+ * To store the stacktrace, the bpf program provides *buf* with
+ * a nonnegative *size*.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * **BPF_F_USER_BUILD_ID**
+ * Collect (build_id, file_offset) instead of ips for user
+ * stack, only valid if **BPF_F_USER_STACK** is also
+ * specified.
+ *
+ * *file_offset* is an offset relative to the beginning
+ * of the executable or shared object file backing the vma
+ * which the *ip* falls in. It is *not* an offset relative
+ * to that object's base address. Accordingly, it must be
+ * adjusted by adding (sh_addr - sh_offset), where
+ * sh_{addr,offset} correspond to the executable section
+ * containing *file_offset* in the object, for comparisons
+ * to symbols' st_value to be valid.
+ *
+ * **bpf_get_stack**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ * to sufficient large buffer size. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ * Return
+ * The non-negative copied *buf* length equal to or less than
+ * *size* on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * Description
+ * This helper is similar to **bpf_skb_load_bytes**\ () in that
+ * it provides an easy way to load *len* bytes from *offset*
+ * from the packet associated to *skb*, into the buffer pointed
+ * by *to*. The difference to **bpf_skb_load_bytes**\ () is that
+ * a fifth argument *start_header* exists in order to select a
+ * base offset to start from. *start_header* can be one of:
+ *
+ * **BPF_HDR_START_MAC**
+ * Base offset to load data from is *skb*'s mac header.
+ * **BPF_HDR_START_NET**
+ * Base offset to load data from is *skb*'s network header.
+ *
+ * In general, "direct packet access" is the preferred method to
+ * access packet data, however, this helper is in particular useful
+ * in socket filters where *skb*\ **->data** does not always point
+ * to the start of the mac header and where "direct packet access"
+ * is not available.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags)
+ * Description
+ * Do FIB lookup in kernel tables using parameters in *params*.
+ * If lookup is successful and result shows packet is to be
+ * forwarded, the neighbor tables are searched for the nexthop.
+ * If successful (ie., FIB lookup shows forwarding and nexthop
+ * is resolved), the nexthop address is returned in ipv4_dst
+ * or ipv6_dst based on family, smac is set to mac address of
+ * egress device, dmac is set to nexthop mac address, rt_metric
+ * is set to metric from route (IPv4/IPv6 only), and ifindex
+ * is set to the device index of the nexthop from the FIB lookup.
+ *
+ * *plen* argument is the size of the passed in struct.
+ * *flags* argument can be a combination of one or more of the
+ * following values:
+ *
+ * **BPF_FIB_LOOKUP_DIRECT**
+ * Do a direct table lookup vs full lookup using FIB
+ * rules.
+ * **BPF_FIB_LOOKUP_TBID**
+ * Used with BPF_FIB_LOOKUP_DIRECT.
+ * Use the routing table ID present in *params*->tbid
+ * for the fib lookup.
+ * **BPF_FIB_LOOKUP_OUTPUT**
+ * Perform lookup from an egress perspective (default is
+ * ingress).
+ * **BPF_FIB_LOOKUP_SKIP_NEIGH**
+ * Skip the neighbour table lookup. *params*->dmac
+ * and *params*->smac will not be set as output. A common
+ * use case is to call **bpf_redirect_neigh**\ () after
+ * doing **bpf_fib_lookup**\ ().
+ * **BPF_FIB_LOOKUP_SRC**
+ * Derive and set source IP addr in *params*->ipv{4,6}_src
+ * for the nexthop. If the src addr cannot be derived,
+ * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
+ * case, *params*->dmac and *params*->smac are not set either.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** tc cls_act programs.
+ * Return
+ * * < 0 if any input argument is invalid
+ * * 0 on success (packet is forwarded, nexthop neighbor exists)
+ * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ * packet is not forwarded or needs assist from full stack
+ *
+ * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ * was exceeded and output params->mtu_result contains the MTU.
+ *
+ * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Add an entry to, or update a sockhash *map* referencing sockets.
+ * The *skops* is used as a new value for the entry associated to
+ * *key*. *flags* is one of:
+ *
+ * **BPF_NOEXIST**
+ * The entry for *key* must not exist in the map.
+ * **BPF_EXIST**
+ * The entry for *key* must already exist in the map.
+ * **BPF_ANY**
+ * No condition on the existence of the entry for *key*.
+ *
+ * If the *map* has eBPF programs (parser and verdict), those will
+ * be inherited by the socket being added. If the socket is
+ * already attached to eBPF programs, this results in an error.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * socket level. If the message *msg* is allowed to pass (i.e. if
+ * the verdict eBPF program returns **SK_PASS**), redirect it to
+ * the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress path otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * long bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * This helper is used in programs implementing policies at the
+ * skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
+ * if the verdict eBPF program returns **SK_PASS**), redirect it
+ * to the socket referenced by *map* (of type
+ * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
+ * egress interfaces can be used for redirection. The
+ * **BPF_F_INGRESS** value in *flags* is used to make the
+ * distinction (ingress path is selected if the flag is present,
+ * egress otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * long bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
+ * Description
+ * Encapsulate the packet associated to *skb* within a Layer 3
+ * protocol header. This header is provided in the buffer at
+ * address *hdr*, with *len* its size in bytes. *type* indicates
+ * the protocol of the header and can be one of:
+ *
+ * **BPF_LWT_ENCAP_SEG6**
+ * IPv6 encapsulation with Segment Routing Header
+ * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH,
+ * the IPv6 header is computed by the kernel.
+ * **BPF_LWT_ENCAP_SEG6_INLINE**
+ * Only works if *skb* contains an IPv6 packet. Insert a
+ * Segment Routing Header (**struct ipv6_sr_hdr**) inside
+ * the IPv6 header.
+ * **BPF_LWT_ENCAP_IP**
+ * IP encapsulation (GRE/GUE/IPIP/etc). The outer header
+ * must be IPv4 or IPv6, followed by zero or more
+ * additional headers, up to **LWT_BPF_MAX_HEADROOM**
+ * total bytes in all prepended headers. Please note that
+ * if **skb_is_gso**\ (*skb*) is true, no more than two
+ * headers can be prepended, and the inner header, if
+ * present, should be either GRE or UDP/GUE.
+ *
+ * **BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs
+ * of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can
+ * be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and
+ * **BPF_PROG_TYPE_LWT_XMIT**.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len)
+ * Description
+ * Store *len* bytes from address *from* into the packet
+ * associated to *skb*, at *offset*. Only the flags, tag and TLVs
+ * inside the outermost IPv6 Segment Routing Header can be
+ * modified through this helper.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta)
+ * Description
+ * Adjust the size allocated to TLVs in the outermost IPv6
+ * Segment Routing Header contained in the packet associated to
+ * *skb*, at position *offset* by *delta* bytes. Only offsets
+ * after the segments are accepted. *delta* can be as well
+ * positive (growing) as negative (shrinking).
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len)
+ * Description
+ * Apply an IPv6 Segment Routing action of type *action* to the
+ * packet associated to *skb*. Each action takes a parameter
+ * contained at address *param*, and of length *param_len* bytes.
+ * *action* can be one of:
+ *
+ * **SEG6_LOCAL_ACTION_END_X**
+ * End.X action: Endpoint with Layer-3 cross-connect.
+ * Type of *param*: **struct in6_addr**.
+ * **SEG6_LOCAL_ACTION_END_T**
+ * End.T action: Endpoint with specific IPv6 table lookup.
+ * Type of *param*: **int**.
+ * **SEG6_LOCAL_ACTION_END_B6**
+ * End.B6 action: Endpoint bound to an SRv6 policy.
+ * Type of *param*: **struct ipv6_sr_hdr**.
+ * **SEG6_LOCAL_ACTION_END_B6_ENCAP**
+ * End.B6.Encap action: Endpoint bound to an SRv6
+ * encapsulation policy.
+ * Type of *param*: **struct ipv6_sr_hdr**.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * packet buffer. Therefore, at load time, all checks on pointers
+ * previously done by the verifier are invalidated and must be
+ * performed again, if the helper is used in combination with
+ * direct packet access.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_rc_repeat(void *ctx)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded repeat key message. This delays
+ * the generation of a key up event for previously generated
+ * key down event.
+ *
+ * Some IR protocols like NEC have a special IR message for
+ * repeating last button, for when a button is held down.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ * Return
+ * 0
+ *
+ * long bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded key press with *scancode*,
+ * *toggle* value in the given *protocol*. The scancode will be
+ * translated to a keycode using the rc keymap, and reported as
+ * an input key down event. After a period a key up event is
+ * generated. This period can be extended by calling either
+ * **bpf_rc_keydown**\ () again with the same values, or calling
+ * **bpf_rc_repeat**\ ().
+ *
+ * Some protocols include a toggle bit, in case the button was
+ * released and pressed again between consecutive scancodes.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * The *protocol* is the decoded protocol number (see
+ * **enum rc_proto** for some predefined values).
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ * Return
+ * 0
+ *
+ * u64 bpf_skb_cgroup_id(struct sk_buff *skb)
+ * Description
+ * Return the cgroup v2 id of the socket associated with the *skb*.
+ * This is roughly similar to the **bpf_get_cgroup_classid**\ ()
+ * helper for cgroup v1 by providing a tag resp. identifier that
+ * can be matched on or used for map lookups e.g. to implement
+ * policy. The cgroup v2 id of a given path in the hierarchy is
+ * exposed in user space through the f_handle API in order to get
+ * to the same 64-bit id.
+ *
+ * This helper can be used on TC egress path, but not on ingress,
+ * and is available only if the kernel was compiled with the
+ * **CONFIG_SOCK_CGROUP_DATA** configuration option.
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * u64 bpf_get_current_cgroup_id(void)
+ * Description
+ * Get the current cgroup id based on the cgroup within which
+ * the current task is running.
+ * Return
+ * A 64-bit integer containing the current cgroup id based
+ * on the cgroup within which the current task is running.
+ *
+ * void *bpf_get_local_storage(void *map, u64 flags)
+ * Description
+ * Get the pointer to the local storage area.
+ * The type and the size of the local storage is defined
+ * by the *map* argument.
+ * The *flags* meaning is specific for each map type,
+ * and has to be 0 for cgroup local storage.
+ *
+ * Depending on the BPF program type, a local storage area
+ * can be shared between multiple instances of the BPF program,
+ * running simultaneously.
+ *
+ * A user should care about the synchronization by himself.
+ * For example, by using the **BPF_ATOMIC** instructions to alter
+ * the shared data.
+ * Return
+ * A pointer to the local storage area.
+ *
+ * long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Select a **SO_REUSEPORT** socket from a
+ * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*.
+ * It checks the selected socket is matching the incoming
+ * request in the socket buffer.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *skb* at the *ancestor_level*. The root cgroup is at
+ * *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with *skb*, then return value will be same as that
+ * of **bpf_skb_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *skb*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_skb_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ * Description
+ * Look for TCP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ * The *ctx* should point to the context of the program, such as
+ * the skb or socket (depending on the hook in use). This is used
+ * to determine the base network namespace for the lookup.
+ *
+ * *tuple_size* must be one of:
+ *
+ * **sizeof**\ (*tuple*\ **->ipv4**)
+ * Look for an IPv4 socket.
+ * **sizeof**\ (*tuple*\ **->ipv6**)
+ * Look for an IPv6 socket.
+ *
+ * If the *netns* is a negative signed 32-bit integer, then the
+ * socket lookup table in the netns associated with the *ctx*
+ * will be used. For the TC hooks, this is the netns of the device
+ * in the skb. For socket hooks, this is the netns of the socket.
+ * If *netns* is any other signed 32-bit value greater than or
+ * equal to zero then it specifies the ID of the netns relative to
+ * the netns associated with the *ctx*. *netns* values beyond the
+ * range of 32-bit integers are reserved for future use.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_NET** configuration option.
+ * Return
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from *reuse*\ **->socks**\ [] using the hash of the
+ * tuple.
+ *
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ * Description
+ * Look for UDP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ * The *ctx* should point to the context of the program, such as
+ * the skb or socket (depending on the hook in use). This is used
+ * to determine the base network namespace for the lookup.
+ *
+ * *tuple_size* must be one of:
+ *
+ * **sizeof**\ (*tuple*\ **->ipv4**)
+ * Look for an IPv4 socket.
+ * **sizeof**\ (*tuple*\ **->ipv6**)
+ * Look for an IPv6 socket.
+ *
+ * If the *netns* is a negative signed 32-bit integer, then the
+ * socket lookup table in the netns associated with the *ctx*
+ * will be used. For the TC hooks, this is the netns of the device
+ * in the skb. For socket hooks, this is the netns of the socket.
+ * If *netns* is any other signed 32-bit value greater than or
+ * equal to zero then it specifies the ID of the netns relative to
+ * the netns associated with the *ctx*. *netns* values beyond the
+ * range of 32-bit integers are reserved for future use.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_NET** configuration option.
+ * Return
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from *reuse*\ **->socks**\ [] using the hash of the
+ * tuple.
+ *
+ * long bpf_sk_release(void *sock)
+ * Description
+ * Release the reference held by *sock*. *sock* must be a
+ * non-**NULL** pointer that was returned from
+ * **bpf_sk_lookup_xxx**\ ().
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * Description
+ * Push an element *value* in *map*. *flags* is one of:
+ *
+ * **BPF_EXIST**
+ * If the queue/stack is full, the oldest element is
+ * removed to make room for this.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * Description
+ * Pop an element from *map*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * Description
+ * Get an element from *map* without removing it.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
+ * Description
+ * For socket policies, insert *len* bytes into *msg* at offset
+ * *start*.
+ *
+ * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ * *msg* it may want to insert metadata or options into the *msg*.
+ * This can later be read and used by any of the lower layer BPF
+ * hooks.
+ *
+ * This helper may fail if under memory pressure (a malloc
+ * fails) in these cases BPF programs will get an appropriate
+ * error and BPF programs will need to handle them.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
+ * Description
+ * Will remove *len* bytes from a *msg* starting at byte *start*.
+ * This may result in **ENOMEM** errors under certain situations if
+ * an allocation and copy are required due to a full ring buffer.
+ * However, the helper will try to avoid doing the allocation
+ * if possible. Other errors can occur if input parameters are
+ * invalid either due to *start* byte not being valid part of *msg*
+ * payload and/or *pop* value being to large.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded pointer movement.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ * Return
+ * 0
+ *
+ * long bpf_spin_lock(struct bpf_spin_lock *lock)
+ * Description
+ * Acquire a spinlock represented by the pointer *lock*, which is
+ * stored as part of a value of a map. Taking the lock allows to
+ * safely update the rest of the fields in that value. The
+ * spinlock can (and must) later be released with a call to
+ * **bpf_spin_unlock**\ (\ *lock*\ ).
+ *
+ * Spinlocks in BPF programs come with a number of restrictions
+ * and constraints:
+ *
+ * * **bpf_spin_lock** objects are only allowed inside maps of
+ * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
+ * list could be extended in the future).
+ * * BTF description of the map is mandatory.
+ * * The BPF program can take ONE lock at a time, since taking two
+ * or more could cause dead locks.
+ * * Only one **struct bpf_spin_lock** is allowed per map element.
+ * * When the lock is taken, calls (either BPF to BPF or helpers)
+ * are not allowed.
+ * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
+ * allowed inside a spinlock-ed region.
+ * * The BPF program MUST call **bpf_spin_unlock**\ () to release
+ * the lock, on all execution paths, before it returns.
+ * * The BPF program can access **struct bpf_spin_lock** only via
+ * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
+ * helpers. Loading or storing data into the **struct
+ * bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
+ * * To use the **bpf_spin_lock**\ () helper, the BTF description
+ * of the map value must be a struct and have **struct
+ * bpf_spin_lock** *anyname*\ **;** field at the top level.
+ * Nested lock inside another struct is not allowed.
+ * * The **struct bpf_spin_lock** *lock* field in a map value must
+ * be aligned on a multiple of 4 bytes in that value.
+ * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
+ * the **bpf_spin_lock** field to user space.
+ * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
+ * a BPF program, do not update the **bpf_spin_lock** field.
+ * * **bpf_spin_lock** cannot be on the stack or inside a
+ * networking packet (it can only be inside of a map values).
+ * * **bpf_spin_lock** is available to root only.
+ * * Tracing programs and socket filter programs cannot use
+ * **bpf_spin_lock**\ () due to insufficient preemption checks
+ * (but this may change in the future).
+ * * **bpf_spin_lock** is not allowed in inner maps of map-in-map.
+ * Return
+ * 0
+ *
+ * long bpf_spin_unlock(struct bpf_spin_lock *lock)
+ * Description
+ * Release the *lock* previously locked by a call to
+ * **bpf_spin_lock**\ (\ *lock*\ ).
+ * Return
+ * 0
+ *
+ * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
+ * Description
+ * This helper gets a **struct bpf_sock** pointer such
+ * that all the fields in this **bpf_sock** can be accessed.
+ * Return
+ * A **struct bpf_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
+ * Description
+ * This helper gets a **struct bpf_tcp_sock** pointer from a
+ * **struct bpf_sock** pointer.
+ * Return
+ * A **struct bpf_tcp_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * long bpf_skb_ecn_set_ce(struct sk_buff *skb)
+ * Description
+ * Set ECN (Explicit Congestion Notification) field of IP header
+ * to **CE** (Congestion Encountered) if current value is **ECT**
+ * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6
+ * and IPv4.
+ * Return
+ * 1 if the **CE** flag is set (either by the current helper call
+ * or because it was already present), 0 if it is not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ * Description
+ * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
+ * **bpf_sk_release**\ () is unnecessary and not allowed.
+ * Return
+ * A **struct bpf_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ * Description
+ * Look for TCP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ * This function is identical to **bpf_sk_lookup_tcp**\ (), except
+ * that it also returns timewait or request sockets. Use
+ * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the
+ * full structure.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_NET** configuration option.
+ * Return
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from *reuse*\ **->socks**\ [] using the hash of the
+ * tuple.
+ *
+ * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK for
+ * the listening socket in *sk*.
+ *
+ * *iph* points to the start of the IPv4 or IPv6 header, while
+ * *iph_len* contains **sizeof**\ (**struct iphdr**) or
+ * **sizeof**\ (**struct ipv6hdr**).
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
+ * error otherwise.
+ *
+ * long bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
+ * Description
+ * Get name of sysctl in /proc/sys/ and copy it into provided by
+ * program buffer *buf* of size *buf_len*.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ *
+ * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is
+ * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name
+ * only (e.g. "tcp_mem").
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * long bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * Description
+ * Get current value of sysctl as it is presented in /proc/sys
+ * (incl. newline, etc), and copy it as a string into provided
+ * by program buffer *buf* of size *buf_len*.
+ *
+ * The whole value is copied, no matter what file position user
+ * space issued e.g. sys_read at.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * **-EINVAL** if current value was unavailable, e.g. because
+ * sysctl is uninitialized and read returns -EIO for it.
+ *
+ * long bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * Description
+ * Get new value being written by user space to sysctl (before
+ * the actual write happens) and copy it as a string into
+ * provided by program buffer *buf* of size *buf_len*.
+ *
+ * User space may write new value at file position > 0.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * **-EINVAL** if sysctl is being read.
+ *
+ * long bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
+ * Description
+ * Override new value being written by user space to sysctl with
+ * value provided by program in buffer *buf* of size *buf_len*.
+ *
+ * *buf* should contain a string in same form as provided by user
+ * space on sysctl write.
+ *
+ * User space may write new value at file position > 0. To override
+ * the whole sysctl value file position should be set to zero.
+ * Return
+ * 0 on success.
+ *
+ * **-E2BIG** if the *buf_len* is too big.
+ *
+ * **-EINVAL** if sysctl is being read.
+ *
+ * long bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
+ * Description
+ * Convert the initial part of the string from buffer *buf* of
+ * size *buf_len* to a long integer according to the given base
+ * and save the result in *res*.
+ *
+ * The string may begin with an arbitrary amount of white space
+ * (as determined by **isspace**\ (3)) followed by a single
+ * optional '**-**' sign.
+ *
+ * Five least significant bits of *flags* encode base, other bits
+ * are currently unused.
+ *
+ * Base must be either 8, 10, 16 or 0 to detect it automatically
+ * similar to user space **strtol**\ (3).
+ * Return
+ * Number of characters consumed on success. Must be positive but
+ * no more than *buf_len*.
+ *
+ * **-EINVAL** if no valid digits were found or unsupported base
+ * was provided.
+ *
+ * **-ERANGE** if resulting value was out of range.
+ *
+ * long bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
+ * Description
+ * Convert the initial part of the string from buffer *buf* of
+ * size *buf_len* to an unsigned long integer according to the
+ * given base and save the result in *res*.
+ *
+ * The string may begin with an arbitrary amount of white space
+ * (as determined by **isspace**\ (3)).
+ *
+ * Five least significant bits of *flags* encode base, other bits
+ * are currently unused.
+ *
+ * Base must be either 8, 10, 16 or 0 to detect it automatically
+ * similar to user space **strtoul**\ (3).
+ * Return
+ * Number of characters consumed on success. Must be positive but
+ * no more than *buf_len*.
+ *
+ * **-EINVAL** if no valid digits were found or unsupported base
+ * was provided.
+ *
+ * **-ERANGE** if resulting value was out of range.
+ *
+ * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
+ * Description
+ * Get a bpf-local-storage from a *sk*.
+ *
+ * Logically, it could be thought of getting the value from
+ * a *map* with *sk* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this
+ * helper enforces the key must be a full socket and the map must
+ * be a **BPF_MAP_TYPE_SK_STORAGE** also.
+ *
+ * Underneath, the value is stored locally at *sk* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf-local-storages residing at *sk*.
+ *
+ * *sk* is a kernel **struct sock** pointer for LSM program.
+ * *sk* is a **struct bpf_sock** pointer for other program types.
+ *
+ * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf-local-storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf-local-storage. If *value* is
+ * **NULL**, the new bpf-local-storage will be zero initialized.
+ * Return
+ * A bpf-local-storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf-local-storage.
+ *
+ * long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
+ * Description
+ * Delete a bpf-local-storage from a *sk*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf-local-storage cannot be found.
+ * **-EINVAL** if sk is not a fullsock (e.g. a request_sock).
+ *
+ * long bpf_send_signal(u32 sig)
+ * Description
+ * Send signal *sig* to the process of the current task.
+ * The signal may be delivered to any of this process's threads.
+ * Return
+ * 0 on success or successfully queued.
+ *
+ * **-EBUSY** if work queue under nmi is full.
+ *
+ * **-EINVAL** if *sig* is invalid.
+ *
+ * **-EPERM** if no permission to send the *sig*.
+ *
+ * **-EAGAIN** if bpf program can try again.
+ *
+ * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
+ *
+ * *iph* points to the start of the IPv4 or IPv6 header, while
+ * *iph_len* contains **sizeof**\ (**struct iphdr**) or
+ * **sizeof**\ (**struct ipv6hdr**).
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header with options (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** SYN cookie cannot be issued due to error
+ *
+ * **-ENOENT** SYN cookie should not be issued (no SYN flood)
+ *
+ * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies
+ *
+ * **-EPROTONOSUPPORT** IP packet version is not 4 or 6
+ *
+ * long bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * Description
+ * Write raw *data* blob into a special BPF perf event held by
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * event must have the following attributes: **PERF_SAMPLE_RAW**
+ * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * **PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * The *flags* are used to indicate the index in *map* for which
+ * the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * to indicate that the index of the current CPU core should be
+ * used.
+ *
+ * The value to write, of *size*, is passed through eBPF stack and
+ * pointed by *data*.
+ *
+ * *ctx* is a pointer to in-kernel struct sk_buff.
+ *
+ * This helper is similar to **bpf_perf_event_output**\ () but
+ * restricted to raw_tracepoint bpf programs.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from user space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from kernel space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe user address
+ * *unsafe_ptr* to *dst*. The *size* should include the
+ * terminating NUL byte. In case the string length is smaller than
+ * *size*, the target is not padded with further NUL bytes. If the
+ * string length is larger than *size*, just *size*-1 bytes are
+ * copied and the last byte is set to NUL.
+ *
+ * On success, returns the number of bytes that were written,
+ * including the terminal NUL. This makes this helper useful in
+ * tracing programs for reading strings, and more importantly to
+ * get its length at runtime. See the following snippet:
+ *
+ * ::
+ *
+ * SEC("kprobe/sys_open")
+ * void bpf_sys_open(struct pt_regs *ctx)
+ * {
+ * char buf[PATHLEN]; // PATHLEN is defined to 256
+ * int res = bpf_probe_read_user_str(buf, sizeof(buf),
+ * ctx->di);
+ *
+ * // Consume buf, for example push it to
+ * // userspace via bpf_perf_event_output(); we
+ * // can use res (the string length) as event
+ * // size, after checking its boundaries.
+ * }
+ *
+ * In comparison, using **bpf_probe_read_user**\ () helper here
+ * instead to read the string would require to estimate the length
+ * at compile time, and would often result in copying more memory
+ * than necessary.
+ *
+ * Another useful use case is when parsing individual process
+ * arguments or individual environment variables navigating
+ * *current*\ **->mm->arg_start** and *current*\
+ * **->mm->env_start**: using this helper and the return value,
+ * one can quickly iterate at the right offset of the memory area.
+ * Return
+ * On success, the strictly positive length of the output string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * long bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
+ * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply.
+ * Return
+ * On success, the strictly positive length of the string, including
+ * the trailing NUL character. On error, a negative value.
+ *
+ * long bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
+ * Description
+ * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**.
+ * *rcv_nxt* is the ack_seq to be sent out.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_send_signal_thread(u32 sig)
+ * Description
+ * Send signal *sig* to the thread corresponding to the current task.
+ * Return
+ * 0 on success or successfully queued.
+ *
+ * **-EBUSY** if work queue under nmi is full.
+ *
+ * **-EINVAL** if *sig* is invalid.
+ *
+ * **-EPERM** if no permission to send the *sig*.
+ *
+ * **-EAGAIN** if bpf program can try again.
+ *
+ * u64 bpf_jiffies64(void)
+ * Description
+ * Obtain the 64bit jiffies
+ * Return
+ * The 64 bit jiffies
+ *
+ * long bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
+ * Description
+ * For an eBPF program attached to a perf event, retrieve the
+ * branch records (**struct perf_branch_entry**) associated to *ctx*
+ * and store it in the buffer pointed by *buf* up to size
+ * *size* bytes.
+ * Return
+ * On success, number of bytes written to *buf*. On error, a
+ * negative value.
+ *
+ * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
+ * instead return the number of bytes required to store all the
+ * branch entries. If this flag is set, *buf* may be NULL.
+ *
+ * **-EINVAL** if arguments invalid or **size** not a multiple
+ * of **sizeof**\ (**struct perf_branch_entry**\ ).
+ *
+ * **-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
+ * Description
+ * Returns 0 on success, values for *pid* and *tgid* as seen from the current
+ * *namespace* will be returned in *nsdata*.
+ * Return
+ * 0 on success, or one of the following in case of failure:
+ *
+ * **-EINVAL** if dev and inum supplied don't match dev_t and inode number
+ * with nsfs of current task, or if dev conversion to dev_t lost high bits.
+ *
+ * **-ENOENT** if pidns does not exists for the current task.
+ *
+ * long bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * Description
+ * Write raw *data* blob into a special BPF perf event held by
+ * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * event must have the following attributes: **PERF_SAMPLE_RAW**
+ * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * **PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * The *flags* are used to indicate the index in *map* for which
+ * the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * to indicate that the index of the current CPU core should be
+ * used.
+ *
+ * The value to write, of *size*, is passed through eBPF stack and
+ * pointed by *data*.
+ *
+ * *ctx* is a pointer to in-kernel struct xdp_buff.
+ *
+ * This helper is similar to **bpf_perf_eventoutput**\ () but
+ * restricted to raw_tracepoint bpf programs.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_get_netns_cookie(void *ctx)
+ * Description
+ * Retrieve the cookie (generated by the kernel) of the network
+ * namespace the input *ctx* is associated with. The network
+ * namespace cookie remains stable for its lifetime and provides
+ * a global identifier that can be assumed unique. If *ctx* is
+ * NULL, then the helper returns the cookie for the initial
+ * network namespace. The cookie itself is very similar to that
+ * of **bpf_get_socket_cookie**\ () helper, but for network
+ * namespaces instead of sockets.
+ * Return
+ * A 8-byte long opaque number.
+ *
+ * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of the cgroup associated
+ * with the current task at the *ancestor_level*. The root cgroup
+ * is at *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with the current task, then return value will be the
+ * same as that of **bpf_get_current_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with the current task.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_get_current_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags)
+ * Description
+ * Helper is overloaded depending on BPF program type. This
+ * description applies to **BPF_PROG_TYPE_SCHED_CLS** and
+ * **BPF_PROG_TYPE_SCHED_ACT** programs.
+ *
+ * Assign the *sk* to the *skb*. When combined with appropriate
+ * routing configuration to receive the packet towards the socket,
+ * will cause *skb* to be delivered to the specified socket.
+ * Subsequent redirection of *skb* via **bpf_redirect**\ (),
+ * **bpf_clone_redirect**\ () or other methods outside of BPF may
+ * interfere with successful delivery to the socket.
+ *
+ * This operation is only valid from TC ingress path.
+ *
+ * The *flags* argument must be zero.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EINVAL** if specified *flags* are not supported.
+ *
+ * **-ENOENT** if the socket is unavailable for assignment.
+ *
+ * **-ENETUNREACH** if the socket is unreachable (wrong netns).
+ *
+ * **-EOPNOTSUPP** if the operation is not supported, for example
+ * a call from outside of TC ingress.
+ *
+ * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
+ * Description
+ * Helper is overloaded depending on BPF program type. This
+ * description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs.
+ *
+ * Select the *sk* as a result of a socket lookup.
+ *
+ * For the operation to succeed passed socket must be compatible
+ * with the packet description provided by the *ctx* object.
+ *
+ * L4 protocol (**IPPROTO_TCP** or **IPPROTO_UDP**) must
+ * be an exact match. While IP family (**AF_INET** or
+ * **AF_INET6**) must be compatible, that is IPv6 sockets
+ * that are not v6-only can be selected for IPv4 packets.
+ *
+ * Only TCP listeners and UDP unconnected sockets can be
+ * selected. *sk* can also be NULL to reset any previous
+ * selection.
+ *
+ * *flags* argument can combination of following values:
+ *
+ * * **BPF_SK_LOOKUP_F_REPLACE** to override the previous
+ * socket selection, potentially done by a BPF program
+ * that ran before us.
+ *
+ * * **BPF_SK_LOOKUP_F_NO_REUSEPORT** to skip
+ * load-balancing within reuseport group for the socket
+ * being selected.
+ *
+ * On success *ctx->sk* will point to the selected socket.
+ *
+ * Return
+ * 0 on success, or a negative errno in case of failure.
+ *
+ * * **-EAFNOSUPPORT** if socket family (*sk->family*) is
+ * not compatible with packet family (*ctx->family*).
+ *
+ * * **-EEXIST** if socket has been already selected,
+ * potentially by another program, and
+ * **BPF_SK_LOOKUP_F_REPLACE** flag was not specified.
+ *
+ * * **-EINVAL** if unsupported flags were specified.
+ *
+ * * **-EPROTOTYPE** if socket L4 protocol
+ * (*sk->protocol*) doesn't match packet protocol
+ * (*ctx->protocol*).
+ *
+ * * **-ESOCKTNOSUPPORT** if socket is not in allowed
+ * state (TCP listening or UDP unconnected).
+ *
+ * u64 bpf_ktime_get_boot_ns(void)
+ * Description
+ * Return the time elapsed since system boot, in nanoseconds.
+ * Does include the time the system was suspended.
+ * See: **clock_gettime**\ (**CLOCK_BOOTTIME**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * Description
+ * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print
+ * out the format string.
+ * The *m* represents the seq_file. The *fmt* and *fmt_size* are for
+ * the format string itself. The *data* and *data_len* are format string
+ * arguments. The *data* are a **u64** array and corresponding format string
+ * values are stored in the array. For strings and pointers where pointees
+ * are accessed, only the pointer values are stored in the *data* array.
+ * The *data_len* is the size of *data* in bytes - must be a multiple of 8.
+ *
+ * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
+ * Reading kernel memory may fail due to either invalid address or
+ * valid address but requiring a major memory fault. If reading kernel memory
+ * fails, the string for **%s** will be an empty string, and the ip
+ * address for **%p{i,I}{4,6}** will be 0. Not returning error to
+ * bpf program is consistent with what **bpf_trace_printk**\ () does for now.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EBUSY** if per-CPU memory copy buffer is busy, can try again
+ * by returning 1 from bpf program.
+ *
+ * **-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported.
+ *
+ * **-E2BIG** if *fmt* contains too many format specifiers.
+ *
+ * **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * long bpf_seq_write(struct seq_file *m, const void *data, u32 len)
+ * Description
+ * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data.
+ * The *m* represents the seq_file. The *data* and *len* represent the
+ * data to write in bytes.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * u64 bpf_sk_cgroup_id(void *sk)
+ * Description
+ * Return the cgroup v2 id of the socket *sk*.
+ *
+ * *sk* must be a non-**NULL** pointer to a socket, e.g. one
+ * returned from **bpf_sk_lookup_xxx**\ (),
+ * **bpf_sk_fullsock**\ (), etc. The format of returned id is
+ * same as in **bpf_skb_cgroup_id**\ ().
+ *
+ * This helper is available only if the kernel was compiled with
+ * the **CONFIG_SOCK_CGROUP_DATA** configuration option.
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *sk* at the *ancestor_level*. The root cgroup is at
+ * *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with *sk*, then return value will be same as that
+ * of **bpf_sk_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *sk*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_sk_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
+ * Description
+ * Copy *size* bytes from *data* into a ring buffer *ringbuf*.
+ * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * of new data availability is sent.
+ * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * of new data availability is sent unconditionally.
+ * If **0** is specified in *flags*, an adaptive notification
+ * of new data availability is sent.
+ *
+ * An adaptive notification is a notification sent whenever the user-space
+ * process has caught up and consumed all available payloads. In case the user-space
+ * process is still processing a previous payload, then no notification is needed
+ * as it will process the newly added payload automatically.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
+ * Description
+ * Reserve *size* bytes of payload in a ring buffer *ringbuf*.
+ * *flags* must be 0.
+ * Return
+ * Valid pointer with *size* bytes of memory available; NULL,
+ * otherwise.
+ *
+ * void bpf_ringbuf_submit(void *data, u64 flags)
+ * Description
+ * Submit reserved ring buffer sample, pointed to by *data*.
+ * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * of new data availability is sent.
+ * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * of new data availability is sent unconditionally.
+ * If **0** is specified in *flags*, an adaptive notification
+ * of new data availability is sent.
+ *
+ * See 'bpf_ringbuf_output()' for the definition of adaptive notification.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard(void *data, u64 flags)
+ * Description
+ * Discard reserved ring buffer sample, pointed to by *data*.
+ * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * of new data availability is sent.
+ * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * of new data availability is sent unconditionally.
+ * If **0** is specified in *flags*, an adaptive notification
+ * of new data availability is sent.
+ *
+ * See 'bpf_ringbuf_output()' for the definition of adaptive notification.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * u64 bpf_ringbuf_query(void *ringbuf, u64 flags)
+ * Description
+ * Query various characteristics of provided ring buffer. What
+ * exactly is queries is determined by *flags*:
+ *
+ * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed.
+ * * **BPF_RB_RING_SIZE**: The size of ring buffer.
+ * * **BPF_RB_CONS_POS**: Consumer position (can wrap around).
+ * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around).
+ *
+ * Data returned is just a momentary snapshot of actual values
+ * and could be inaccurate, so this facility should be used to
+ * power heuristics and for reporting, not to make 100% correct
+ * calculation.
+ * Return
+ * Requested value, or 0, if *flags* are not recognized.
+ *
+ * long bpf_csum_level(struct sk_buff *skb, u64 level)
+ * Description
+ * Change the skbs checksum level by one layer up or down, or
+ * reset it entirely to none in order to have the stack perform
+ * checksum validation. The level is applicable to the following
+ * protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of
+ * | ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP |
+ * through **bpf_skb_adjust_room**\ () helper with passing in
+ * **BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one call
+ * to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since
+ * the UDP header is removed. Similarly, an encap of the latter
+ * into the former could be accompanied by a helper call to
+ * **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the
+ * skb is still intended to be processed in higher layers of the
+ * stack instead of just egressing at tc.
+ *
+ * There are three supported level settings at this time:
+ *
+ * * **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs
+ * with CHECKSUM_UNNECESSARY.
+ * * **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs
+ * with CHECKSUM_UNNECESSARY.
+ * * **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and
+ * sets CHECKSUM_NONE to force checksum validation by the stack.
+ * * **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current
+ * skb->csum_level.
+ * Return
+ * 0 on success, or a negative error in case of failure. In the
+ * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
+ * is returned or the error code -EACCES in case the skb is not
+ * subject to CHECKSUM_UNNECESSARY.
+ *
+ * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
+ * Description
+ * Return a user or a kernel stack in bpf program provided buffer.
+ * Note: the user stack will only be populated if the *task* is
+ * the current task; all other tasks will return -EOPNOTSUPP.
+ * To achieve this, the helper needs *task*, which is a valid
+ * pointer to **struct task_struct**. To store the stacktrace, the
+ * bpf program provides *buf* with a nonnegative *size*.
+ *
+ * The last argument, *flags*, holds the number of stack frames to
+ * skip (from 0 to 255), masked with
+ * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
+ * the following flags:
+ *
+ * **BPF_F_USER_STACK**
+ * Collect a user space stack instead of a kernel stack.
+ * The *task* must be the current task.
+ * **BPF_F_USER_BUILD_ID**
+ * Collect buildid+offset instead of ips for user stack,
+ * only valid if **BPF_F_USER_STACK** is also specified.
+ *
+ * **bpf_get_task_stack**\ () can collect up to
+ * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
+ * to sufficient large buffer size. Note that
+ * this limit can be controlled with the **sysctl** program, and
+ * that it should be manually increased in order to profile long
+ * user stacks (such as stacks for Java programs). To do so, use:
+ *
+ * ::
+ *
+ * # sysctl kernel.perf_event_max_stack=<new value>
+ * Return
+ * The non-negative copied *buf* length equal to or less than
+ * *size* on success, or a negative error in case of failure.
+ *
+ * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
+ * Description
+ * Load header option. Support reading a particular TCP header
+ * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**).
+ *
+ * If *flags* is 0, it will search the option from the
+ * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops**
+ * has details on what skb_data contains under different
+ * *skops*\ **->op**.
+ *
+ * The first byte of the *searchby_res* specifies the
+ * kind that it wants to search.
+ *
+ * If the searching kind is an experimental kind
+ * (i.e. 253 or 254 according to RFC6994). It also
+ * needs to specify the "magic" which is either
+ * 2 bytes or 4 bytes. It then also needs to
+ * specify the size of the magic by using
+ * the 2nd byte which is "kind-length" of a TCP
+ * header option and the "kind-length" also
+ * includes the first 2 bytes "kind" and "kind-length"
+ * itself as a normal TCP header option also does.
+ *
+ * For example, to search experimental kind 254 with
+ * 2 byte magic 0xeB9F, the searchby_res should be
+ * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
+ *
+ * To search for the standard window scale option (3),
+ * the *searchby_res* should be [ 3, 0, 0, .... 0 ].
+ * Note, kind-length must be 0 for regular option.
+ *
+ * Searching for No-Op (0) and End-of-Option-List (1) are
+ * not supported.
+ *
+ * *len* must be at least 2 bytes which is the minimal size
+ * of a header option.
+ *
+ * Supported flags:
+ *
+ * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
+ * saved_syn packet or the just-received syn packet.
+ *
+ * Return
+ * > 0 when found, the header option is copied to *searchby_res*.
+ * The return value is the total length copied. On failure, a
+ * negative error code is returned:
+ *
+ * **-EINVAL** if a parameter is invalid.
+ *
+ * **-ENOMSG** if the option is not found.
+ *
+ * **-ENOENT** if no syn packet is available when
+ * **BPF_LOAD_HDR_OPT_TCP_SYN** is used.
+ *
+ * **-ENOSPC** if there is not enough space. Only *len* number of
+ * bytes are copied.
+ *
+ * **-EFAULT** on failure to parse the header options in the
+ * packet.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
+ * Description
+ * Store header option. The data will be copied
+ * from buffer *from* with length *len* to the TCP header.
+ *
+ * The buffer *from* should have the whole option that
+ * includes the kind, kind-length, and the actual
+ * option data. The *len* must be at least kind-length
+ * long. The kind-length does not have to be 4 byte
+ * aligned. The kernel will take care of the padding
+ * and setting the 4 bytes aligned value to th->doff.
+ *
+ * This helper will check for duplicated option
+ * by searching the same option in the outgoing skb.
+ *
+ * This helper can only be called during
+ * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** If param is invalid.
+ *
+ * **-ENOSPC** if there is not enough space in the header.
+ * Nothing has been written
+ *
+ * **-EEXIST** if the option already exists.
+ *
+ * **-EFAULT** on failure to parse the existing header options.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
+ * Description
+ * Reserve *len* bytes for the bpf header option. The
+ * space will be used by **bpf_store_hdr_opt**\ () later in
+ * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
+ *
+ * If **bpf_reserve_hdr_opt**\ () is called multiple times,
+ * the total number of bytes will be reserved.
+ *
+ * This helper can only be called during
+ * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** if a parameter is invalid.
+ *
+ * **-ENOSPC** if there is not enough space in the header.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from an *inode*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *inode* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this
+ * helper enforces the key must be an inode and the map must also
+ * be a **BPF_MAP_TYPE_INODE_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *inode* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *inode*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * int bpf_inode_storage_delete(struct bpf_map *map, void *inode)
+ * Description
+ * Delete a bpf_local_storage from an *inode*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * long bpf_d_path(struct path *path, char *buf, u32 sz)
+ * Description
+ * Return full path for given **struct path** object, which
+ * needs to be the kernel BTF *path* object. The path is
+ * returned in the provided buffer *buf* of size *sz* and
+ * is zero terminated.
+ *
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
+ * Description
+ * Read *size* bytes from user space address *user_ptr* and store
+ * the data in *dst*. This is a wrapper of **copy_from_user**\ ().
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ * Description
+ * Use BTF to store a string representation of *ptr*->ptr in *str*,
+ * using *ptr*->type_id. This value should specify the type
+ * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ * can be used to look up vmlinux BTF type ids. Traversing the
+ * data structure using BTF, the type information and values are
+ * stored in the first *str_size* - 1 bytes of *str*. Safe copy of
+ * the pointer data is carried out to avoid kernel crashes during
+ * operation. Smaller types can use string space on the stack;
+ * larger programs can use map data to store the string
+ * representation.
+ *
+ * The string can be subsequently shared with userspace via
+ * bpf_perf_event_output() or ring buffer interfaces.
+ * bpf_trace_printk() is to be avoided as it places too small
+ * a limit on string size to be useful.
+ *
+ * *flags* is a combination of
+ *
+ * **BTF_F_COMPACT**
+ * no formatting around type information
+ * **BTF_F_NONAME**
+ * no struct/union member names/types
+ * **BTF_F_PTR_RAW**
+ * show raw (unobfuscated) pointer values;
+ * equivalent to printk specifier %px.
+ * **BTF_F_ZERO**
+ * show zero-valued struct/union members; they
+ * are not displayed by default
+ *
+ * Return
+ * The number of bytes that were written (or would have been
+ * written if output had to be truncated due to string size),
+ * or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ * Description
+ * Use BTF to write to seq_write a string representation of
+ * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ * *flags* are identical to those used for bpf_snprintf_btf.
+ * Return
+ * 0 on success or a negative error in case of failure.
+ *
+ * u64 bpf_skb_cgroup_classid(struct sk_buff *skb)
+ * Description
+ * See **bpf_get_cgroup_classid**\ () for the main description.
+ * This helper differs from **bpf_get_cgroup_classid**\ () in that
+ * the cgroup v1 net_cls class is retrieved only from the *skb*'s
+ * associated socket instead of the current process.
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*
+ * and fill in L2 addresses from neighboring subsystem. This helper
+ * is somewhat similar to **bpf_redirect**\ (), except that it
+ * populates L2 addresses as well, meaning, internally, the helper
+ * relies on the neighbor lookup for the L2 address of the nexthop.
+ *
+ * The helper will perform a FIB lookup based on the skb's
+ * networking header to get the address of the next hop, unless
+ * this is supplied by the caller in the *params* argument. The
+ * *plen* argument indicates the len of *params* and should be set
+ * to 0 if *params* is NULL.
+ *
+ * The *flags* argument is reserved and must be 0. The helper is
+ * currently only supported for tc BPF program types, and enabled
+ * for IPv4 and IPv6 protocols.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
+ *
+ * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu)
+ * Description
+ * Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ * pointer to the percpu kernel variable on *cpu*. A ksym is an
+ * extern variable decorated with '__ksym'. For ksym, there is a
+ * global var (either static or global) defined of the same name
+ * in the kernel. The ksym is percpu if the global var is percpu.
+ * The returned pointer points to the global percpu var on *cpu*.
+ *
+ * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the
+ * kernel, except that bpf_per_cpu_ptr() may return NULL. This
+ * happens if *cpu* is larger than nr_cpu_ids. The caller of
+ * bpf_per_cpu_ptr() must check the returned value.
+ * Return
+ * A pointer pointing to the kernel percpu variable on *cpu*, or
+ * NULL, if *cpu* is invalid.
+ *
+ * void *bpf_this_cpu_ptr(const void *percpu_ptr)
+ * Description
+ * Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ * pointer to the percpu kernel variable on this cpu. See the
+ * description of 'ksym' in **bpf_per_cpu_ptr**\ ().
+ *
+ * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in
+ * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would
+ * never return NULL.
+ * Return
+ * A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_redirect**\ (), except
+ * that the redirection happens to the *ifindex*' peer device and
+ * the netns switch takes place from ingress to ingress without
+ * going through the CPU's backlog queue.
+ *
+ * The *flags* argument is reserved and must be 0. The helper is
+ * currently only supported for tc BPF program types at the ingress
+ * hook and for veth device types. The peer device must reside in a
+ * different network namespace.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
+ *
+ * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from the *task*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *task* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
+ * helper enforces the key must be a task_struct and the map must also
+ * be a **BPF_MAP_TYPE_TASK_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *task* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *task*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task)
+ * Description
+ * Delete a bpf_local_storage from a *task*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * struct task_struct *bpf_get_current_task_btf(void)
+ * Description
+ * Return a BTF pointer to the "current" task.
+ * This pointer can also be used in helpers that accept an
+ * *ARG_PTR_TO_BTF_ID* of type *task_struct*.
+ * Return
+ * Pointer to the current task.
+ *
+ * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags)
+ * Description
+ * Set or clear certain options on *bprm*:
+ *
+ * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit
+ * which sets the **AT_SECURE** auxv for glibc. The bit
+ * is cleared if the flag is not specified.
+ * Return
+ * **-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ * Description
+ * Return a coarse-grained version of the time elapsed since
+ * system boot, in nanoseconds. Does not include time the system
+ * was suspended.
+ *
+ * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
+ * Description
+ * Returns the stored IMA hash of the *inode* (if it's available).
+ * If the hash is larger than *size*, then only *size*
+ * bytes will be copied to *dst*
+ * Return
+ * The **hash_algo** is returned on success,
+ * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if
+ * invalid arguments are passed.
+ *
+ * struct socket *bpf_sock_from_file(struct file *file)
+ * Description
+ * If the given file represents a socket, returns the associated
+ * socket.
+ * Return
+ * A pointer to a struct socket on success or NULL if the file is
+ * not a socket.
+ *
+ * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
+ * Description
+ * Check packet size against exceeding MTU of net device (based
+ * on *ifindex*). This helper will likely be used in combination
+ * with helpers that adjust/change the packet size.
+ *
+ * The argument *len_diff* can be used for querying with a planned
+ * size change. This allows to check MTU prior to changing packet
+ * ctx. Providing a *len_diff* adjustment that is larger than the
+ * actual packet size (resulting in negative packet size) will in
+ * principle not exceed the MTU, which is why it is not considered
+ * a failure. Other BPF helpers are needed for performing the
+ * planned size change; therefore the responsibility for catching
+ * a negative packet size belongs in those helpers.
+ *
+ * Specifying *ifindex* zero means the MTU check is performed
+ * against the current net device. This is practical if this isn't
+ * used prior to redirect.
+ *
+ * On input *mtu_len* must be a valid pointer, else verifier will
+ * reject BPF program. If the value *mtu_len* is initialized to
+ * zero then the ctx packet size is use. When value *mtu_len* is
+ * provided as input this specify the L3 length that the MTU check
+ * is done against. Remember XDP and TC length operate at L2, but
+ * this value is L3 as this correlate to MTU and IP-header tot_len
+ * values which are L3 (similar behavior as bpf_fib_lookup).
+ *
+ * The Linux kernel route table can configure MTUs on a more
+ * specific per route level, which is not provided by this helper.
+ * For route level MTU checks use the **bpf_fib_lookup**\ ()
+ * helper.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** for tc cls_act programs.
+ *
+ * The *flags* argument can be a combination of one or more of the
+ * following values:
+ *
+ * **BPF_MTU_CHK_SEGS**
+ * This flag will only works for *ctx* **struct sk_buff**.
+ * If packet context contains extra packet segment buffers
+ * (often knows as GSO skb), then MTU check is harder to
+ * check at this point, because in transmit path it is
+ * possible for the skb packet to get re-segmented
+ * (depending on net device features). This could still be
+ * a MTU violation, so this flag enables performing MTU
+ * check against segments, with a different violation
+ * return code to tell it apart. Check cannot use len_diff.
+ *
+ * On return *mtu_len* pointer contains the MTU value of the net
+ * device. Remember the net device configured MTU is the L3 size,
+ * which is returned here and XDP and TC length operate at L2.
+ * Helper take this into account for you, but remember when using
+ * MTU value in your BPF-code.
+ *
+ * Return
+ * * 0 on success, and populate MTU value in *mtu_len* pointer.
+ *
+ * * < 0 if any input argument is invalid (*mtu_len* not updated)
+ *
+ * MTU violations return positive values, but also populate MTU
+ * value in *mtu_len* pointer, as this can be needed for
+ * implementing PMTU handing:
+ *
+ * * **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ * * **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
+ * long bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * For each element in **map**, call **callback_fn** function with
+ * **map**, **callback_ctx** and other map-specific parameters.
+ * The **callback_fn** should be a static function and
+ * the **callback_ctx** should be a pointer to the stack.
+ * The **flags** is used to control certain aspects of the helper.
+ * Currently, the **flags** must be 0.
+ *
+ * The following are a list of supported map types and their
+ * respective expected callback signatures:
+ *
+ * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH,
+ * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH,
+ * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY
+ *
+ * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx);
+ *
+ * For per_cpu maps, the map_value is the value on the cpu where the
+ * bpf_prog is running.
+ *
+ * If **callback_fn** return 0, the helper will continue to the next
+ * element. If return value is 1, the helper will skip the rest of
+ * elements and return. Other return values are not used now.
+ *
+ * Return
+ * The number of traversed map elements for success, **-EINVAL** for
+ * invalid **flags**.
+ *
+ * long bpf_snprintf(char *str, u32 str_size, const char *fmt, u64 *data, u32 data_len)
+ * Description
+ * Outputs a string into the **str** buffer of size **str_size**
+ * based on a format string stored in a read-only map pointed by
+ * **fmt**.
+ *
+ * Each format specifier in **fmt** corresponds to one u64 element
+ * in the **data** array. For strings and pointers where pointees
+ * are accessed, only the pointer values are stored in the *data*
+ * array. The *data_len* is the size of *data* in bytes - must be
+ * a multiple of 8.
+ *
+ * Formats **%s** and **%p{i,I}{4,6}** require to read kernel
+ * memory. Reading kernel memory may fail due to either invalid
+ * address or valid address but requiring a major memory fault. If
+ * reading kernel memory fails, the string for **%s** will be an
+ * empty string, and the ip address for **%p{i,I}{4,6}** will be 0.
+ * Not returning error to bpf program is consistent with what
+ * **bpf_trace_printk**\ () does for now.
+ *
+ * Return
+ * The strictly positive length of the formatted string, including
+ * the trailing zero character. If the return value is greater than
+ * **str_size**, **str** contains a truncated string, guaranteed to
+ * be zero-terminated except when **str_size** is 0.
+ *
+ * Or **-EBUSY** if the per-CPU memory copy buffer is busy.
+ *
+ * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size)
+ * Description
+ * Execute bpf syscall with given arguments.
+ * Return
+ * A syscall result.
+ *
+ * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags)
+ * Description
+ * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs.
+ * Return
+ * Returns btf_id and btf_obj_fd in lower and upper 32 bits.
+ *
+ * long bpf_sys_close(u32 fd)
+ * Description
+ * Execute close syscall for given FD.
+ * Return
+ * A syscall result.
+ *
+ * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags)
+ * Description
+ * Initialize the timer.
+ * First 4 bits of *flags* specify clockid.
+ * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed.
+ * All other bits of *flags* are reserved.
+ * The verifier will reject the program if *timer* is not from
+ * the same *map*.
+ * Return
+ * 0 on success.
+ * **-EBUSY** if *timer* is already initialized.
+ * **-EINVAL** if invalid *flags* are passed.
+ * **-EPERM** if *timer* is in a map that doesn't have any user references.
+ * The user space should either hold a file descriptor to a map with timers
+ * or pin such map in bpffs. When map is unpinned or file descriptor is
+ * closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn)
+ * Description
+ * Configure the timer to call *callback_fn* static function.
+ * Return
+ * 0 on success.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ * **-EPERM** if *timer* is in a map that doesn't have any user references.
+ * The user space should either hold a file descriptor to a map with timers
+ * or pin such map in bpffs. When map is unpinned or file descriptor is
+ * closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags)
+ * Description
+ * Set timer expiration N nanoseconds from the current time. The
+ * configured callback will be invoked in soft irq context on some cpu
+ * and will not repeat unless another bpf_timer_start() is made.
+ * In such case the next invocation can migrate to a different cpu.
+ * Since struct bpf_timer is a field inside map element the map
+ * owns the timer. The bpf_timer_set_callback() will increment refcnt
+ * of BPF program to make sure that callback_fn code stays valid.
+ * When user space reference to a map reaches zero all timers
+ * in a map are cancelled and corresponding program's refcnts are
+ * decremented. This is done to make sure that Ctrl-C of a user
+ * process doesn't leave any timers running. If map is pinned in
+ * bpffs the callback_fn can re-arm itself indefinitely.
+ * bpf_map_update/delete_elem() helpers and user space sys_bpf commands
+ * cancel and free the timer in the given map element.
+ * The map can contain timers that invoke callback_fn-s from different
+ * programs. The same callback_fn can serve different timers from
+ * different maps if key/value layout matches across maps.
+ * Every bpf_timer_set_callback() can have different callback_fn.
+ *
+ * *flags* can be one of:
+ *
+ * **BPF_F_TIMER_ABS**
+ * Start the timer in absolute expire value instead of the
+ * default relative one.
+ * **BPF_F_TIMER_CPU_PIN**
+ * Timer will be pinned to the CPU of the caller.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier
+ * or invalid *flags* are passed.
+ *
+ * long bpf_timer_cancel(struct bpf_timer *timer)
+ * Description
+ * Cancel the timer and wait for callback_fn to finish if it was running.
+ * Return
+ * 0 if the timer was not active.
+ * 1 if the timer was active.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its
+ * own timer which would have led to a deadlock otherwise.
+ *
+ * u64 bpf_get_func_ip(void *ctx)
+ * Description
+ * Get address of the traced function (for tracing and kprobe programs).
+ *
+ * When called for kprobe program attached as uprobe it returns
+ * probe address for both entry and return uprobe.
+ *
+ * Return
+ * Address of the traced function for kprobe.
+ * 0 for kprobes placed within the function (not at the entry).
+ * Address of the probe for uprobe and return uprobe.
+ *
+ * u64 bpf_get_attach_cookie(void *ctx)
+ * Description
+ * Get bpf_cookie value provided (optionally) during the program
+ * attachment. It might be different for each individual
+ * attachment, even if BPF program itself is the same.
+ * Expects BPF program context *ctx* as a first argument.
+ *
+ * Supported for the following program types:
+ * - kprobe/uprobe;
+ * - tracepoint;
+ * - perf_event.
+ * Return
+ * Value specified by user at BPF link creation/attachment time
+ * or 0, if it was not specified.
+ *
+ * long bpf_task_pt_regs(struct task_struct *task)
+ * Description
+ * Get the struct pt_regs associated with **task**.
+ * Return
+ * A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags)
+ * Description
+ * Get branch trace from hardware engines like Intel LBR. The
+ * hardware engine is stopped shortly after the helper is
+ * called. Therefore, the user need to filter branch entries
+ * based on the actual use case. To capture branch trace
+ * before the trigger point of the BPF program, the helper
+ * should be called at the beginning of the BPF program.
+ *
+ * The data is stored as struct perf_branch_entry into output
+ * buffer *entries*. *size* is the size of *entries* in bytes.
+ * *flags* is reserved for now and must be zero.
+ *
+ * Return
+ * On success, number of bytes written to *buf*. On error, a
+ * negative value.
+ *
+ * **-EINVAL** if *flags* is not zero.
+ *
+ * **-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * Description
+ * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ * to format and can handle more format args as a result.
+ *
+ * Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ * Return
+ * The number of bytes written to the buffer, or a negative error
+ * in case of failure.
+ *
+ * struct unix_sock *bpf_skc_to_unix_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *unix_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res)
+ * Description
+ * Get the address of a kernel symbol, returned in *res*. *res* is
+ * set to 0 if the symbol is not found.
+ * Return
+ * On success, zero. On error, a negative value.
+ *
+ * **-EINVAL** if *flags* is not zero.
+ *
+ * **-EINVAL** if string *name* is not the same size as *name_sz*.
+ *
+ * **-ENOENT** if symbol is not found.
+ *
+ * **-EPERM** if caller does not have permission to obtain kernel address.
+ *
+ * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * Find vma of *task* that contains *addr*, call *callback_fn*
+ * function with *task*, *vma*, and *callback_ctx*.
+ * The *callback_fn* should be a static function and
+ * the *callback_ctx* should be a pointer to the stack.
+ * The *flags* is used to control certain aspects of the helper.
+ * Currently, the *flags* must be 0.
+ *
+ * The expected callback signature is
+ *
+ * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx);
+ *
+ * Return
+ * 0 on success.
+ * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
+ * **-EBUSY** if failed to try lock mmap_lock.
+ * **-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * For **nr_loops**, call **callback_fn** function
+ * with **callback_ctx** as the context parameter.
+ * The **callback_fn** should be a static function and
+ * the **callback_ctx** should be a pointer to the stack.
+ * The **flags** is used to control certain aspects of the helper.
+ * Currently, the **flags** must be 0. Currently, nr_loops is
+ * limited to 1 << 23 (~8 million) loops.
+ *
+ * long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ * where **index** is the current index in the loop. The index
+ * is zero-indexed.
+ *
+ * If **callback_fn** returns 0, the helper will continue to the next
+ * loop. If return value is 1, the helper will skip the rest of
+ * the loops and return. Other return values are not used now,
+ * and will be rejected by the verifier.
+ *
+ * Return
+ * The number of loops performed, **-EINVAL** for invalid **flags**,
+ * **-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ * Description
+ * Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ * to be null-terminated and **s1_sz** is the maximum storage
+ * size of **s1**. **s2** must be a read-only string.
+ * Return
+ * An integer less than, equal to, or greater than zero
+ * if the first **s1_sz** bytes of **s1** is found to be
+ * less than, to match, or be greater than **s2**.
+ *
+ * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
+ * Description
+ * Get **n**-th argument register (zero based) of the traced function (for tracing programs)
+ * returned in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if n >= argument register count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ * Description
+ * Get return value of the traced function (for tracing programs)
+ * in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ * Description
+ * Get number of registers of the traced function (for tracing programs) where
+ * function arguments are stored in these registers.
+ *
+ * Return
+ * The number of argument registers of the traced function.
+ *
+ * int bpf_get_retval(void)
+ * Description
+ * Get the BPF program's return value that will be returned to the upper layers.
+ *
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
+ * Return
+ * The BPF program's return value.
+ *
+ * int bpf_set_retval(int retval)
+ * Description
+ * Set the BPF program's return value that will be returned to the upper layers.
+ *
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
+ *
+ * Note that there is the following corner case where the program exports an error
+ * via bpf_set_retval but signals success via 'return 1':
+ *
+ * bpf_set_retval(-EPERM);
+ * return 1;
+ *
+ * In this case, the BPF program's return value will use helper's -EPERM. This
+ * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
+ *
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ * Description
+ * Get the total size of a given xdp buff (linear and paged area)
+ * Return
+ * The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * This helper is provided as an easy way to load data from a
+ * xdp buffer. It can be used to load *len* bytes from *offset* from
+ * the frame associated to *xdp_md*, into the buffer pointed by
+ * *buf*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * Store *len* bytes from buffer *buf* into the frame
+ * associated to *xdp_md*, at *offset*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags)
+ * Description
+ * Read *size* bytes from user space address *user_ptr* in *tsk*'s
+ * address space, and stores the data in *dst*. *flags* is not
+ * used yet and is provided for future extensibility. This helper
+ * can only be used by sleepable programs.
+ * Return
+ * 0 on success, or a negative error in case of failure. On error
+ * *dst* buffer is zeroed out.
+ *
+ * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type)
+ * Description
+ * Change the __sk_buff->tstamp_type to *tstamp_type*
+ * and set *tstamp* to the __sk_buff->tstamp together.
+ *
+ * If there is no need to change the __sk_buff->tstamp_type,
+ * the tstamp value can be directly written to __sk_buff->tstamp
+ * instead.
+ *
+ * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that
+ * will be kept during bpf_redirect_*(). A non zero
+ * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO
+ * *tstamp_type*.
+ *
+ * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used
+ * with a zero *tstamp*.
+ *
+ * Only IPv4 and IPv6 skb->protocol are supported.
+ *
+ * This function is most useful when it needs to set a
+ * mono delivery time to __sk_buff->tstamp and then
+ * bpf_redirect_*() to the egress of an iface. For example,
+ * changing the (rcv) timestamp in __sk_buff->tstamp at
+ * ingress to a mono delivery time and then bpf_redirect_*()
+ * to sch_fq@phy-dev.
+ * Return
+ * 0 on success.
+ * **-EINVAL** for invalid input
+ * **-EOPNOTSUPP** for unsupported protocol
+ *
+ * long bpf_ima_file_hash(struct file *file, void *dst, u32 size)
+ * Description
+ * Returns a calculated IMA hash of the *file*.
+ * If the hash is larger than *size*, then only *size*
+ * bytes will be copied to *dst*
+ * Return
+ * The **hash_algo** is returned on success,
+ * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
+ * invalid arguments are passed.
+ *
+ * void *bpf_kptr_xchg(void *map_value, void *ptr)
+ * Description
+ * Exchange kptr at pointer *map_value* with *ptr*, and return the
+ * old value. *ptr* can be NULL, otherwise it must be a referenced
+ * pointer which will be released when this helper is called.
+ * Return
+ * The old value of kptr (which can be NULL). The returned pointer
+ * if not NULL, is a reference which must be released using its
+ * corresponding release function, or moved into a BPF map before
+ * program exit.
+ *
+ * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu)
+ * Description
+ * Perform a lookup in *percpu map* for an entry associated to
+ * *key* on *cpu*.
+ * Return
+ * Map value associated to *key* on *cpu*, or **NULL** if no entry
+ * was found or *cpu* is invalid.
+ *
+ * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Get a dynptr to local memory *data*.
+ *
+ * *data* must be a ptr to a map value.
+ * The maximum *size* supported is DYNPTR_MAX_SIZE.
+ * *flags* is currently unused.
+ * Return
+ * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ * -EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ * through the dynptr interface. *flags* must be 0.
+ *
+ * Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ * reservation fails. This is enforced by the verifier.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Submit reserved ring buffer sample, pointed to by *data*,
+ * through the dynptr interface. This is a no-op if the dynptr is
+ * invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_submit'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Discard reserved ring buffer sample through the dynptr
+ * interface. This is a no-op if the dynptr is invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_discard'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags)
+ * Description
+ * Read *len* bytes from *src* into *dst*, starting from *offset*
+ * into *src*.
+ * *flags* is currently unused.
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
+ * *flags* is not 0.
+ *
+ * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
+ * Description
+ * Write *len* bytes from *src* into *dst*, starting from *offset*
+ * into *dst*.
+ *
+ * *flags* must be 0 except for skb-type dynptrs.
+ *
+ * For skb-type dynptrs:
+ * * All data slices of the dynptr are automatically
+ * invalidated after **bpf_dynptr_write**\ (). This is
+ * because writing may pull the skb and change the
+ * underlying packet buffer.
+ *
+ * * For *flags*, please see the flags accepted by
+ * **bpf_skb_store_bytes**\ ().
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
+ * is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs,
+ * other errors correspond to errors returned by **bpf_skb_store_bytes**\ ().
+ *
+ * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len)
+ * Description
+ * Get a pointer to the underlying dynptr data.
+ *
+ * *len* must be a statically known value. The returned data slice
+ * is invalidated whenever the dynptr is invalidated.
+ *
+ * skb and xdp type dynptrs may not use bpf_dynptr_data. They should
+ * instead use bpf_dynptr_slice and bpf_dynptr_slice_rdwr.
+ * Return
+ * Pointer to the underlying dynptr data, NULL if the dynptr is
+ * read-only, if the dynptr is invalid, or if the offset and length
+ * is out of bounds.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv4/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv6/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ * Description
+ * A nonsettable system-wide clock derived from wall-clock time but
+ * ignoring leap seconds. This clock does not experience
+ * discontinuities and backwards jumps caused by NTP inserting leap
+ * seconds as CLOCK_REALTIME does.
+ *
+ * See: **clock_gettime**\ (**CLOCK_TAI**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags)
+ * Description
+ * Drain samples from the specified user ring buffer, and invoke
+ * the provided callback for each such sample:
+ *
+ * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ * If **callback_fn** returns 0, the helper will continue to try
+ * and drain the next sample, up to a maximum of
+ * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ * the helper will skip the rest of the samples and return. Other
+ * return values are not used now, and will be rejected by the
+ * verifier.
+ * Return
+ * The number of drained samples if no error was encountered while
+ * draining samples, or 0 if no samples were present in the ring
+ * buffer. If a user-space producer was epoll-waiting on this map,
+ * and at least one sample was drained, they will receive an event
+ * notification notifying them of available space in the ring
+ * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ * function, no wakeup notification will be sent. If the
+ * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ * be sent even if no sample was drained.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EBUSY** if the ring buffer is contended, and another calling
+ * context was concurrently draining the ring buffer.
+ *
+ * **-EINVAL** if user-space is not properly tracking the ring
+ * buffer due to the producer position not being aligned to 8
+ * bytes, a sample not being aligned to 8 bytes, or the producer
+ * position not matching the advertised length of a sample.
+ *
+ * **-E2BIG** if user-space has tried to publish a sample which is
+ * larger than the size of the ring buffer, or which cannot fit
+ * within a struct bpf_dynptr.
+ *
+ * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from the *cgroup*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *cgroup* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this
+ * helper enforces the key must be a cgroup struct and the map must also
+ * be a **BPF_MAP_TYPE_CGRP_STORAGE**.
+ *
+ * In reality, the local-storage value is embedded directly inside of the
+ * *cgroup* object itself, rather than being located in the
+ * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is
+ * queried for some *map* on a *cgroup* object, the kernel will perform an
+ * O(n) iteration over all of the live local-storage values for that
+ * *cgroup* object until the local-storage value for the *map* is found.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup)
+ * Description
+ * Delete a bpf_local_storage from a *cgroup*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ */
+#define ___BPF_FUNC_MAPPER(FN, ctx...) \
+ FN(unspec, 0, ##ctx) \
+ FN(map_lookup_elem, 1, ##ctx) \
+ FN(map_update_elem, 2, ##ctx) \
+ FN(map_delete_elem, 3, ##ctx) \
+ FN(probe_read, 4, ##ctx) \
+ FN(ktime_get_ns, 5, ##ctx) \
+ FN(trace_printk, 6, ##ctx) \
+ FN(get_prandom_u32, 7, ##ctx) \
+ FN(get_smp_processor_id, 8, ##ctx) \
+ FN(skb_store_bytes, 9, ##ctx) \
+ FN(l3_csum_replace, 10, ##ctx) \
+ FN(l4_csum_replace, 11, ##ctx) \
+ FN(tail_call, 12, ##ctx) \
+ FN(clone_redirect, 13, ##ctx) \
+ FN(get_current_pid_tgid, 14, ##ctx) \
+ FN(get_current_uid_gid, 15, ##ctx) \
+ FN(get_current_comm, 16, ##ctx) \
+ FN(get_cgroup_classid, 17, ##ctx) \
+ FN(skb_vlan_push, 18, ##ctx) \
+ FN(skb_vlan_pop, 19, ##ctx) \
+ FN(skb_get_tunnel_key, 20, ##ctx) \
+ FN(skb_set_tunnel_key, 21, ##ctx) \
+ FN(perf_event_read, 22, ##ctx) \
+ FN(redirect, 23, ##ctx) \
+ FN(get_route_realm, 24, ##ctx) \
+ FN(perf_event_output, 25, ##ctx) \
+ FN(skb_load_bytes, 26, ##ctx) \
+ FN(get_stackid, 27, ##ctx) \
+ FN(csum_diff, 28, ##ctx) \
+ FN(skb_get_tunnel_opt, 29, ##ctx) \
+ FN(skb_set_tunnel_opt, 30, ##ctx) \
+ FN(skb_change_proto, 31, ##ctx) \
+ FN(skb_change_type, 32, ##ctx) \
+ FN(skb_under_cgroup, 33, ##ctx) \
+ FN(get_hash_recalc, 34, ##ctx) \
+ FN(get_current_task, 35, ##ctx) \
+ FN(probe_write_user, 36, ##ctx) \
+ FN(current_task_under_cgroup, 37, ##ctx) \
+ FN(skb_change_tail, 38, ##ctx) \
+ FN(skb_pull_data, 39, ##ctx) \
+ FN(csum_update, 40, ##ctx) \
+ FN(set_hash_invalid, 41, ##ctx) \
+ FN(get_numa_node_id, 42, ##ctx) \
+ FN(skb_change_head, 43, ##ctx) \
+ FN(xdp_adjust_head, 44, ##ctx) \
+ FN(probe_read_str, 45, ##ctx) \
+ FN(get_socket_cookie, 46, ##ctx) \
+ FN(get_socket_uid, 47, ##ctx) \
+ FN(set_hash, 48, ##ctx) \
+ FN(setsockopt, 49, ##ctx) \
+ FN(skb_adjust_room, 50, ##ctx) \
+ FN(redirect_map, 51, ##ctx) \
+ FN(sk_redirect_map, 52, ##ctx) \
+ FN(sock_map_update, 53, ##ctx) \
+ FN(xdp_adjust_meta, 54, ##ctx) \
+ FN(perf_event_read_value, 55, ##ctx) \
+ FN(perf_prog_read_value, 56, ##ctx) \
+ FN(getsockopt, 57, ##ctx) \
+ FN(override_return, 58, ##ctx) \
+ FN(sock_ops_cb_flags_set, 59, ##ctx) \
+ FN(msg_redirect_map, 60, ##ctx) \
+ FN(msg_apply_bytes, 61, ##ctx) \
+ FN(msg_cork_bytes, 62, ##ctx) \
+ FN(msg_pull_data, 63, ##ctx) \
+ FN(bind, 64, ##ctx) \
+ FN(xdp_adjust_tail, 65, ##ctx) \
+ FN(skb_get_xfrm_state, 66, ##ctx) \
+ FN(get_stack, 67, ##ctx) \
+ FN(skb_load_bytes_relative, 68, ##ctx) \
+ FN(fib_lookup, 69, ##ctx) \
+ FN(sock_hash_update, 70, ##ctx) \
+ FN(msg_redirect_hash, 71, ##ctx) \
+ FN(sk_redirect_hash, 72, ##ctx) \
+ FN(lwt_push_encap, 73, ##ctx) \
+ FN(lwt_seg6_store_bytes, 74, ##ctx) \
+ FN(lwt_seg6_adjust_srh, 75, ##ctx) \
+ FN(lwt_seg6_action, 76, ##ctx) \
+ FN(rc_repeat, 77, ##ctx) \
+ FN(rc_keydown, 78, ##ctx) \
+ FN(skb_cgroup_id, 79, ##ctx) \
+ FN(get_current_cgroup_id, 80, ##ctx) \
+ FN(get_local_storage, 81, ##ctx) \
+ FN(sk_select_reuseport, 82, ##ctx) \
+ FN(skb_ancestor_cgroup_id, 83, ##ctx) \
+ FN(sk_lookup_tcp, 84, ##ctx) \
+ FN(sk_lookup_udp, 85, ##ctx) \
+ FN(sk_release, 86, ##ctx) \
+ FN(map_push_elem, 87, ##ctx) \
+ FN(map_pop_elem, 88, ##ctx) \
+ FN(map_peek_elem, 89, ##ctx) \
+ FN(msg_push_data, 90, ##ctx) \
+ FN(msg_pop_data, 91, ##ctx) \
+ FN(rc_pointer_rel, 92, ##ctx) \
+ FN(spin_lock, 93, ##ctx) \
+ FN(spin_unlock, 94, ##ctx) \
+ FN(sk_fullsock, 95, ##ctx) \
+ FN(tcp_sock, 96, ##ctx) \
+ FN(skb_ecn_set_ce, 97, ##ctx) \
+ FN(get_listener_sock, 98, ##ctx) \
+ FN(skc_lookup_tcp, 99, ##ctx) \
+ FN(tcp_check_syncookie, 100, ##ctx) \
+ FN(sysctl_get_name, 101, ##ctx) \
+ FN(sysctl_get_current_value, 102, ##ctx) \
+ FN(sysctl_get_new_value, 103, ##ctx) \
+ FN(sysctl_set_new_value, 104, ##ctx) \
+ FN(strtol, 105, ##ctx) \
+ FN(strtoul, 106, ##ctx) \
+ FN(sk_storage_get, 107, ##ctx) \
+ FN(sk_storage_delete, 108, ##ctx) \
+ FN(send_signal, 109, ##ctx) \
+ FN(tcp_gen_syncookie, 110, ##ctx) \
+ FN(skb_output, 111, ##ctx) \
+ FN(probe_read_user, 112, ##ctx) \
+ FN(probe_read_kernel, 113, ##ctx) \
+ FN(probe_read_user_str, 114, ##ctx) \
+ FN(probe_read_kernel_str, 115, ##ctx) \
+ FN(tcp_send_ack, 116, ##ctx) \
+ FN(send_signal_thread, 117, ##ctx) \
+ FN(jiffies64, 118, ##ctx) \
+ FN(read_branch_records, 119, ##ctx) \
+ FN(get_ns_current_pid_tgid, 120, ##ctx) \
+ FN(xdp_output, 121, ##ctx) \
+ FN(get_netns_cookie, 122, ##ctx) \
+ FN(get_current_ancestor_cgroup_id, 123, ##ctx) \
+ FN(sk_assign, 124, ##ctx) \
+ FN(ktime_get_boot_ns, 125, ##ctx) \
+ FN(seq_printf, 126, ##ctx) \
+ FN(seq_write, 127, ##ctx) \
+ FN(sk_cgroup_id, 128, ##ctx) \
+ FN(sk_ancestor_cgroup_id, 129, ##ctx) \
+ FN(ringbuf_output, 130, ##ctx) \
+ FN(ringbuf_reserve, 131, ##ctx) \
+ FN(ringbuf_submit, 132, ##ctx) \
+ FN(ringbuf_discard, 133, ##ctx) \
+ FN(ringbuf_query, 134, ##ctx) \
+ FN(csum_level, 135, ##ctx) \
+ FN(skc_to_tcp6_sock, 136, ##ctx) \
+ FN(skc_to_tcp_sock, 137, ##ctx) \
+ FN(skc_to_tcp_timewait_sock, 138, ##ctx) \
+ FN(skc_to_tcp_request_sock, 139, ##ctx) \
+ FN(skc_to_udp6_sock, 140, ##ctx) \
+ FN(get_task_stack, 141, ##ctx) \
+ FN(load_hdr_opt, 142, ##ctx) \
+ FN(store_hdr_opt, 143, ##ctx) \
+ FN(reserve_hdr_opt, 144, ##ctx) \
+ FN(inode_storage_get, 145, ##ctx) \
+ FN(inode_storage_delete, 146, ##ctx) \
+ FN(d_path, 147, ##ctx) \
+ FN(copy_from_user, 148, ##ctx) \
+ FN(snprintf_btf, 149, ##ctx) \
+ FN(seq_printf_btf, 150, ##ctx) \
+ FN(skb_cgroup_classid, 151, ##ctx) \
+ FN(redirect_neigh, 152, ##ctx) \
+ FN(per_cpu_ptr, 153, ##ctx) \
+ FN(this_cpu_ptr, 154, ##ctx) \
+ FN(redirect_peer, 155, ##ctx) \
+ FN(task_storage_get, 156, ##ctx) \
+ FN(task_storage_delete, 157, ##ctx) \
+ FN(get_current_task_btf, 158, ##ctx) \
+ FN(bprm_opts_set, 159, ##ctx) \
+ FN(ktime_get_coarse_ns, 160, ##ctx) \
+ FN(ima_inode_hash, 161, ##ctx) \
+ FN(sock_from_file, 162, ##ctx) \
+ FN(check_mtu, 163, ##ctx) \
+ FN(for_each_map_elem, 164, ##ctx) \
+ FN(snprintf, 165, ##ctx) \
+ FN(sys_bpf, 166, ##ctx) \
+ FN(btf_find_by_name_kind, 167, ##ctx) \
+ FN(sys_close, 168, ##ctx) \
+ FN(timer_init, 169, ##ctx) \
+ FN(timer_set_callback, 170, ##ctx) \
+ FN(timer_start, 171, ##ctx) \
+ FN(timer_cancel, 172, ##ctx) \
+ FN(get_func_ip, 173, ##ctx) \
+ FN(get_attach_cookie, 174, ##ctx) \
+ FN(task_pt_regs, 175, ##ctx) \
+ FN(get_branch_snapshot, 176, ##ctx) \
+ FN(trace_vprintk, 177, ##ctx) \
+ FN(skc_to_unix_sock, 178, ##ctx) \
+ FN(kallsyms_lookup_name, 179, ##ctx) \
+ FN(find_vma, 180, ##ctx) \
+ FN(loop, 181, ##ctx) \
+ FN(strncmp, 182, ##ctx) \
+ FN(get_func_arg, 183, ##ctx) \
+ FN(get_func_ret, 184, ##ctx) \
+ FN(get_func_arg_cnt, 185, ##ctx) \
+ FN(get_retval, 186, ##ctx) \
+ FN(set_retval, 187, ##ctx) \
+ FN(xdp_get_buff_len, 188, ##ctx) \
+ FN(xdp_load_bytes, 189, ##ctx) \
+ FN(xdp_store_bytes, 190, ##ctx) \
+ FN(copy_from_user_task, 191, ##ctx) \
+ FN(skb_set_tstamp, 192, ##ctx) \
+ FN(ima_file_hash, 193, ##ctx) \
+ FN(kptr_xchg, 194, ##ctx) \
+ FN(map_lookup_percpu_elem, 195, ##ctx) \
+ FN(skc_to_mptcp_sock, 196, ##ctx) \
+ FN(dynptr_from_mem, 197, ##ctx) \
+ FN(ringbuf_reserve_dynptr, 198, ##ctx) \
+ FN(ringbuf_submit_dynptr, 199, ##ctx) \
+ FN(ringbuf_discard_dynptr, 200, ##ctx) \
+ FN(dynptr_read, 201, ##ctx) \
+ FN(dynptr_write, 202, ##ctx) \
+ FN(dynptr_data, 203, ##ctx) \
+ FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \
+ FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \
+ FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \
+ FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \
+ FN(ktime_get_tai_ns, 208, ##ctx) \
+ FN(user_ringbuf_drain, 209, ##ctx) \
+ FN(cgrp_storage_get, 210, ##ctx) \
+ FN(cgrp_storage_delete, 211, ##ctx) \
+ /* */
+
+/* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't
+ * know or care about integer value that is now passed as second argument
+ */
+#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name),
+#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN)
+
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y,
+enum bpf_func_id {
+ ___BPF_FUNC_MAPPER(__BPF_ENUM_FN)
+ __BPF_FUNC_MAX_ID,
+};
+#undef __BPF_ENUM_FN
+
+/* All flags used by eBPF helper functions, placed here. */
+
+/* BPF_FUNC_skb_store_bytes flags. */
+enum {
+ BPF_F_RECOMPUTE_CSUM = (1ULL << 0),
+ BPF_F_INVALIDATE_HASH = (1ULL << 1),
+};
+
+/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
+ * First 4 bits are for passing the header field size.
+ */
+enum {
+ BPF_F_HDR_FIELD_MASK = 0xfULL,
+};
+
+/* BPF_FUNC_l4_csum_replace flags. */
+enum {
+ BPF_F_PSEUDO_HDR = (1ULL << 4),
+ BPF_F_MARK_MANGLED_0 = (1ULL << 5),
+ BPF_F_MARK_ENFORCE = (1ULL << 6),
+};
+
+/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
+enum {
+ BPF_F_INGRESS = (1ULL << 0),
+};
+
+/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+ BPF_F_TUNINFO_IPV6 = (1ULL << 0),
+};
+
+/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
+enum {
+ BPF_F_SKIP_FIELD_MASK = 0xffULL,
+ BPF_F_USER_STACK = (1ULL << 8),
+/* flags used by BPF_FUNC_get_stackid only. */
+ BPF_F_FAST_STACK_CMP = (1ULL << 9),
+ BPF_F_REUSE_STACKID = (1ULL << 10),
+/* flags used by BPF_FUNC_get_stack only. */
+ BPF_F_USER_BUILD_ID = (1ULL << 11),
+};
+
+/* BPF_FUNC_skb_set_tunnel_key flags. */
+enum {
+ BPF_F_ZERO_CSUM_TX = (1ULL << 1),
+ BPF_F_DONT_FRAGMENT = (1ULL << 2),
+ BPF_F_SEQ_NUMBER = (1ULL << 3),
+ BPF_F_NO_TUNNEL_KEY = (1ULL << 4),
+};
+
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+ BPF_F_TUNINFO_FLAGS = (1ULL << 4),
+};
+
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
+enum {
+ BPF_F_INDEX_MASK = 0xffffffffULL,
+ BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK,
+/* BPF_FUNC_perf_event_output for sk_buff input context. */
+ BPF_F_CTXLEN_MASK = (0xfffffULL << 32),
+};
+
+/* Current network namespace */
+enum {
+ BPF_F_CURRENT_NETNS = (-1L),
+};
+
+/* BPF_FUNC_csum_level level values. */
+enum {
+ BPF_CSUM_LEVEL_QUERY,
+ BPF_CSUM_LEVEL_INC,
+ BPF_CSUM_LEVEL_DEC,
+ BPF_CSUM_LEVEL_RESET,
+};
+
+/* BPF_FUNC_skb_adjust_room flags. */
+enum {
+ BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0),
+ BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 = (1ULL << 1),
+ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2),
+ BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3),
+ BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4),
+ BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5),
+ BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6),
+ BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7),
+ BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8),
+};
+
+enum {
+ BPF_ADJ_ROOM_ENCAP_L2_MASK = 0xff,
+ BPF_ADJ_ROOM_ENCAP_L2_SHIFT = 56,
+};
+
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \
+ BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
+
+/* BPF_FUNC_sysctl_get_name flags. */
+enum {
+ BPF_F_SYSCTL_BASE_NAME = (1ULL << 0),
+};
+
+/* BPF_FUNC_<kernel_obj>_storage_get flags */
+enum {
+ BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0),
+ /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility
+ * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead.
+ */
+ BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE,
+};
+
+/* BPF_FUNC_read_branch_records flags. */
+enum {
+ BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0),
+};
+
+/* BPF_FUNC_bpf_ringbuf_commit, BPF_FUNC_bpf_ringbuf_discard, and
+ * BPF_FUNC_bpf_ringbuf_output flags.
+ */
+enum {
+ BPF_RB_NO_WAKEUP = (1ULL << 0),
+ BPF_RB_FORCE_WAKEUP = (1ULL << 1),
+};
+
+/* BPF_FUNC_bpf_ringbuf_query flags */
+enum {
+ BPF_RB_AVAIL_DATA = 0,
+ BPF_RB_RING_SIZE = 1,
+ BPF_RB_CONS_POS = 2,
+ BPF_RB_PROD_POS = 3,
+};
+
+/* BPF ring buffer constants */
+enum {
+ BPF_RINGBUF_BUSY_BIT = (1U << 31),
+ BPF_RINGBUF_DISCARD_BIT = (1U << 30),
+ BPF_RINGBUF_HDR_SZ = 8,
+};
+
+/* BPF_FUNC_sk_assign flags in bpf_sk_lookup context. */
+enum {
+ BPF_SK_LOOKUP_F_REPLACE = (1ULL << 0),
+ BPF_SK_LOOKUP_F_NO_REUSEPORT = (1ULL << 1),
+};
+
+/* Mode for BPF_FUNC_skb_adjust_room helper. */
+enum bpf_adj_room_mode {
+ BPF_ADJ_ROOM_NET,
+ BPF_ADJ_ROOM_MAC,
+};
+
+/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
+enum bpf_hdr_start_off {
+ BPF_HDR_START_MAC,
+ BPF_HDR_START_NET,
+};
+
+/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */
+enum bpf_lwt_encap_mode {
+ BPF_LWT_ENCAP_SEG6,
+ BPF_LWT_ENCAP_SEG6_INLINE,
+ BPF_LWT_ENCAP_IP,
+};
+
+/* Flags for bpf_bprm_opts_set helper */
+enum {
+ BPF_F_BPRM_SECUREEXEC = (1ULL << 0),
+};
+
+/* Flags for bpf_redirect_map helper */
+enum {
+ BPF_F_BROADCAST = (1ULL << 3),
+ BPF_F_EXCLUDE_INGRESS = (1ULL << 4),
+};
+
+#define __bpf_md_ptr(type, name) \
+union { \
+ type name; \
+ __u64 :64; \
+} __attribute__((aligned(8)))
+
+enum {
+ BPF_SKB_TSTAMP_UNSPEC,
+ BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */
+ /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle,
+ * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC
+ * and try to deduce it by ingress, egress or skb->sk->sk_clockid.
+ */
+};
+
+/* user accessible mirror of in-kernel sk_buff.
+ * new fields can only be added to the end of this structure
+ */
+struct __sk_buff {
+ __u32 len;
+ __u32 pkt_type;
+ __u32 mark;
+ __u32 queue_mapping;
+ __u32 protocol;
+ __u32 vlan_present;
+ __u32 vlan_tci;
+ __u32 vlan_proto;
+ __u32 priority;
+ __u32 ingress_ifindex;
+ __u32 ifindex;
+ __u32 tc_index;
+ __u32 cb[5];
+ __u32 hash;
+ __u32 tc_classid;
+ __u32 data;
+ __u32 data_end;
+ __u32 napi_id;
+
+ /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
+ __u32 family;
+ __u32 remote_ip4; /* Stored in network byte order */
+ __u32 local_ip4; /* Stored in network byte order */
+ __u32 remote_ip6[4]; /* Stored in network byte order */
+ __u32 local_ip6[4]; /* Stored in network byte order */
+ __u32 remote_port; /* Stored in network byte order */
+ __u32 local_port; /* stored in host byte order */
+ /* ... here. */
+
+ __u32 data_meta;
+ __bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
+ __u64 tstamp;
+ __u32 wire_len;
+ __u32 gso_segs;
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __u32 gso_size;
+ __u8 tstamp_type;
+ __u32 :24; /* Padding, future use. */
+ __u64 hwtstamp;
+};
+
+struct bpf_tunnel_key {
+ __u32 tunnel_id;
+ union {
+ __u32 remote_ipv4;
+ __u32 remote_ipv6[4];
+ };
+ __u8 tunnel_tos;
+ __u8 tunnel_ttl;
+ union {
+ __u16 tunnel_ext; /* compat */
+ __be16 tunnel_flags;
+ };
+ __u32 tunnel_label;
+ union {
+ __u32 local_ipv4;
+ __u32 local_ipv6[4];
+ };
+};
+
+/* user accessible mirror of in-kernel xfrm_state.
+ * new fields can only be added to the end of this structure
+ */
+struct bpf_xfrm_state {
+ __u32 reqid;
+ __u32 spi; /* Stored in network byte order */
+ __u16 family;
+ __u16 ext; /* Padding, future use. */
+ union {
+ __u32 remote_ipv4; /* Stored in network byte order */
+ __u32 remote_ipv6[4]; /* Stored in network byte order */
+ };
+};
+
+/* Generic BPF return codes which all BPF program types may support.
+ * The values are binary compatible with their TC_ACT_* counter-part to
+ * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
+ * programs.
+ *
+ * XDP is handled seprately, see XDP_*.
+ */
+enum bpf_ret_code {
+ BPF_OK = 0,
+ /* 1 reserved */
+ BPF_DROP = 2,
+ /* 3-6 reserved */
+ BPF_REDIRECT = 7,
+ /* >127 are reserved for prog type specific return codes.
+ *
+ * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and
+ * BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been
+ * changed and should be routed based on its new L3 header.
+ * (This is an L3 redirect, as opposed to L2 redirect
+ * represented by BPF_REDIRECT above).
+ */
+ BPF_LWT_REROUTE = 128,
+ /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+ * to indicate that no custom dissection was performed, and
+ * fallback to standard dissector is requested.
+ */
+ BPF_FLOW_DISSECTOR_CONTINUE = 129,
+};
+
+struct bpf_sock {
+ __u32 bound_dev_if;
+ __u32 family;
+ __u32 type;
+ __u32 protocol;
+ __u32 mark;
+ __u32 priority;
+ /* IP address also allows 1 and 2 bytes access */
+ __u32 src_ip4;
+ __u32 src_ip6[4];
+ __u32 src_port; /* host byte order */
+ __be16 dst_port; /* network byte order */
+ __u16 :16; /* zero padding */
+ __u32 dst_ip4;
+ __u32 dst_ip6[4];
+ __u32 state;
+ __s32 rx_queue_mapping;
+};
+
+struct bpf_tcp_sock {
+ __u32 snd_cwnd; /* Sending congestion window */
+ __u32 srtt_us; /* smoothed round trip time << 3 in usecs */
+ __u32 rtt_min;
+ __u32 snd_ssthresh; /* Slow start size threshold */
+ __u32 rcv_nxt; /* What we want to receive next */
+ __u32 snd_nxt; /* Next sequence we send */
+ __u32 snd_una; /* First byte we want an ack for */
+ __u32 mss_cache; /* Cached effective mss, not including SACKS */
+ __u32 ecn_flags; /* ECN status bits. */
+ __u32 rate_delivered; /* saved rate sample: packets delivered */
+ __u32 rate_interval_us; /* saved rate sample: time elapsed */
+ __u32 packets_out; /* Packets which are "in flight" */
+ __u32 retrans_out; /* Retransmitted packets out */
+ __u32 total_retrans; /* Total retransmits for entire connection */
+ __u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn
+ * total number of segments in.
+ */
+ __u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn
+ * total number of data segments in.
+ */
+ __u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut
+ * The total number of segments sent.
+ */
+ __u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut
+ * total number of data segments sent.
+ */
+ __u32 lost_out; /* Lost packets */
+ __u32 sacked_out; /* SACK'd packets */
+ __u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived
+ * sum(delta(rcv_nxt)), or how many bytes
+ * were acked.
+ */
+ __u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
+ * sum(delta(snd_una)), or how many bytes
+ * were acked.
+ */
+ __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups
+ * total number of DSACK blocks received
+ */
+ __u32 delivered; /* Total data packets delivered incl. rexmits */
+ __u32 delivered_ce; /* Like the above but only ECE marked packets */
+ __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */
+};
+
+struct bpf_sock_tuple {
+ union {
+ struct {
+ __be32 saddr;
+ __be32 daddr;
+ __be16 sport;
+ __be16 dport;
+ } ipv4;
+ struct {
+ __be32 saddr[4];
+ __be32 daddr[4];
+ __be16 sport;
+ __be16 dport;
+ } ipv6;
+ };
+};
+
+/* (Simplified) user return codes for tcx prog type.
+ * A valid tcx program must return one of these defined values. All other
+ * return codes are reserved for future use. Must remain compatible with
+ * their TC_ACT_* counter-parts. For compatibility in behavior, unknown
+ * return codes are mapped to TCX_NEXT.
+ */
+enum tcx_action_base {
+ TCX_NEXT = -1,
+ TCX_PASS = 0,
+ TCX_DROP = 2,
+ TCX_REDIRECT = 7,
+};
+
+struct bpf_xdp_sock {
+ __u32 queue_id;
+};
+
+#define XDP_PACKET_HEADROOM 256
+
+/* User return codes for XDP prog type.
+ * A valid XDP program must return one of these defined values. All other
+ * return codes are reserved for future use. Unknown return codes will
+ * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
+ */
+enum xdp_action {
+ XDP_ABORTED = 0,
+ XDP_DROP,
+ XDP_PASS,
+ XDP_TX,
+ XDP_REDIRECT,
+};
+
+/* user accessible metadata for XDP packet hook
+ * new fields must be added to the end of this structure
+ */
+struct xdp_md {
+ __u32 data;
+ __u32 data_end;
+ __u32 data_meta;
+ /* Below access go through struct xdp_rxq_info */
+ __u32 ingress_ifindex; /* rxq->dev->ifindex */
+ __u32 rx_queue_index; /* rxq->queue_index */
+
+ __u32 egress_ifindex; /* txq->dev->ifindex */
+};
+
+/* DEVMAP map-value layout
+ *
+ * The struct data-layout of map-value is a configuration interface.
+ * New members can only be added to the end of this structure.
+ */
+struct bpf_devmap_val {
+ __u32 ifindex; /* device index */
+ union {
+ int fd; /* prog fd on map write */
+ __u32 id; /* prog id on map read */
+ } bpf_prog;
+};
+
+/* CPUMAP map-value layout
+ *
+ * The struct data-layout of map-value is a configuration interface.
+ * New members can only be added to the end of this structure.
+ */
+struct bpf_cpumap_val {
+ __u32 qsize; /* queue size to remote target CPU */
+ union {
+ int fd; /* prog fd on map write */
+ __u32 id; /* prog id on map read */
+ } bpf_prog;
+};
+
+enum sk_action {
+ SK_DROP = 0,
+ SK_PASS,
+};
+
+/* user accessible metadata for SK_MSG packet hook, new fields must
+ * be added to the end of this structure
+ */
+struct sk_msg_md {
+ __bpf_md_ptr(void *, data);
+ __bpf_md_ptr(void *, data_end);
+
+ __u32 family;
+ __u32 remote_ip4; /* Stored in network byte order */
+ __u32 local_ip4; /* Stored in network byte order */
+ __u32 remote_ip6[4]; /* Stored in network byte order */
+ __u32 local_ip6[4]; /* Stored in network byte order */
+ __u32 remote_port; /* Stored in network byte order */
+ __u32 local_port; /* stored in host byte order */
+ __u32 size; /* Total size of sk_msg */
+
+ __bpf_md_ptr(struct bpf_sock *, sk); /* current socket */
+};
+
+struct sk_reuseport_md {
+ /*
+ * Start of directly accessible data. It begins from
+ * the tcp/udp header.
+ */
+ __bpf_md_ptr(void *, data);
+ /* End of directly accessible data */
+ __bpf_md_ptr(void *, data_end);
+ /*
+ * Total length of packet (starting from the tcp/udp header).
+ * Note that the directly accessible bytes (data_end - data)
+ * could be less than this "len". Those bytes could be
+ * indirectly read by a helper "bpf_skb_load_bytes()".
+ */
+ __u32 len;
+ /*
+ * Eth protocol in the mac header (network byte order). e.g.
+ * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD)
+ */
+ __u32 eth_protocol;
+ __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
+ __u32 bind_inany; /* Is sock bound to an INANY address? */
+ __u32 hash; /* A hash of the packet 4 tuples */
+ /* When reuse->migrating_sk is NULL, it is selecting a sk for the
+ * new incoming connection request (e.g. selecting a listen sk for
+ * the received SYN in the TCP case). reuse->sk is one of the sk
+ * in the reuseport group. The bpf prog can use reuse->sk to learn
+ * the local listening ip/port without looking into the skb.
+ *
+ * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+ * reuse->migrating_sk is the socket that needs to be migrated
+ * to another listening socket. migrating_sk could be a fullsock
+ * sk that is fully established or a reqsk that is in-the-middle
+ * of 3-way handshake.
+ */
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(struct bpf_sock *, migrating_sk);
+};
+
+#define BPF_TAG_SIZE 8
+
+struct bpf_prog_info {
+ __u32 type;
+ __u32 id;
+ __u8 tag[BPF_TAG_SIZE];
+ __u32 jited_prog_len;
+ __u32 xlated_prog_len;
+ __aligned_u64 jited_prog_insns;
+ __aligned_u64 xlated_prog_insns;
+ __u64 load_time; /* ns since boottime */
+ __u32 created_by_uid;
+ __u32 nr_map_ids;
+ __aligned_u64 map_ids;
+ char name[BPF_OBJ_NAME_LEN];
+ __u32 ifindex;
+ __u32 gpl_compatible:1;
+ __u32 :31; /* alignment pad */
+ __u64 netns_dev;
+ __u64 netns_ino;
+ __u32 nr_jited_ksyms;
+ __u32 nr_jited_func_lens;
+ __aligned_u64 jited_ksyms;
+ __aligned_u64 jited_func_lens;
+ __u32 btf_id;
+ __u32 func_info_rec_size;
+ __aligned_u64 func_info;
+ __u32 nr_func_info;
+ __u32 nr_line_info;
+ __aligned_u64 line_info;
+ __aligned_u64 jited_line_info;
+ __u32 nr_jited_line_info;
+ __u32 line_info_rec_size;
+ __u32 jited_line_info_rec_size;
+ __u32 nr_prog_tags;
+ __aligned_u64 prog_tags;
+ __u64 run_time_ns;
+ __u64 run_cnt;
+ __u64 recursion_misses;
+ __u32 verified_insns;
+ __u32 attach_btf_obj_id;
+ __u32 attach_btf_id;
+} __attribute__((aligned(8)));
+
+struct bpf_map_info {
+ __u32 type;
+ __u32 id;
+ __u32 key_size;
+ __u32 value_size;
+ __u32 max_entries;
+ __u32 map_flags;
+ char name[BPF_OBJ_NAME_LEN];
+ __u32 ifindex;
+ __u32 btf_vmlinux_value_type_id;
+ __u64 netns_dev;
+ __u64 netns_ino;
+ __u32 btf_id;
+ __u32 btf_key_type_id;
+ __u32 btf_value_type_id;
+ __u32 :32; /* alignment pad */
+ __u64 map_extra;
+} __attribute__((aligned(8)));
+
+struct bpf_btf_info {
+ __aligned_u64 btf;
+ __u32 btf_size;
+ __u32 id;
+ __aligned_u64 name;
+ __u32 name_len;
+ __u32 kernel_btf;
+} __attribute__((aligned(8)));
+
+struct bpf_link_info {
+ __u32 type;
+ __u32 id;
+ __u32 prog_id;
+ union {
+ struct {
+ __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
+ __u32 tp_name_len; /* in/out: tp_name buffer len */
+ } raw_tracepoint;
+ struct {
+ __u32 attach_type;
+ __u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */
+ __u32 target_btf_id; /* BTF type id inside the object */
+ } tracing;
+ struct {
+ __u64 cgroup_id;
+ __u32 attach_type;
+ } cgroup;
+ struct {
+ __aligned_u64 target_name; /* in/out: target_name buffer ptr */
+ __u32 target_name_len; /* in/out: target_name buffer len */
+
+ /* If the iter specific field is 32 bits, it can be put
+ * in the first or second union. Otherwise it should be
+ * put in the second union.
+ */
+ union {
+ struct {
+ __u32 map_id;
+ } map;
+ };
+ union {
+ struct {
+ __u64 cgroup_id;
+ __u32 order;
+ } cgroup;
+ struct {
+ __u32 tid;
+ __u32 pid;
+ } task;
+ };
+ } iter;
+ struct {
+ __u32 netns_ino;
+ __u32 attach_type;
+ } netns;
+ struct {
+ __u32 ifindex;
+ } xdp;
+ struct {
+ __u32 map_id;
+ } struct_ops;
+ struct {
+ __u32 pf;
+ __u32 hooknum;
+ __s32 priority;
+ __u32 flags;
+ } netfilter;
+ struct {
+ __aligned_u64 addrs;
+ __u32 count; /* in/out: kprobe_multi function count */
+ __u32 flags;
+ __u64 missed;
+ } kprobe_multi;
+ struct {
+ __aligned_u64 path;
+ __aligned_u64 offsets;
+ __aligned_u64 ref_ctr_offsets;
+ __aligned_u64 cookies;
+ __u32 path_size; /* in/out: real path size on success, including zero byte */
+ __u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
+ __u32 flags;
+ __u32 pid;
+ } uprobe_multi;
+ struct {
+ __u32 type; /* enum bpf_perf_event_type */
+ __u32 :32;
+ union {
+ struct {
+ __aligned_u64 file_name; /* in/out */
+ __u32 name_len;
+ __u32 offset; /* offset from file_name */
+ } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */
+ struct {
+ __aligned_u64 func_name; /* in/out */
+ __u32 name_len;
+ __u32 offset; /* offset from func_name */
+ __u64 addr;
+ __u64 missed;
+ } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
+ struct {
+ __aligned_u64 tp_name; /* in/out */
+ __u32 name_len;
+ } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */
+ struct {
+ __u64 config;
+ __u32 type;
+ } event; /* BPF_PERF_EVENT_EVENT */
+ };
+ } perf_event;
+ struct {
+ __u32 ifindex;
+ __u32 attach_type;
+ } tcx;
+ struct {
+ __u32 ifindex;
+ __u32 attach_type;
+ } netkit;
+ };
+} __attribute__((aligned(8)));
+
+/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
+ * by user and intended to be used by socket (e.g. to bind to, depends on
+ * attach type).
+ */
+struct bpf_sock_addr {
+ __u32 user_family; /* Allows 4-byte read, but no write. */
+ __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_port; /* Allows 1,2,4-byte read and 4-byte write.
+ * Stored in network byte order
+ */
+ __u32 family; /* Allows 4-byte read, but no write */
+ __u32 type; /* Allows 4-byte read, but no write */
+ __u32 protocol; /* Allows 4-byte read, but no write */
+ __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write.
+ * Stored in network byte order.
+ */
+ __bpf_md_ptr(struct bpf_sock *, sk);
+};
+
+/* User bpf_sock_ops struct to access socket values and specify request ops
+ * and their replies.
+ * Some of this fields are in network (bigendian) byte order and may need
+ * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h).
+ * New fields can only be added at the end of this structure
+ */
+struct bpf_sock_ops {
+ __u32 op;
+ union {
+ __u32 args[4]; /* Optionally passed to bpf program */
+ __u32 reply; /* Returned by bpf program */
+ __u32 replylong[4]; /* Optionally returned by bpf prog */
+ };
+ __u32 family;
+ __u32 remote_ip4; /* Stored in network byte order */
+ __u32 local_ip4; /* Stored in network byte order */
+ __u32 remote_ip6[4]; /* Stored in network byte order */
+ __u32 local_ip6[4]; /* Stored in network byte order */
+ __u32 remote_port; /* Stored in network byte order */
+ __u32 local_port; /* stored in host byte order */
+ __u32 is_fullsock; /* Some TCP fields are only valid if
+ * there is a full socket. If not, the
+ * fields read as zero.
+ */
+ __u32 snd_cwnd;
+ __u32 srtt_us; /* Averaged RTT << 3 in usecs */
+ __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */
+ __u32 state;
+ __u32 rtt_min;
+ __u32 snd_ssthresh;
+ __u32 rcv_nxt;
+ __u32 snd_nxt;
+ __u32 snd_una;
+ __u32 mss_cache;
+ __u32 ecn_flags;
+ __u32 rate_delivered;
+ __u32 rate_interval_us;
+ __u32 packets_out;
+ __u32 retrans_out;
+ __u32 total_retrans;
+ __u32 segs_in;
+ __u32 data_segs_in;
+ __u32 segs_out;
+ __u32 data_segs_out;
+ __u32 lost_out;
+ __u32 sacked_out;
+ __u32 sk_txhash;
+ __u64 bytes_received;
+ __u64 bytes_acked;
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ /* [skb_data, skb_data_end) covers the whole TCP header.
+ *
+ * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received
+ * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the
+ * header has not been written.
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have
+ * been written so far.
+ * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes
+ * the 3WHS.
+ * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes
+ * the 3WHS.
+ *
+ * bpf_load_hdr_opt() can also be used to read a particular option.
+ */
+ __bpf_md_ptr(void *, skb_data);
+ __bpf_md_ptr(void *, skb_data_end);
+ __u32 skb_len; /* The total length of a packet.
+ * It includes the header, options,
+ * and payload.
+ */
+ __u32 skb_tcp_flags; /* tcp_flags of the header. It provides
+ * an easy way to check for tcp_flags
+ * without parsing skb_data.
+ *
+ * In particular, the skb_tcp_flags
+ * will still be available in
+ * BPF_SOCK_OPS_HDR_OPT_LEN even though
+ * the outgoing header has not
+ * been written yet.
+ */
+ __u64 skb_hwtstamp;
+};
+
+/* Definitions for bpf_sock_ops_cb_flags */
+enum {
+ BPF_SOCK_OPS_RTO_CB_FLAG = (1<<0),
+ BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1),
+ BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2),
+ BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3),
+ /* Call bpf for all received TCP headers. The bpf prog will be
+ * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ *
+ * It could be used at the client/active side (i.e. connect() side)
+ * when the server told it that the server was in syncookie
+ * mode and required the active side to resend the bpf-written
+ * options. The active side can keep writing the bpf-options until
+ * it received a valid packet from the server side to confirm
+ * the earlier packet (and options) has been received. The later
+ * example patch is using it like this at the active side when the
+ * server is in syncookie mode.
+ *
+ * The bpf prog will usually turn this off in the common cases.
+ */
+ BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4),
+ /* Call bpf when kernel has received a header option that
+ * the kernel cannot handle. The bpf prog will be called under
+ * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ */
+ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
+ /* Call bpf when the kernel is writing header options for the
+ * outgoing packet. The bpf prog will first be called
+ * to reserve space in a skb under
+ * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then
+ * the bpf prog will be called to write the header option(s)
+ * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB
+ * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option
+ * related helpers that will be useful to the bpf programs.
+ *
+ * The kernel gets its chance to reserve space and write
+ * options first before the BPF program does.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
+/* Mask of all currently supported cb flags */
+ BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F,
+};
+
+/* List of known BPF sock_ops operators.
+ * New entries can only be added at the end
+ */
+enum {
+ BPF_SOCK_OPS_VOID,
+ BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or
+ * -1 if default value should be used
+ */
+ BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized
+ * window (in packets) or -1 if default
+ * value should be used
+ */
+ BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an
+ * active connection is initialized
+ */
+ BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an
+ * active connection is
+ * established
+ */
+ BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a
+ * passive connection is
+ * established
+ */
+ BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control
+ * needs ECN
+ */
+ BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is
+ * based on the path and may be
+ * dependent on the congestion control
+ * algorithm. In general it indicates
+ * a congestion threshold. RTTs above
+ * this indicate congestion
+ */
+ BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered.
+ * Arg1: value of icsk_retransmits
+ * Arg2: value of icsk_rto
+ * Arg3: whether RTO has expired
+ */
+ BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted.
+ * Arg1: sequence number of 1st byte
+ * Arg2: # segments
+ * Arg3: return value of
+ * tcp_transmit_skb (0 => success)
+ */
+ BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state.
+ * Arg1: old_state
+ * Arg2: new_state
+ */
+ BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after
+ * socket transition to LISTEN state.
+ */
+ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT.
+ */
+ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option.
+ * It will be called to handle
+ * the packets received at
+ * an already established
+ * connection.
+ *
+ * sock_ops->skb_data:
+ * Referring to the received skb.
+ * It covers the TCP header only.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option.
+ */
+ BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the
+ * header option later in
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Not available because no header has
+ * been written yet.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the
+ * outgoing skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_reserve_hdr_opt() should
+ * be used to reserve space.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Referring to the outgoing skb.
+ * It covers the TCP header
+ * that has already been written
+ * by the kernel and the
+ * earlier bpf-progs.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the outgoing
+ * skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_store_hdr_opt() should
+ * be used to write the
+ * option.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option that
+ * has already been written
+ * by the kernel or the
+ * earlier bpf-progs.
+ */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+ BPF_TCP_ESTABLISHED = 1,
+ BPF_TCP_SYN_SENT,
+ BPF_TCP_SYN_RECV,
+ BPF_TCP_FIN_WAIT1,
+ BPF_TCP_FIN_WAIT2,
+ BPF_TCP_TIME_WAIT,
+ BPF_TCP_CLOSE,
+ BPF_TCP_CLOSE_WAIT,
+ BPF_TCP_LAST_ACK,
+ BPF_TCP_LISTEN,
+ BPF_TCP_CLOSING, /* Now a valid state */
+ BPF_TCP_NEW_SYN_RECV,
+ BPF_TCP_BOUND_INACTIVE,
+
+ BPF_TCP_MAX_STATES /* Leave at the end! */
+};
+
+enum {
+ TCP_BPF_IW = 1001, /* Set TCP initial congestion window */
+ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */
+ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */
+ TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */
+ /* Copy the SYN pkt to optval
+ *
+ * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the
+ * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit
+ * to only getting from the saved_syn. It can either get the
+ * syn packet from:
+ *
+ * 1. the just-received SYN packet (only available when writing the
+ * SYNACK). It will be useful when it is not necessary to
+ * save the SYN packet for latter use. It is also the only way
+ * to get the SYN during syncookie mode because the syn
+ * packet cannot be saved during syncookie.
+ *
+ * OR
+ *
+ * 2. the earlier saved syn which was done by
+ * bpf_setsockopt(TCP_SAVE_SYN).
+ *
+ * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the
+ * SYN packet is obtained.
+ *
+ * If the bpf-prog does not need the IP[46] header, the
+ * bpf-prog can avoid parsing the IP header by using
+ * TCP_BPF_SYN. Otherwise, the bpf-prog can get both
+ * IP[46] and TCP header by using TCP_BPF_SYN_IP.
+ *
+ * >0: Total number of bytes copied
+ * -ENOSPC: Not enough space in optval. Only optlen number of
+ * bytes is copied.
+ * -ENOENT: The SYN skb is not available now and the earlier SYN pkt
+ * is not saved by setsockopt(TCP_SAVE_SYN).
+ */
+ TCP_BPF_SYN = 1005, /* Copy the TCP header */
+ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */
+ TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */
+};
+
+enum {
+ BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0),
+};
+
+/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ */
+enum {
+ BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the
+ * total option spaces
+ * required for an established
+ * sk in order to calculate the
+ * MSS. No skb is actually
+ * sent.
+ */
+ BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode
+ * when sending a SYN.
+ */
+};
+
+struct bpf_perf_event_value {
+ __u64 counter;
+ __u64 enabled;
+ __u64 running;
+};
+
+enum {
+ BPF_DEVCG_ACC_MKNOD = (1ULL << 0),
+ BPF_DEVCG_ACC_READ = (1ULL << 1),
+ BPF_DEVCG_ACC_WRITE = (1ULL << 2),
+};
+
+enum {
+ BPF_DEVCG_DEV_BLOCK = (1ULL << 0),
+ BPF_DEVCG_DEV_CHAR = (1ULL << 1),
+};
+
+struct bpf_cgroup_dev_ctx {
+ /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
+ __u32 access_type;
+ __u32 major;
+ __u32 minor;
+};
+
+struct bpf_raw_tracepoint_args {
+ __u64 args[0];
+};
+
+/* DIRECT: Skip the FIB rules and go to FIB table associated with device
+ * OUTPUT: Do lookup from egress perspective; default is ingress
+ */
+enum {
+ BPF_FIB_LOOKUP_DIRECT = (1U << 0),
+ BPF_FIB_LOOKUP_OUTPUT = (1U << 1),
+ BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
+ BPF_FIB_LOOKUP_TBID = (1U << 3),
+ BPF_FIB_LOOKUP_SRC = (1U << 4),
+};
+
+enum {
+ BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
+ BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */
+ BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */
+ BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */
+ BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */
+ BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+ BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */
+ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */
+ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+ BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */
+};
+
+struct bpf_fib_lookup {
+ /* input: network family for lookup (AF_INET, AF_INET6)
+ * output: network family of egress nexthop
+ */
+ __u8 family;
+
+ /* set if lookup is to consider L4 data - e.g., FIB rules */
+ __u8 l4_protocol;
+ __be16 sport;
+ __be16 dport;
+
+ union { /* used for MTU check */
+ /* input to lookup */
+ __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */
+
+ /* output: MTU value */
+ __u16 mtu_result;
+ };
+ /* input: L3 device index for lookup
+ * output: device index from FIB lookup
+ */
+ __u32 ifindex;
+
+ union {
+ /* inputs to lookup */
+ __u8 tos; /* AF_INET */
+ __be32 flowinfo; /* AF_INET6, flow_label + priority */
+
+ /* output: metric of fib result (IPv4/IPv6 only) */
+ __u32 rt_metric;
+ };
+
+ /* input: source address to consider for lookup
+ * output: source address result from lookup
+ */
+ union {
+ __be32 ipv4_src;
+ __u32 ipv6_src[4]; /* in6_addr; network order */
+ };
+
+ /* input to bpf_fib_lookup, ipv{4,6}_dst is destination address in
+ * network header. output: bpf_fib_lookup sets to gateway address
+ * if FIB lookup returns gateway route
+ */
+ union {
+ __be32 ipv4_dst;
+ __u32 ipv6_dst[4]; /* in6_addr; network order */
+ };
+
+ union {
+ struct {
+ /* output */
+ __be16 h_vlan_proto;
+ __be16 h_vlan_TCI;
+ };
+ /* input: when accompanied with the
+ * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a
+ * specific routing table to use for the fib lookup.
+ */
+ __u32 tbid;
+ };
+
+ __u8 smac[6]; /* ETH_ALEN */
+ __u8 dmac[6]; /* ETH_ALEN */
+};
+
+struct bpf_redir_neigh {
+ /* network family for lookup (AF_INET, AF_INET6) */
+ __u32 nh_family;
+ /* network address of nexthop; skips fib lookup to find gateway */
+ union {
+ __be32 ipv4_nh;
+ __u32 ipv6_nh[4]; /* in6_addr; network order */
+ };
+};
+
+/* bpf_check_mtu flags*/
+enum bpf_check_mtu_flags {
+ BPF_MTU_CHK_SEGS = (1U << 0),
+};
+
+enum bpf_check_mtu_ret {
+ BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */
+ BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+ BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */
+};
+
+enum bpf_task_fd_type {
+ BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
+ BPF_FD_TYPE_TRACEPOINT, /* tp name */
+ BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */
+ BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */
+ BPF_FD_TYPE_UPROBE, /* filename + offset */
+ BPF_FD_TYPE_URETPROBE, /* filename + offset */
+};
+
+enum {
+ BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG = (1U << 0),
+ BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL = (1U << 1),
+ BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP = (1U << 2),
+};
+
+struct bpf_flow_keys {
+ __u16 nhoff;
+ __u16 thoff;
+ __u16 addr_proto; /* ETH_P_* of valid addrs */
+ __u8 is_frag;
+ __u8 is_first_frag;
+ __u8 is_encap;
+ __u8 ip_proto;
+ __be16 n_proto;
+ __be16 sport;
+ __be16 dport;
+ union {
+ struct {
+ __be32 ipv4_src;
+ __be32 ipv4_dst;
+ };
+ struct {
+ __u32 ipv6_src[4]; /* in6_addr; network order */
+ __u32 ipv6_dst[4]; /* in6_addr; network order */
+ };
+ };
+ __u32 flags;
+ __be32 flow_label;
+};
+
+struct bpf_func_info {
+ __u32 insn_off;
+ __u32 type_id;
+};
+
+#define BPF_LINE_INFO_LINE_NUM(line_col) ((line_col) >> 10)
+#define BPF_LINE_INFO_LINE_COL(line_col) ((line_col) & 0x3ff)
+
+struct bpf_line_info {
+ __u32 insn_off;
+ __u32 file_name_off;
+ __u32 line_off;
+ __u32 line_col;
+};
+
+struct bpf_spin_lock {
+ __u32 val;
+};
+
+struct bpf_timer {
+ __u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_dynptr {
+ __u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_list_head {
+ __u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_list_node {
+ __u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_rb_root {
+ __u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_rb_node {
+ __u64 __opaque[4];
+} __attribute__((aligned(8)));
+
+struct bpf_refcount {
+ __u32 __opaque[1];
+} __attribute__((aligned(4)));
+
+struct bpf_sysctl {
+ __u32 write; /* Sysctl is being read (= 0) or written (= 1).
+ * Allows 1,2,4-byte read, but no write.
+ */
+ __u32 file_pos; /* Sysctl file position to read from, write to.
+ * Allows 1,2,4-byte read an 4-byte write.
+ */
+};
+
+struct bpf_sockopt {
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(void *, optval);
+ __bpf_md_ptr(void *, optval_end);
+
+ __s32 level;
+ __s32 optname;
+ __s32 optlen;
+ __s32 retval;
+};
+
+struct bpf_pidns_info {
+ __u32 pid;
+ __u32 tgid;
+};
+
+/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */
+struct bpf_sk_lookup {
+ union {
+ __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */
+ __u64 cookie; /* Non-zero if socket was selected in PROG_TEST_RUN */
+ };
+
+ __u32 family; /* Protocol family (AF_INET, AF_INET6) */
+ __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */
+ __u32 remote_ip4; /* Network byte order */
+ __u32 remote_ip6[4]; /* Network byte order */
+ __be16 remote_port; /* Network byte order */
+ __u16 :16; /* Zero padding */
+ __u32 local_ip4; /* Network byte order */
+ __u32 local_ip6[4]; /* Network byte order */
+ __u32 local_port; /* Host byte order */
+ __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */
+};
+
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above. A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+ void *ptr;
+ __u32 type_id;
+ __u32 flags; /* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ * - BTF_F_COMPACT: no formatting around type information
+ * - BTF_F_NONAME: no struct/union member names/types
+ * - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ * equivalent to %px.
+ * - BTF_F_ZERO: show zero-valued struct/union members; they
+ * are not displayed by default
+ */
+enum {
+ BTF_F_COMPACT = (1ULL << 0),
+ BTF_F_NONAME = (1ULL << 1),
+ BTF_F_PTR_RAW = (1ULL << 2),
+ BTF_F_ZERO = (1ULL << 3),
+};
+
+/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
+ * has to be adjusted by relocations. It is emitted by llvm and passed to
+ * libbpf and later to the kernel.
+ */
+enum bpf_core_relo_kind {
+ BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */
+ BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */
+ BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */
+ BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */
+ BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */
+ BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */
+ BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */
+ BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */
+ BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */
+ BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */
+ BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */
+ BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */
+ BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */
+};
+
+/*
+ * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf
+ * and from libbpf to the kernel.
+ *
+ * CO-RE relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ * its insn->imm field to be relocated with actual field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ * type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ * interpretation depends on specific relocation kind:
+ * - for field-based relocations, string encodes an accessed field using
+ * a sequence of field and array indices, separated by colon (:). It's
+ * conceptually very close to LLVM's getelementptr ([0]) instruction's
+ * arguments for identifying offset to a field.
+ * - for type-based relocations, strings is expected to be just "0";
+ * - for enum value-based relocations, string contains an index of enum
+ * value within its enum type;
+ * - kind - one of enum bpf_core_relo_kind;
+ *
+ * Example:
+ * struct sample {
+ * int a;
+ * struct {
+ * int b[10];
+ * };
+ * };
+ *
+ * struct sample *s = ...;
+ * int *x = &s->a; // encoded as "0:0" (a is field #0)
+ * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1,
+ * // b is field #0 inside anon struct, accessing elem #5)
+ * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ * __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit field relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_core_relo {
+ __u32 insn_off;
+ __u32 type_id;
+ __u32 access_str_off;
+ enum bpf_core_relo_kind kind;
+};
+
+/*
+ * Flags to control bpf_timer_start() behaviour.
+ * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
+ * relative to current time.
+ * - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller.
+ */
+enum {
+ BPF_F_TIMER_ABS = (1ULL << 0),
+ BPF_F_TIMER_CPU_PIN = (1ULL << 1),
+};
+
+/* BPF numbers iterator state */
+struct bpf_iter_num {
+ /* opaque iterator state; having __u64 here allows to preserve correct
+ * alignment requirements in vmlinux.h, generated from BTF
+ */
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+#endif /* __LINUX_BPF_H__ */
diff --git a/include/uapi/linux/bpf_common.h b/include/uapi/linux/bpf_common.h
new file mode 100644
index 0000000..f0fe139
--- /dev/null
+++ b/include/uapi/linux/bpf_common.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_BPF_COMMON_H__
+#define __LINUX_BPF_COMMON_H__
+
+/* Instruction classes */
+#define BPF_CLASS(code) ((code) & 0x07)
+#define BPF_LD 0x00
+#define BPF_LDX 0x01
+#define BPF_ST 0x02
+#define BPF_STX 0x03
+#define BPF_ALU 0x04
+#define BPF_JMP 0x05
+#define BPF_RET 0x06
+#define BPF_MISC 0x07
+
+/* ld/ldx fields */
+#define BPF_SIZE(code) ((code) & 0x18)
+#define BPF_W 0x00 /* 32-bit */
+#define BPF_H 0x08 /* 16-bit */
+#define BPF_B 0x10 /* 8-bit */
+/* eBPF BPF_DW 0x18 64-bit */
+#define BPF_MODE(code) ((code) & 0xe0)
+#define BPF_IMM 0x00
+#define BPF_ABS 0x20
+#define BPF_IND 0x40
+#define BPF_MEM 0x60
+#define BPF_LEN 0x80
+#define BPF_MSH 0xa0
+
+/* alu/jmp fields */
+#define BPF_OP(code) ((code) & 0xf0)
+#define BPF_ADD 0x00
+#define BPF_SUB 0x10
+#define BPF_MUL 0x20
+#define BPF_DIV 0x30
+#define BPF_OR 0x40
+#define BPF_AND 0x50
+#define BPF_LSH 0x60
+#define BPF_RSH 0x70
+#define BPF_NEG 0x80
+#define BPF_MOD 0x90
+#define BPF_XOR 0xa0
+
+#define BPF_JA 0x00
+#define BPF_JEQ 0x10
+#define BPF_JGT 0x20
+#define BPF_JGE 0x30
+#define BPF_JSET 0x40
+#define BPF_SRC(code) ((code) & 0x08)
+#define BPF_K 0x00
+#define BPF_X 0x08
+
+#ifndef BPF_MAXINSNS
+#define BPF_MAXINSNS 4096
+#endif
+
+#endif /* __LINUX_BPF_COMMON_H__ */
diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
new file mode 100644
index 0000000..426daf5
--- /dev/null
+++ b/include/uapi/linux/btf.h
@@ -0,0 +1,200 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2018 Facebook */
+#ifndef __LINUX_BTF_H__
+#define __LINUX_BTF_H__
+
+#include <linux/types.h>
+
+#define BTF_MAGIC 0xeB9F
+#define BTF_VERSION 1
+
+struct btf_header {
+ __u16 magic;
+ __u8 version;
+ __u8 flags;
+ __u32 hdr_len;
+
+ /* All offsets are in bytes relative to the end of this header */
+ __u32 type_off; /* offset of type section */
+ __u32 type_len; /* length of type section */
+ __u32 str_off; /* offset of string section */
+ __u32 str_len; /* length of string section */
+};
+
+/* Max # of type identifier */
+#define BTF_MAX_TYPE 0x000fffff
+/* Max offset into the string section */
+#define BTF_MAX_NAME_OFFSET 0x00ffffff
+/* Max # of struct/union/enum members or func args */
+#define BTF_MAX_VLEN 0xffff
+
+struct btf_type {
+ __u32 name_off;
+ /* "info" bits arrangement
+ * bits 0-15: vlen (e.g. # of struct's members)
+ * bits 16-23: unused
+ * bits 24-28: kind (e.g. int, ptr, array...etc)
+ * bits 29-30: unused
+ * bit 31: kind_flag, currently used by
+ * struct, union, enum, fwd and enum64
+ */
+ __u32 info;
+ /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64.
+ * "size" tells the size of the type it is describing.
+ *
+ * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
+ * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG.
+ * "type" is a type_id referring to another type.
+ */
+ union {
+ __u32 size;
+ __u32 type;
+ };
+};
+
+#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f)
+#define BTF_INFO_VLEN(info) ((info) & 0xffff)
+#define BTF_INFO_KFLAG(info) ((info) >> 31)
+
+enum {
+ BTF_KIND_UNKN = 0, /* Unknown */
+ BTF_KIND_INT = 1, /* Integer */
+ BTF_KIND_PTR = 2, /* Pointer */
+ BTF_KIND_ARRAY = 3, /* Array */
+ BTF_KIND_STRUCT = 4, /* Struct */
+ BTF_KIND_UNION = 5, /* Union */
+ BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */
+ BTF_KIND_FWD = 7, /* Forward */
+ BTF_KIND_TYPEDEF = 8, /* Typedef */
+ BTF_KIND_VOLATILE = 9, /* Volatile */
+ BTF_KIND_CONST = 10, /* Const */
+ BTF_KIND_RESTRICT = 11, /* Restrict */
+ BTF_KIND_FUNC = 12, /* Function */
+ BTF_KIND_FUNC_PROTO = 13, /* Function Proto */
+ BTF_KIND_VAR = 14, /* Variable */
+ BTF_KIND_DATASEC = 15, /* Section */
+ BTF_KIND_FLOAT = 16, /* Floating point */
+ BTF_KIND_DECL_TAG = 17, /* Decl Tag */
+ BTF_KIND_TYPE_TAG = 18, /* Type Tag */
+ BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */
+
+ NR_BTF_KINDS,
+ BTF_KIND_MAX = NR_BTF_KINDS - 1,
+};
+
+/* For some specific BTF_KIND, "struct btf_type" is immediately
+ * followed by extra data.
+ */
+
+/* BTF_KIND_INT is followed by a u32 and the following
+ * is the 32 bits arrangement:
+ */
+#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24)
+#define BTF_INT_OFFSET(VAL) (((VAL) & 0x00ff0000) >> 16)
+#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff)
+
+/* Attributes stored in the BTF_INT_ENCODING */
+#define BTF_INT_SIGNED (1 << 0)
+#define BTF_INT_CHAR (1 << 1)
+#define BTF_INT_BOOL (1 << 2)
+
+/* BTF_KIND_ENUM is followed by multiple "struct btf_enum".
+ * The exact number of btf_enum is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum {
+ __u32 name_off;
+ __s32 val;
+};
+
+/* BTF_KIND_ARRAY is followed by one "struct btf_array" */
+struct btf_array {
+ __u32 type;
+ __u32 index_type;
+ __u32 nelems;
+};
+
+/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed
+ * by multiple "struct btf_member". The exact number
+ * of btf_member is stored in the vlen (of the info in
+ * "struct btf_type").
+ */
+struct btf_member {
+ __u32 name_off;
+ __u32 type;
+ /* If the type info kind_flag is set, the btf_member offset
+ * contains both member bitfield size and bit offset. The
+ * bitfield size is set for bitfield members. If the type
+ * info kind_flag is not set, the offset contains only bit
+ * offset.
+ */
+ __u32 offset;
+};
+
+/* If the struct/union type info kind_flag is set, the
+ * following two macros are used to access bitfield_size
+ * and bit_offset from btf_member.offset.
+ */
+#define BTF_MEMBER_BITFIELD_SIZE(val) ((val) >> 24)
+#define BTF_MEMBER_BIT_OFFSET(val) ((val) & 0xffffff)
+
+/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
+ * The exact number of btf_param is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_param {
+ __u32 name_off;
+ __u32 type;
+};
+
+enum {
+ BTF_VAR_STATIC = 0,
+ BTF_VAR_GLOBAL_ALLOCATED = 1,
+ BTF_VAR_GLOBAL_EXTERN = 2,
+};
+
+enum btf_func_linkage {
+ BTF_FUNC_STATIC = 0,
+ BTF_FUNC_GLOBAL = 1,
+ BTF_FUNC_EXTERN = 2,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+ __u32 linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+ __u32 type;
+ __u32 offset;
+ __u32 size;
+};
+
+/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe
+ * additional information related to the tag applied location.
+ * If component_idx == -1, the tag is applied to a struct, union,
+ * variable or function. Otherwise, it is applied to a struct/union
+ * member or a func argument, and component_idx indicates which member
+ * or argument (0 ... vlen-1).
+ */
+struct btf_decl_tag {
+ __s32 component_idx;
+};
+
+/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64".
+ * The exact number of btf_enum64 is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum64 {
+ __u32 name_off;
+ __u32 val_lo32;
+ __u32 val_hi32;
+};
+
+#endif /* __LINUX_BTF_H__ */
diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
new file mode 100644
index 0000000..23d5bf4
--- /dev/null
+++ b/include/uapi/linux/can.h
@@ -0,0 +1,289 @@
+/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */
+/*
+ * linux/can.h
+ *
+ * Definitions for CAN network layer (socket addr / CAN frame / CAN filter)
+ *
+ * Authors: Oliver Hartkopp <oliver.hartkopp@volkswagen.de>
+ * Urs Thuermann <urs.thuermann@volkswagen.de>
+ * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ */
+
+#ifndef _CAN_H
+#define _CAN_H
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/stddef.h> /* for offsetof */
+
+/* controller area network (CAN) kernel definitions */
+
+/* special address description flags for the CAN_ID */
+#define CAN_EFF_FLAG 0x80000000U /* EFF/SFF is set in the MSB */
+#define CAN_RTR_FLAG 0x40000000U /* remote transmission request */
+#define CAN_ERR_FLAG 0x20000000U /* error message frame */
+
+/* valid bits in CAN ID for frame formats */
+#define CAN_SFF_MASK 0x000007FFU /* standard frame format (SFF) */
+#define CAN_EFF_MASK 0x1FFFFFFFU /* extended frame format (EFF) */
+#define CAN_ERR_MASK 0x1FFFFFFFU /* omit EFF, RTR, ERR flags */
+#define CANXL_PRIO_MASK CAN_SFF_MASK /* 11 bit priority mask */
+
+/*
+ * Controller Area Network Identifier structure
+ *
+ * bit 0-28 : CAN identifier (11/29 bit)
+ * bit 29 : error message frame flag (0 = data frame, 1 = error message)
+ * bit 30 : remote transmission request flag (1 = rtr frame)
+ * bit 31 : frame format flag (0 = standard 11 bit, 1 = extended 29 bit)
+ */
+typedef __u32 canid_t;
+
+#define CAN_SFF_ID_BITS 11
+#define CAN_EFF_ID_BITS 29
+#define CANXL_PRIO_BITS CAN_SFF_ID_BITS
+
+/*
+ * Controller Area Network Error Message Frame Mask structure
+ *
+ * bit 0-28 : error class mask (see include/uapi/linux/can/error.h)
+ * bit 29-31 : set to zero
+ */
+typedef __u32 can_err_mask_t;
+
+/* CAN payload length and DLC definitions according to ISO 11898-1 */
+#define CAN_MAX_DLC 8
+#define CAN_MAX_RAW_DLC 15
+#define CAN_MAX_DLEN 8
+
+/* CAN FD payload length and DLC definitions according to ISO 11898-7 */
+#define CANFD_MAX_DLC 15
+#define CANFD_MAX_DLEN 64
+
+/*
+ * CAN XL payload length and DLC definitions according to ISO 11898-1
+ * CAN XL DLC ranges from 0 .. 2047 => data length from 1 .. 2048 byte
+ */
+#define CANXL_MIN_DLC 0
+#define CANXL_MAX_DLC 2047
+#define CANXL_MAX_DLC_MASK 0x07FF
+#define CANXL_MIN_DLEN 1
+#define CANXL_MAX_DLEN 2048
+
+/**
+ * struct can_frame - Classical CAN frame structure (aka CAN 2.0B)
+ * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition
+ * @len: CAN frame payload length in byte (0 .. 8)
+ * @can_dlc: deprecated name for CAN frame payload length in byte (0 .. 8)
+ * @__pad: padding
+ * @__res0: reserved / padding
+ * @len8_dlc: optional DLC value (9 .. 15) at 8 byte payload length
+ * len8_dlc contains values from 9 .. 15 when the payload length is
+ * 8 bytes but the DLC value (see ISO 11898-1) is greater then 8.
+ * CAN_CTRLMODE_CC_LEN8_DLC flag has to be enabled in CAN driver.
+ * @data: CAN frame payload (up to 8 byte)
+ */
+struct can_frame {
+ canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */
+ union {
+ /* CAN frame payload length in byte (0 .. CAN_MAX_DLEN)
+ * was previously named can_dlc so we need to carry that
+ * name for legacy support
+ */
+ __u8 len;
+ __u8 can_dlc; /* deprecated */
+ } __attribute__((packed)); /* disable padding added in some ABIs */
+ __u8 __pad; /* padding */
+ __u8 __res0; /* reserved / padding */
+ __u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */
+ __u8 data[CAN_MAX_DLEN] __attribute__((aligned(8)));
+};
+
+/*
+ * defined bits for canfd_frame.flags
+ *
+ * The use of struct canfd_frame implies the FD Frame (FDF) bit to
+ * be set in the CAN frame bitstream on the wire. The FDF bit switch turns
+ * the CAN controllers bitstream processor into the CAN FD mode which creates
+ * two new options within the CAN FD frame specification:
+ *
+ * Bit Rate Switch - to indicate a second bitrate is/was used for the payload
+ * Error State Indicator - represents the error state of the transmitting node
+ *
+ * As the CANFD_ESI bit is internally generated by the transmitting CAN
+ * controller only the CANFD_BRS bit is relevant for real CAN controllers when
+ * building a CAN FD frame for transmission. Setting the CANFD_ESI bit can make
+ * sense for virtual CAN interfaces to test applications with echoed frames.
+ *
+ * The struct can_frame and struct canfd_frame intentionally share the same
+ * layout to be able to write CAN frame content into a CAN FD frame structure.
+ * When this is done the former differentiation via CAN_MTU / CANFD_MTU gets
+ * lost. CANFD_FDF allows programmers to mark CAN FD frames in the case of
+ * using struct canfd_frame for mixed CAN / CAN FD content (dual use).
+ * Since the introduction of CAN XL the CANFD_FDF flag is set in all CAN FD
+ * frame structures provided by the CAN subsystem of the Linux kernel.
+ */
+#define CANFD_BRS 0x01 /* bit rate switch (second bitrate for payload data) */
+#define CANFD_ESI 0x02 /* error state indicator of the transmitting node */
+#define CANFD_FDF 0x04 /* mark CAN FD for dual use of struct canfd_frame */
+
+/**
+ * struct canfd_frame - CAN flexible data rate frame structure
+ * @can_id: CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition
+ * @len: frame payload length in byte (0 .. CANFD_MAX_DLEN)
+ * @flags: additional flags for CAN FD
+ * @__res0: reserved / padding
+ * @__res1: reserved / padding
+ * @data: CAN FD frame payload (up to CANFD_MAX_DLEN byte)
+ */
+struct canfd_frame {
+ canid_t can_id; /* 32 bit CAN_ID + EFF/RTR/ERR flags */
+ __u8 len; /* frame payload length in byte */
+ __u8 flags; /* additional flags for CAN FD */
+ __u8 __res0; /* reserved / padding */
+ __u8 __res1; /* reserved / padding */
+ __u8 data[CANFD_MAX_DLEN] __attribute__((aligned(8)));
+};
+
+/*
+ * defined bits for canxl_frame.flags
+ *
+ * The canxl_frame.flags element contains two bits CANXL_XLF and CANXL_SEC
+ * and shares the relative position of the struct can[fd]_frame.len element.
+ * The CANXL_XLF bit ALWAYS needs to be set to indicate a valid CAN XL frame.
+ * As a side effect setting this bit intentionally breaks the length checks
+ * for Classical CAN and CAN FD frames.
+ *
+ * Undefined bits in canxl_frame.flags are reserved and shall be set to zero.
+ */
+#define CANXL_XLF 0x80 /* mandatory CAN XL frame flag (must always be set!) */
+#define CANXL_SEC 0x01 /* Simple Extended Content (security/segmentation) */
+
+/**
+ * struct canxl_frame - CAN with e'X'tended frame 'L'ength frame structure
+ * @prio: 11 bit arbitration priority with zero'ed CAN_*_FLAG flags
+ * @flags: additional flags for CAN XL
+ * @sdt: SDU (service data unit) type
+ * @len: frame payload length in byte (CANXL_MIN_DLEN .. CANXL_MAX_DLEN)
+ * @af: acceptance field
+ * @data: CAN XL frame payload (CANXL_MIN_DLEN .. CANXL_MAX_DLEN byte)
+ *
+ * @prio shares the same position as @can_id from struct can[fd]_frame.
+ */
+struct canxl_frame {
+ canid_t prio; /* 11 bit priority for arbitration (canid_t) */
+ __u8 flags; /* additional flags for CAN XL */
+ __u8 sdt; /* SDU (service data unit) type */
+ __u16 len; /* frame payload length in byte */
+ __u32 af; /* acceptance field */
+ __u8 data[CANXL_MAX_DLEN];
+};
+
+#define CAN_MTU (sizeof(struct can_frame))
+#define CANFD_MTU (sizeof(struct canfd_frame))
+#define CANXL_MTU (sizeof(struct canxl_frame))
+#define CANXL_HDR_SIZE (offsetof(struct canxl_frame, data))
+#define CANXL_MIN_MTU (CANXL_HDR_SIZE + 64)
+#define CANXL_MAX_MTU CANXL_MTU
+
+/* particular protocols of the protocol family PF_CAN */
+#define CAN_RAW 1 /* RAW sockets */
+#define CAN_BCM 2 /* Broadcast Manager */
+#define CAN_TP16 3 /* VAG Transport Protocol v1.6 */
+#define CAN_TP20 4 /* VAG Transport Protocol v2.0 */
+#define CAN_MCNET 5 /* Bosch MCNet */
+#define CAN_ISOTP 6 /* ISO 15765-2 Transport Protocol */
+#define CAN_J1939 7 /* SAE J1939 */
+#define CAN_NPROTO 8
+
+#define SOL_CAN_BASE 100
+
+/**
+ * struct sockaddr_can - the sockaddr structure for CAN sockets
+ * @can_family: address family number AF_CAN.
+ * @can_ifindex: CAN network interface index.
+ * @can_addr: protocol specific address information
+ */
+struct sockaddr_can {
+ __kernel_sa_family_t can_family;
+ int can_ifindex;
+ union {
+ /* transport protocol class address information (e.g. ISOTP) */
+ struct { canid_t rx_id, tx_id; } tp;
+
+ /* J1939 address information */
+ struct {
+ /* 8 byte name when using dynamic addressing */
+ __u64 name;
+
+ /* pgn:
+ * 8 bit: PS in PDU2 case, else 0
+ * 8 bit: PF
+ * 1 bit: DP
+ * 1 bit: reserved
+ */
+ __u32 pgn;
+
+ /* 1 byte address */
+ __u8 addr;
+ } j1939;
+
+ /* reserved for future CAN protocols address information */
+ } can_addr;
+};
+
+/**
+ * struct can_filter - CAN ID based filter in can_register().
+ * @can_id: relevant bits of CAN ID which are not masked out.
+ * @can_mask: CAN mask (see description)
+ *
+ * Description:
+ * A filter matches, when
+ *
+ * <received_can_id> & mask == can_id & mask
+ *
+ * The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can
+ * filter for error message frames (CAN_ERR_FLAG bit set in mask).
+ */
+struct can_filter {
+ canid_t can_id;
+ canid_t can_mask;
+};
+
+#define CAN_INV_FILTER 0x20000000U /* to be set in can_filter.can_id */
+
+#endif /* !_UAPI_CAN_H */
diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h
new file mode 100644
index 0000000..8ec98c2
--- /dev/null
+++ b/include/uapi/linux/can/netlink.h
@@ -0,0 +1,185 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * linux/can/netlink.h
+ *
+ * Definitions for the CAN netlink interface
+ *
+ * Copyright (c) 2009 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CAN_NETLINK_H
+#define _CAN_NETLINK_H
+
+#include <linux/types.h>
+
+/*
+ * CAN bit-timing parameters
+ *
+ * For further information, please read chapter "8 BIT TIMING
+ * REQUIREMENTS" of the "Bosch CAN Specification version 2.0"
+ * at http://www.semiconductors.bosch.de/pdf/can2spec.pdf.
+ */
+struct can_bittiming {
+ __u32 bitrate; /* Bit-rate in bits/second */
+ __u32 sample_point; /* Sample point in one-tenth of a percent */
+ __u32 tq; /* Time quanta (TQ) in nanoseconds */
+ __u32 prop_seg; /* Propagation segment in TQs */
+ __u32 phase_seg1; /* Phase buffer segment 1 in TQs */
+ __u32 phase_seg2; /* Phase buffer segment 2 in TQs */
+ __u32 sjw; /* Synchronisation jump width in TQs */
+ __u32 brp; /* Bit-rate prescaler */
+};
+
+/*
+ * CAN hardware-dependent bit-timing constant
+ *
+ * Used for calculating and checking bit-timing parameters
+ */
+struct can_bittiming_const {
+ char name[16]; /* Name of the CAN controller hardware */
+ __u32 tseg1_min; /* Time segment 1 = prop_seg + phase_seg1 */
+ __u32 tseg1_max;
+ __u32 tseg2_min; /* Time segment 2 = phase_seg2 */
+ __u32 tseg2_max;
+ __u32 sjw_max; /* Synchronisation jump width */
+ __u32 brp_min; /* Bit-rate prescaler */
+ __u32 brp_max;
+ __u32 brp_inc;
+};
+
+/*
+ * CAN clock parameters
+ */
+struct can_clock {
+ __u32 freq; /* CAN system clock frequency in Hz */
+};
+
+/*
+ * CAN operational and error states
+ */
+enum can_state {
+ CAN_STATE_ERROR_ACTIVE = 0, /* RX/TX error count < 96 */
+ CAN_STATE_ERROR_WARNING, /* RX/TX error count < 128 */
+ CAN_STATE_ERROR_PASSIVE, /* RX/TX error count < 256 */
+ CAN_STATE_BUS_OFF, /* RX/TX error count >= 256 */
+ CAN_STATE_STOPPED, /* Device is stopped */
+ CAN_STATE_SLEEPING, /* Device is sleeping */
+ CAN_STATE_MAX
+};
+
+/*
+ * CAN bus error counters
+ */
+struct can_berr_counter {
+ __u16 txerr;
+ __u16 rxerr;
+};
+
+/*
+ * CAN controller mode
+ */
+struct can_ctrlmode {
+ __u32 mask;
+ __u32 flags;
+};
+
+#define CAN_CTRLMODE_LOOPBACK 0x01 /* Loopback mode */
+#define CAN_CTRLMODE_LISTENONLY 0x02 /* Listen-only mode */
+#define CAN_CTRLMODE_3_SAMPLES 0x04 /* Triple sampling mode */
+#define CAN_CTRLMODE_ONE_SHOT 0x08 /* One-Shot mode */
+#define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */
+#define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */
+#define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */
+#define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */
+#define CAN_CTRLMODE_CC_LEN8_DLC 0x100 /* Classic CAN DLC option */
+#define CAN_CTRLMODE_TDC_AUTO 0x200 /* CAN transiver automatically calculates TDCV */
+#define CAN_CTRLMODE_TDC_MANUAL 0x400 /* TDCV is manually set up by user */
+
+/*
+ * CAN device statistics
+ */
+struct can_device_stats {
+ __u32 bus_error; /* Bus errors */
+ __u32 error_warning; /* Changes to error warning state */
+ __u32 error_passive; /* Changes to error passive state */
+ __u32 bus_off; /* Changes to bus off state */
+ __u32 arbitration_lost; /* Arbitration lost errors */
+ __u32 restarts; /* CAN controller re-starts */
+};
+
+/*
+ * CAN netlink interface
+ */
+enum {
+ IFLA_CAN_UNSPEC,
+ IFLA_CAN_BITTIMING,
+ IFLA_CAN_BITTIMING_CONST,
+ IFLA_CAN_CLOCK,
+ IFLA_CAN_STATE,
+ IFLA_CAN_CTRLMODE,
+ IFLA_CAN_RESTART_MS,
+ IFLA_CAN_RESTART,
+ IFLA_CAN_BERR_COUNTER,
+ IFLA_CAN_DATA_BITTIMING,
+ IFLA_CAN_DATA_BITTIMING_CONST,
+ IFLA_CAN_TERMINATION,
+ IFLA_CAN_TERMINATION_CONST,
+ IFLA_CAN_BITRATE_CONST,
+ IFLA_CAN_DATA_BITRATE_CONST,
+ IFLA_CAN_BITRATE_MAX,
+ IFLA_CAN_TDC,
+ IFLA_CAN_CTRLMODE_EXT,
+
+ /* add new constants above here */
+ __IFLA_CAN_MAX,
+ IFLA_CAN_MAX = __IFLA_CAN_MAX - 1
+};
+
+/*
+ * CAN FD Transmitter Delay Compensation (TDC)
+ *
+ * Please refer to struct can_tdc_const and can_tdc in
+ * include/linux/can/bittiming.h for further details.
+ */
+enum {
+ IFLA_CAN_TDC_UNSPEC,
+ IFLA_CAN_TDC_TDCV_MIN, /* u32 */
+ IFLA_CAN_TDC_TDCV_MAX, /* u32 */
+ IFLA_CAN_TDC_TDCO_MIN, /* u32 */
+ IFLA_CAN_TDC_TDCO_MAX, /* u32 */
+ IFLA_CAN_TDC_TDCF_MIN, /* u32 */
+ IFLA_CAN_TDC_TDCF_MAX, /* u32 */
+ IFLA_CAN_TDC_TDCV, /* u32 */
+ IFLA_CAN_TDC_TDCO, /* u32 */
+ IFLA_CAN_TDC_TDCF, /* u32 */
+
+ /* add new constants above here */
+ __IFLA_CAN_TDC,
+ IFLA_CAN_TDC_MAX = __IFLA_CAN_TDC - 1
+};
+
+/*
+ * IFLA_CAN_CTRLMODE_EXT nest: controller mode extended parameters
+ */
+enum {
+ IFLA_CAN_CTRLMODE_UNSPEC,
+ IFLA_CAN_CTRLMODE_SUPPORTED, /* u32 */
+
+ /* add new constants above here */
+ __IFLA_CAN_CTRLMODE,
+ IFLA_CAN_CTRLMODE_MAX = __IFLA_CAN_CTRLMODE - 1
+};
+
+/* u16 termination range: 1..65535 Ohms */
+#define CAN_TERMINATION_DISABLED 0
+
+#endif /* !_UAPI_CAN_NETLINK_H */
diff --git a/include/uapi/linux/can/vxcan.h b/include/uapi/linux/can/vxcan.h
new file mode 100644
index 0000000..3e3d2eb
--- /dev/null
+++ b/include/uapi/linux/can/vxcan.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+#ifndef _CAN_VXCAN_H
+#define _CAN_VXCAN_H
+
+enum {
+ VXCAN_INFO_UNSPEC,
+ VXCAN_INFO_PEER,
+
+ __VXCAN_INFO_MAX
+#define VXCAN_INFO_MAX (__VXCAN_INFO_MAX - 1)
+};
+
+#endif
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
new file mode 100644
index 0000000..e48f039
--- /dev/null
+++ b/include/uapi/linux/capability.h
@@ -0,0 +1,431 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * This is <linux/capability.h>
+ *
+ * Andrew G. Morgan <morgan@kernel.org>
+ * Alexander Kjeldaas <astor@guardian.no>
+ * with help from Aleph1, Roland Buresund and Andrew Main.
+ *
+ * See here for the libcap library ("POSIX draft" compliance):
+ *
+ * ftp://www.kernel.org/pub/linux/libs/security/linux-privs/kernel-2.6/
+ */
+
+#ifndef _LINUX_CAPABILITY_H
+#define _LINUX_CAPABILITY_H
+
+#include <linux/types.h>
+
+/* User-level do most of the mapping between kernel and user
+ capabilities based on the version tag given by the kernel. The
+ kernel might be somewhat backwards compatible, but don't bet on
+ it. */
+
+/* Note, cap_t, is defined by POSIX (draft) to be an "opaque" pointer to
+ a set of three capability sets. The transposition of 3*the
+ following structure to such a composite is better handled in a user
+ library since the draft standard requires the use of malloc/free
+ etc.. */
+
+#define _LINUX_CAPABILITY_VERSION_1 0x19980330
+#define _LINUX_CAPABILITY_U32S_1 1
+
+#define _LINUX_CAPABILITY_VERSION_2 0x20071026 /* deprecated - use v3 */
+#define _LINUX_CAPABILITY_U32S_2 2
+
+#define _LINUX_CAPABILITY_VERSION_3 0x20080522
+#define _LINUX_CAPABILITY_U32S_3 2
+
+typedef struct __user_cap_header_struct {
+ __u32 version;
+ int pid;
+} *cap_user_header_t;
+
+struct __user_cap_data_struct {
+ __u32 effective;
+ __u32 permitted;
+ __u32 inheritable;
+};
+typedef struct __user_cap_data_struct *cap_user_data_t;
+
+
+#define VFS_CAP_REVISION_MASK 0xFF000000
+#define VFS_CAP_REVISION_SHIFT 24
+#define VFS_CAP_FLAGS_MASK ~VFS_CAP_REVISION_MASK
+#define VFS_CAP_FLAGS_EFFECTIVE 0x000001
+
+#define VFS_CAP_REVISION_1 0x01000000
+#define VFS_CAP_U32_1 1
+#define XATTR_CAPS_SZ_1 (sizeof(__le32)*(1 + 2*VFS_CAP_U32_1))
+
+#define VFS_CAP_REVISION_2 0x02000000
+#define VFS_CAP_U32_2 2
+#define XATTR_CAPS_SZ_2 (sizeof(__le32)*(1 + 2*VFS_CAP_U32_2))
+
+#define VFS_CAP_REVISION_3 0x03000000
+#define VFS_CAP_U32_3 2
+#define XATTR_CAPS_SZ_3 (sizeof(__le32)*(2 + 2*VFS_CAP_U32_3))
+
+#define XATTR_CAPS_SZ XATTR_CAPS_SZ_3
+#define VFS_CAP_U32 VFS_CAP_U32_3
+#define VFS_CAP_REVISION VFS_CAP_REVISION_3
+
+struct vfs_cap_data {
+ __le32 magic_etc; /* Little endian */
+ struct {
+ __le32 permitted; /* Little endian */
+ __le32 inheritable; /* Little endian */
+ } data[VFS_CAP_U32];
+};
+
+/*
+ * same as vfs_cap_data but with a rootid at the end
+ */
+struct vfs_ns_cap_data {
+ __le32 magic_etc;
+ struct {
+ __le32 permitted; /* Little endian */
+ __le32 inheritable; /* Little endian */
+ } data[VFS_CAP_U32];
+ __le32 rootid;
+};
+
+
+/*
+ * Backwardly compatible definition for source code - trapped in a
+ * 32-bit world. If you find you need this, please consider using
+ * libcap to untrap yourself...
+ */
+#define _LINUX_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_1
+#define _LINUX_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_1
+
+
+
+/**
+ ** POSIX-draft defined capabilities.
+ **/
+
+/* In a system with the [_POSIX_CHOWN_RESTRICTED] option defined, this
+ overrides the restriction of changing file ownership and group
+ ownership. */
+
+#define CAP_CHOWN 0
+
+/* Override all DAC access, including ACL execute access if
+ [_POSIX_ACL] is defined. Excluding DAC access covered by
+ CAP_LINUX_IMMUTABLE. */
+
+#define CAP_DAC_OVERRIDE 1
+
+/* Overrides all DAC restrictions regarding read and search on files
+ and directories, including ACL restrictions if [_POSIX_ACL] is
+ defined. Excluding DAC access covered by CAP_LINUX_IMMUTABLE. */
+
+#define CAP_DAC_READ_SEARCH 2
+
+/* Overrides all restrictions about allowed operations on files, where
+ file owner ID must be equal to the user ID, except where CAP_FSETID
+ is applicable. It doesn't override MAC and DAC restrictions. */
+
+#define CAP_FOWNER 3
+
+/* Overrides the following restrictions that the effective user ID
+ shall match the file owner ID when setting the S_ISUID and S_ISGID
+ bits on that file; that the effective group ID (or one of the
+ supplementary group IDs) shall match the file owner ID when setting
+ the S_ISGID bit on that file; that the S_ISUID and S_ISGID bits are
+ cleared on successful return from chown(2) (not implemented). */
+
+#define CAP_FSETID 4
+
+/* Overrides the restriction that the real or effective user ID of a
+ process sending a signal must match the real or effective user ID
+ of the process receiving the signal. */
+
+#define CAP_KILL 5
+
+/* Allows setgid(2) manipulation */
+/* Allows setgroups(2) */
+/* Allows forged gids on socket credentials passing. */
+
+#define CAP_SETGID 6
+
+/* Allows set*uid(2) manipulation (including fsuid). */
+/* Allows forged pids on socket credentials passing. */
+
+#define CAP_SETUID 7
+
+
+/**
+ ** Linux-specific capabilities
+ **/
+
+/* Without VFS support for capabilities:
+ * Transfer any capability in your permitted set to any pid,
+ * remove any capability in your permitted set from any pid
+ * With VFS support for capabilities (neither of above, but)
+ * Add any capability from current's capability bounding set
+ * to the current process' inheritable set
+ * Allow taking bits out of capability bounding set
+ * Allow modification of the securebits for a process
+ */
+
+#define CAP_SETPCAP 8
+
+/* Allow modification of S_IMMUTABLE and S_APPEND file attributes */
+
+#define CAP_LINUX_IMMUTABLE 9
+
+/* Allows binding to TCP/UDP sockets below 1024 */
+/* Allows binding to ATM VCIs below 32 */
+
+#define CAP_NET_BIND_SERVICE 10
+
+/* Allow broadcasting, listen to multicast */
+
+#define CAP_NET_BROADCAST 11
+
+/* Allow interface configuration */
+/* Allow administration of IP firewall, masquerading and accounting */
+/* Allow setting debug option on sockets */
+/* Allow modification of routing tables */
+/* Allow setting arbitrary process / process group ownership on
+ sockets */
+/* Allow binding to any address for transparent proxying (also via NET_RAW) */
+/* Allow setting TOS (type of service) */
+/* Allow setting promiscuous mode */
+/* Allow clearing driver statistics */
+/* Allow multicasting */
+/* Allow read/write of device-specific registers */
+/* Allow activation of ATM control sockets */
+
+#define CAP_NET_ADMIN 12
+
+/* Allow use of RAW sockets */
+/* Allow use of PACKET sockets */
+/* Allow binding to any address for transparent proxying (also via NET_ADMIN) */
+
+#define CAP_NET_RAW 13
+
+/* Allow locking of shared memory segments */
+/* Allow mlock and mlockall (which doesn't really have anything to do
+ with IPC) */
+
+#define CAP_IPC_LOCK 14
+
+/* Override IPC ownership checks */
+
+#define CAP_IPC_OWNER 15
+
+/* Insert and remove kernel modules - modify kernel without limit */
+#define CAP_SYS_MODULE 16
+
+/* Allow ioperm/iopl access */
+/* Allow sending USB messages to any device via /dev/bus/usb */
+
+#define CAP_SYS_RAWIO 17
+
+/* Allow use of chroot() */
+
+#define CAP_SYS_CHROOT 18
+
+/* Allow ptrace() of any process */
+
+#define CAP_SYS_PTRACE 19
+
+/* Allow configuration of process accounting */
+
+#define CAP_SYS_PACCT 20
+
+/* Allow configuration of the secure attention key */
+/* Allow administration of the random device */
+/* Allow examination and configuration of disk quotas */
+/* Allow setting the domainname */
+/* Allow setting the hostname */
+/* Allow mount() and umount(), setting up new smb connection */
+/* Allow some autofs root ioctls */
+/* Allow nfsservctl */
+/* Allow VM86_REQUEST_IRQ */
+/* Allow to read/write pci config on alpha */
+/* Allow irix_prctl on mips (setstacksize) */
+/* Allow flushing all cache on m68k (sys_cacheflush) */
+/* Allow removing semaphores */
+/* Used instead of CAP_CHOWN to "chown" IPC message queues, semaphores
+ and shared memory */
+/* Allow locking/unlocking of shared memory segment */
+/* Allow turning swap on/off */
+/* Allow forged pids on socket credentials passing */
+/* Allow setting readahead and flushing buffers on block devices */
+/* Allow setting geometry in floppy driver */
+/* Allow turning DMA on/off in xd driver */
+/* Allow administration of md devices (mostly the above, but some
+ extra ioctls) */
+/* Allow tuning the ide driver */
+/* Allow access to the nvram device */
+/* Allow administration of apm_bios, serial and bttv (TV) device */
+/* Allow manufacturer commands in isdn CAPI support driver */
+/* Allow reading non-standardized portions of pci configuration space */
+/* Allow DDI debug ioctl on sbpcd driver */
+/* Allow setting up serial ports */
+/* Allow sending raw qic-117 commands */
+/* Allow enabling/disabling tagged queuing on SCSI controllers and sending
+ arbitrary SCSI commands */
+/* Allow setting encryption key on loopback filesystem */
+/* Allow setting zone reclaim policy */
+/* Allow everything under CAP_BPF and CAP_PERFMON for backward compatibility */
+
+#define CAP_SYS_ADMIN 21
+
+/* Allow use of reboot() */
+
+#define CAP_SYS_BOOT 22
+
+/* Allow raising priority and setting priority on other (different
+ UID) processes */
+/* Allow use of FIFO and round-robin (realtime) scheduling on own
+ processes and setting the scheduling algorithm used by another
+ process. */
+/* Allow setting cpu affinity on other processes */
+/* Allow setting realtime ioprio class */
+/* Allow setting ioprio class on other processes */
+
+#define CAP_SYS_NICE 23
+
+/* Override resource limits. Set resource limits. */
+/* Override quota limits. */
+/* Override reserved space on ext2 filesystem */
+/* Modify data journaling mode on ext3 filesystem (uses journaling
+ resources) */
+/* NOTE: ext2 honors fsuid when checking for resource overrides, so
+ you can override using fsuid too */
+/* Override size restrictions on IPC message queues */
+/* Allow more than 64hz interrupts from the real-time clock */
+/* Override max number of consoles on console allocation */
+/* Override max number of keymaps */
+/* Control memory reclaim behavior */
+
+#define CAP_SYS_RESOURCE 24
+
+/* Allow manipulation of system clock */
+/* Allow irix_stime on mips */
+/* Allow setting the real-time clock */
+
+#define CAP_SYS_TIME 25
+
+/* Allow configuration of tty devices */
+/* Allow vhangup() of tty */
+
+#define CAP_SYS_TTY_CONFIG 26
+
+/* Allow the privileged aspects of mknod() */
+
+#define CAP_MKNOD 27
+
+/* Allow taking of leases on files */
+
+#define CAP_LEASE 28
+
+/* Allow writing the audit log via unicast netlink socket */
+
+#define CAP_AUDIT_WRITE 29
+
+/* Allow configuration of audit via unicast netlink socket */
+
+#define CAP_AUDIT_CONTROL 30
+
+/* Set or remove capabilities on files.
+ Map uid=0 into a child user namespace. */
+
+#define CAP_SETFCAP 31
+
+/* Override MAC access.
+ The base kernel enforces no MAC policy.
+ An LSM may enforce a MAC policy, and if it does and it chooses
+ to implement capability based overrides of that policy, this is
+ the capability it should use to do so. */
+
+#define CAP_MAC_OVERRIDE 32
+
+/* Allow MAC configuration or state changes.
+ The base kernel requires no MAC configuration.
+ An LSM may enforce a MAC policy, and if it does and it chooses
+ to implement capability based checks on modifications to that
+ policy or the data required to maintain it, this is the
+ capability it should use to do so. */
+
+#define CAP_MAC_ADMIN 33
+
+/* Allow configuring the kernel's syslog (printk behaviour) */
+
+#define CAP_SYSLOG 34
+
+/* Allow triggering something that will wake the system */
+
+#define CAP_WAKE_ALARM 35
+
+/* Allow preventing system suspends */
+
+#define CAP_BLOCK_SUSPEND 36
+
+/* Allow reading the audit log via multicast netlink socket */
+
+#define CAP_AUDIT_READ 37
+
+/*
+ * Allow system performance and observability privileged operations
+ * using perf_events, i915_perf and other kernel subsystems
+ */
+
+#define CAP_PERFMON 38
+
+/*
+ * CAP_BPF allows the following BPF operations:
+ * - Creating all types of BPF maps
+ * - Advanced verifier features
+ * - Indirect variable access
+ * - Bounded loops
+ * - BPF to BPF function calls
+ * - Scalar precision tracking
+ * - Larger complexity limits
+ * - Dead code elimination
+ * - And potentially other features
+ * - Loading BPF Type Format (BTF) data
+ * - Retrieve xlated and JITed code of BPF programs
+ * - Use bpf_spin_lock() helper
+ *
+ * CAP_PERFMON relaxes the verifier checks further:
+ * - BPF progs can use of pointer-to-integer conversions
+ * - speculation attack hardening measures are bypassed
+ * - bpf_probe_read to read arbitrary kernel memory is allowed
+ * - bpf_trace_printk to print kernel memory is allowed
+ *
+ * CAP_SYS_ADMIN is required to use bpf_probe_write_user.
+ *
+ * CAP_SYS_ADMIN is required to iterate system wide loaded
+ * programs, maps, links, BTFs and convert their IDs to file descriptors.
+ *
+ * CAP_PERFMON and CAP_BPF are required to load tracing programs.
+ * CAP_NET_ADMIN and CAP_BPF are required to load networking programs.
+ */
+#define CAP_BPF 39
+
+
+/* Allow checkpoint/restore related operations */
+/* Allow PID selection during clone3() */
+/* Allow writing to ns_last_pid */
+
+#define CAP_CHECKPOINT_RESTORE 40
+
+#define CAP_LAST_CAP CAP_CHECKPOINT_RESTORE
+
+#define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
+
+/*
+ * Bit location of each capability (used by user-space library and kernel)
+ */
+
+#define CAP_TO_INDEX(x) ((x) >> 5) /* 1 << 5 == bits in __u32 */
+#define CAP_TO_MASK(x) (1U << ((x) & 31)) /* mask for indexed __u32 */
+
+
+#endif /* _LINUX_CAPABILITY_H */
diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h
new file mode 100644
index 0000000..1eb84b5
--- /dev/null
+++ b/include/uapi/linux/const.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* const.h: Macros for dealing with constants. */
+
+#ifndef _LINUX_CONST_H
+#define _LINUX_CONST_H
+
+/* Some constant macros are used in both assembler and
+ * C code. Therefore we cannot annotate them always with
+ * 'UL' and other type specifiers unilaterally. We
+ * use the following macros to deal with this.
+ *
+ * Similarly, _AT() will cast an expression with a type in C, but
+ * leave it unchanged in asm.
+ */
+
+#ifdef __ASSEMBLY__
+#define _AC(X,Y) X
+#define _AT(T,X) X
+#else
+#define __AC(X,Y) (X##Y)
+#define _AC(X,Y) __AC(X,Y)
+#define _AT(T,X) ((T)(X))
+#endif
+
+#define _UL(x) (_AC(x, UL))
+#define _ULL(x) (_AC(x, ULL))
+
+#define _BITUL(x) (_UL(1) << (x))
+#define _BITULL(x) (_ULL(1) << (x))
+
+#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
+
+#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+
+#endif /* _LINUX_CONST_H */
diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h
new file mode 100644
index 0000000..7e15214
--- /dev/null
+++ b/include/uapi/linux/dcbnl.h
@@ -0,0 +1,779 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2008-2011, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: Lucy Liu <lucy.liu@intel.com>
+ */
+
+#ifndef __LINUX_DCBNL_H__
+#define __LINUX_DCBNL_H__
+
+#include <linux/types.h>
+
+/* IEEE 802.1Qaz std supported values */
+#define IEEE_8021QAZ_MAX_TCS 8
+
+#define IEEE_8021QAZ_TSA_STRICT 0
+#define IEEE_8021QAZ_TSA_CB_SHAPER 1
+#define IEEE_8021QAZ_TSA_ETS 2
+#define IEEE_8021QAZ_TSA_VENDOR 255
+
+/* This structure contains the IEEE 802.1Qaz ETS managed object
+ *
+ * @willing: willing bit in ETS configuration TLV
+ * @ets_cap: indicates supported capacity of ets feature
+ * @cbs: credit based shaper ets algorithm supported
+ * @tc_tx_bw: tc tx bandwidth indexed by traffic class
+ * @tc_rx_bw: tc rx bandwidth indexed by traffic class
+ * @tc_tsa: TSA Assignment table, indexed by traffic class
+ * @prio_tc: priority assignment table mapping 8021Qp to traffic class
+ * @tc_reco_bw: recommended tc bandwidth indexed by traffic class for TLV
+ * @tc_reco_tsa: recommended tc bandwidth indexed by traffic class for TLV
+ * @reco_prio_tc: recommended tc tx bandwidth indexed by traffic class for TLV
+ *
+ * Recommended values are used to set fields in the ETS recommendation TLV
+ * with hardware offloaded LLDP.
+ *
+ * ----
+ * TSA Assignment 8 bit identifiers
+ * 0 strict priority
+ * 1 credit-based shaper
+ * 2 enhanced transmission selection
+ * 3-254 reserved
+ * 255 vendor specific
+ */
+struct ieee_ets {
+ __u8 willing;
+ __u8 ets_cap;
+ __u8 cbs;
+ __u8 tc_tx_bw[IEEE_8021QAZ_MAX_TCS];
+ __u8 tc_rx_bw[IEEE_8021QAZ_MAX_TCS];
+ __u8 tc_tsa[IEEE_8021QAZ_MAX_TCS];
+ __u8 prio_tc[IEEE_8021QAZ_MAX_TCS];
+ __u8 tc_reco_bw[IEEE_8021QAZ_MAX_TCS];
+ __u8 tc_reco_tsa[IEEE_8021QAZ_MAX_TCS];
+ __u8 reco_prio_tc[IEEE_8021QAZ_MAX_TCS];
+};
+
+/* This structure contains rate limit extension to the IEEE 802.1Qaz ETS
+ * managed object.
+ * Values are 64 bits long and specified in Kbps to enable usage over both
+ * slow and very fast networks.
+ *
+ * @tc_maxrate: maximal tc tx bandwidth indexed by traffic class
+ */
+struct ieee_maxrate {
+ __u64 tc_maxrate[IEEE_8021QAZ_MAX_TCS];
+};
+
+enum dcbnl_cndd_states {
+ DCB_CNDD_RESET = 0,
+ DCB_CNDD_EDGE,
+ DCB_CNDD_INTERIOR,
+ DCB_CNDD_INTERIOR_READY,
+};
+
+/* This structure contains the IEEE 802.1Qau QCN managed object.
+ *
+ *@rpg_enable: enable QCN RP
+ *@rppp_max_rps: maximum number of RPs allowed for this CNPV on this port
+ *@rpg_time_reset: time between rate increases if no CNMs received.
+ * given in u-seconds
+ *@rpg_byte_reset: transmitted data between rate increases if no CNMs received.
+ * given in Bytes
+ *@rpg_threshold: The number of times rpByteStage or rpTimeStage can count
+ * before RP rate control state machine advances states
+ *@rpg_max_rate: the maxinun rate, in Mbits per second,
+ * at which an RP can transmit
+ *@rpg_ai_rate: The rate, in Mbits per second,
+ * used to increase rpTargetRate in the RPR_ACTIVE_INCREASE
+ *@rpg_hai_rate: The rate, in Mbits per second,
+ * used to increase rpTargetRate in the RPR_HYPER_INCREASE state
+ *@rpg_gd: Upon CNM receive, flow rate is limited to (Fb/Gd)*CurrentRate.
+ * rpgGd is given as log2(Gd), where Gd may only be powers of 2
+ *@rpg_min_dec_fac: The minimum factor by which the current transmit rate
+ * can be changed by reception of a CNM.
+ * value is given as percentage (1-100)
+ *@rpg_min_rate: The minimum value, in bits per second, for rate to limit
+ *@cndd_state_machine: The state of the congestion notification domain
+ * defense state machine, as defined by IEEE 802.3Qau
+ * section 32.1.1. In the interior ready state,
+ * the QCN capable hardware may add CN-TAG TLV to the
+ * outgoing traffic, to specifically identify outgoing
+ * flows.
+ */
+
+struct ieee_qcn {
+ __u8 rpg_enable[IEEE_8021QAZ_MAX_TCS];
+ __u32 rppp_max_rps[IEEE_8021QAZ_MAX_TCS];
+ __u32 rpg_time_reset[IEEE_8021QAZ_MAX_TCS];
+ __u32 rpg_byte_reset[IEEE_8021QAZ_MAX_TCS];
+ __u32 rpg_threshold[IEEE_8021QAZ_MAX_TCS];
+ __u32 rpg_max_rate[IEEE_8021QAZ_MAX_TCS];
+ __u32 rpg_ai_rate[IEEE_8021QAZ_MAX_TCS];
+ __u32 rpg_hai_rate[IEEE_8021QAZ_MAX_TCS];
+ __u32 rpg_gd[IEEE_8021QAZ_MAX_TCS];
+ __u32 rpg_min_dec_fac[IEEE_8021QAZ_MAX_TCS];
+ __u32 rpg_min_rate[IEEE_8021QAZ_MAX_TCS];
+ __u32 cndd_state_machine[IEEE_8021QAZ_MAX_TCS];
+};
+
+/* This structure contains the IEEE 802.1Qau QCN statistics.
+ *
+ *@rppp_rp_centiseconds: the number of RP-centiseconds accumulated
+ * by RPs at this priority level on this Port
+ *@rppp_created_rps: number of active RPs(flows) that react to CNMs
+ */
+
+struct ieee_qcn_stats {
+ __u64 rppp_rp_centiseconds[IEEE_8021QAZ_MAX_TCS];
+ __u32 rppp_created_rps[IEEE_8021QAZ_MAX_TCS];
+};
+
+/* This structure contains the IEEE 802.1Qaz PFC managed object
+ *
+ * @pfc_cap: Indicates the number of traffic classes on the local device
+ * that may simultaneously have PFC enabled.
+ * @pfc_en: bitmap indicating pfc enabled traffic classes
+ * @mbc: enable macsec bypass capability
+ * @delay: the allowance made for a round-trip propagation delay of the
+ * link in bits.
+ * @requests: count of the sent pfc frames
+ * @indications: count of the received pfc frames
+ */
+struct ieee_pfc {
+ __u8 pfc_cap;
+ __u8 pfc_en;
+ __u8 mbc;
+ __u16 delay;
+ __u64 requests[IEEE_8021QAZ_MAX_TCS];
+ __u64 indications[IEEE_8021QAZ_MAX_TCS];
+};
+
+#define IEEE_8021Q_MAX_PRIORITIES 8
+#define DCBX_MAX_BUFFERS 8
+struct dcbnl_buffer {
+ /* priority to buffer mapping */
+ __u8 prio2buffer[IEEE_8021Q_MAX_PRIORITIES];
+ /* buffer size in Bytes */
+ __u32 buffer_size[DCBX_MAX_BUFFERS];
+ __u32 total_size;
+};
+
+/* CEE DCBX std supported values */
+#define CEE_DCBX_MAX_PGS 8
+#define CEE_DCBX_MAX_PRIO 8
+
+/**
+ * struct cee_pg - CEE Priority-Group managed object
+ *
+ * @willing: willing bit in the PG tlv
+ * @error: error bit in the PG tlv
+ * @pg_en: enable bit of the PG feature
+ * @tcs_supported: number of traffic classes supported
+ * @pg_bw: bandwidth percentage for each priority group
+ * @prio_pg: priority to PG mapping indexed by priority
+ */
+struct cee_pg {
+ __u8 willing;
+ __u8 error;
+ __u8 pg_en;
+ __u8 tcs_supported;
+ __u8 pg_bw[CEE_DCBX_MAX_PGS];
+ __u8 prio_pg[CEE_DCBX_MAX_PGS];
+};
+
+/**
+ * struct cee_pfc - CEE PFC managed object
+ *
+ * @willing: willing bit in the PFC tlv
+ * @error: error bit in the PFC tlv
+ * @pfc_en: bitmap indicating pfc enabled traffic classes
+ * @tcs_supported: number of traffic classes supported
+ */
+struct cee_pfc {
+ __u8 willing;
+ __u8 error;
+ __u8 pfc_en;
+ __u8 tcs_supported;
+};
+
+/* IEEE 802.1Qaz std supported values */
+#define IEEE_8021QAZ_APP_SEL_ETHERTYPE 1
+#define IEEE_8021QAZ_APP_SEL_STREAM 2
+#define IEEE_8021QAZ_APP_SEL_DGRAM 3
+#define IEEE_8021QAZ_APP_SEL_ANY 4
+#define IEEE_8021QAZ_APP_SEL_DSCP 5
+
+/* Non-std selector values */
+#define DCB_APP_SEL_PCP 255
+
+/* This structure contains the IEEE 802.1Qaz APP managed object. This
+ * object is also used for the CEE std as well.
+ *
+ * @selector: protocol identifier type
+ * @protocol: protocol of type indicated
+ * @priority: 3-bit unsigned integer indicating priority for IEEE
+ * 8-bit 802.1p user priority bitmap for CEE
+ *
+ * ----
+ * Selector field values for IEEE 802.1Qaz
+ * 0 Reserved
+ * 1 Ethertype
+ * 2 Well known port number over TCP or SCTP
+ * 3 Well known port number over UDP or DCCP
+ * 4 Well known port number over TCP, SCTP, UDP, or DCCP
+ * 5 Differentiated Services Code Point (DSCP) value
+ * 6-7 Reserved
+ *
+ * Selector field values for CEE
+ * 0 Ethertype
+ * 1 Well known port number over TCP or UDP
+ * 2-3 Reserved
+ */
+struct dcb_app {
+ __u8 selector;
+ __u8 priority;
+ __u16 protocol;
+};
+
+#define IEEE_8021QAZ_APP_SEL_MAX 255
+
+/**
+ * struct dcb_peer_app_info - APP feature information sent by the peer
+ *
+ * @willing: willing bit in the peer APP tlv
+ * @error: error bit in the peer APP tlv
+ *
+ * In addition to this information the full peer APP tlv also contains
+ * a table of 'app_count' APP objects defined above.
+ */
+struct dcb_peer_app_info {
+ __u8 willing;
+ __u8 error;
+};
+
+struct dcbmsg {
+ __u8 dcb_family;
+ __u8 cmd;
+ __u16 dcb_pad;
+};
+
+/**
+ * enum dcbnl_commands - supported DCB commands
+ *
+ * @DCB_CMD_UNDEFINED: unspecified command to catch errors
+ * @DCB_CMD_GSTATE: request the state of DCB in the device
+ * @DCB_CMD_SSTATE: set the state of DCB in the device
+ * @DCB_CMD_PGTX_GCFG: request the priority group configuration for Tx
+ * @DCB_CMD_PGTX_SCFG: set the priority group configuration for Tx
+ * @DCB_CMD_PGRX_GCFG: request the priority group configuration for Rx
+ * @DCB_CMD_PGRX_SCFG: set the priority group configuration for Rx
+ * @DCB_CMD_PFC_GCFG: request the priority flow control configuration
+ * @DCB_CMD_PFC_SCFG: set the priority flow control configuration
+ * @DCB_CMD_SET_ALL: apply all changes to the underlying device
+ * @DCB_CMD_GPERM_HWADDR: get the permanent MAC address of the underlying
+ * device. Only useful when using bonding.
+ * @DCB_CMD_GCAP: request the DCB capabilities of the device
+ * @DCB_CMD_GNUMTCS: get the number of traffic classes currently supported
+ * @DCB_CMD_SNUMTCS: set the number of traffic classes
+ * @DCB_CMD_GBCN: set backward congestion notification configuration
+ * @DCB_CMD_SBCN: get backward congestion notification configuration.
+ * @DCB_CMD_GAPP: get application protocol configuration
+ * @DCB_CMD_SAPP: set application protocol configuration
+ * @DCB_CMD_IEEE_SET: set IEEE 802.1Qaz configuration
+ * @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration
+ * @DCB_CMD_GDCBX: get DCBX engine configuration
+ * @DCB_CMD_SDCBX: set DCBX engine configuration
+ * @DCB_CMD_GFEATCFG: get DCBX features flags
+ * @DCB_CMD_SFEATCFG: set DCBX features negotiation flags
+ * @DCB_CMD_CEE_GET: get CEE aggregated configuration
+ * @DCB_CMD_IEEE_DEL: delete IEEE 802.1Qaz configuration
+ */
+enum dcbnl_commands {
+ DCB_CMD_UNDEFINED,
+
+ DCB_CMD_GSTATE,
+ DCB_CMD_SSTATE,
+
+ DCB_CMD_PGTX_GCFG,
+ DCB_CMD_PGTX_SCFG,
+ DCB_CMD_PGRX_GCFG,
+ DCB_CMD_PGRX_SCFG,
+
+ DCB_CMD_PFC_GCFG,
+ DCB_CMD_PFC_SCFG,
+
+ DCB_CMD_SET_ALL,
+
+ DCB_CMD_GPERM_HWADDR,
+
+ DCB_CMD_GCAP,
+
+ DCB_CMD_GNUMTCS,
+ DCB_CMD_SNUMTCS,
+
+ DCB_CMD_PFC_GSTATE,
+ DCB_CMD_PFC_SSTATE,
+
+ DCB_CMD_BCN_GCFG,
+ DCB_CMD_BCN_SCFG,
+
+ DCB_CMD_GAPP,
+ DCB_CMD_SAPP,
+
+ DCB_CMD_IEEE_SET,
+ DCB_CMD_IEEE_GET,
+
+ DCB_CMD_GDCBX,
+ DCB_CMD_SDCBX,
+
+ DCB_CMD_GFEATCFG,
+ DCB_CMD_SFEATCFG,
+
+ DCB_CMD_CEE_GET,
+ DCB_CMD_IEEE_DEL,
+
+ __DCB_CMD_ENUM_MAX,
+ DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_attrs - DCB top-level netlink attributes
+ *
+ * @DCB_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_ATTR_IFNAME: interface name of the underlying device (NLA_STRING)
+ * @DCB_ATTR_STATE: enable state of DCB in the device (NLA_U8)
+ * @DCB_ATTR_PFC_STATE: enable state of PFC in the device (NLA_U8)
+ * @DCB_ATTR_PFC_CFG: priority flow control configuration (NLA_NESTED)
+ * @DCB_ATTR_NUM_TC: number of traffic classes supported in the device (NLA_U8)
+ * @DCB_ATTR_PG_CFG: priority group configuration (NLA_NESTED)
+ * @DCB_ATTR_SET_ALL: bool to commit changes to hardware or not (NLA_U8)
+ * @DCB_ATTR_PERM_HWADDR: MAC address of the physical device (NLA_NESTED)
+ * @DCB_ATTR_CAP: DCB capabilities of the device (NLA_NESTED)
+ * @DCB_ATTR_NUMTCS: number of traffic classes supported (NLA_NESTED)
+ * @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED)
+ * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED)
+ * @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8)
+ * @DCB_ATTR_FEATCFG: DCBX features flags (NLA_NESTED)
+ * @DCB_ATTR_CEE: CEE std supported attributes (NLA_NESTED)
+ */
+enum dcbnl_attrs {
+ DCB_ATTR_UNDEFINED,
+
+ DCB_ATTR_IFNAME,
+ DCB_ATTR_STATE,
+ DCB_ATTR_PFC_STATE,
+ DCB_ATTR_PFC_CFG,
+ DCB_ATTR_NUM_TC,
+ DCB_ATTR_PG_CFG,
+ DCB_ATTR_SET_ALL,
+ DCB_ATTR_PERM_HWADDR,
+ DCB_ATTR_CAP,
+ DCB_ATTR_NUMTCS,
+ DCB_ATTR_BCN,
+ DCB_ATTR_APP,
+
+ /* IEEE std attributes */
+ DCB_ATTR_IEEE,
+
+ DCB_ATTR_DCBX,
+ DCB_ATTR_FEATCFG,
+
+ /* CEE nested attributes */
+ DCB_ATTR_CEE,
+
+ __DCB_ATTR_ENUM_MAX,
+ DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum ieee_attrs - IEEE 802.1Qaz get/set attributes
+ *
+ * @DCB_ATTR_IEEE_UNSPEC: unspecified
+ * @DCB_ATTR_IEEE_ETS: negotiated ETS configuration
+ * @DCB_ATTR_IEEE_PFC: negotiated PFC configuration
+ * @DCB_ATTR_IEEE_APP_TABLE: negotiated APP configuration
+ * @DCB_ATTR_IEEE_PEER_ETS: peer ETS configuration - get only
+ * @DCB_ATTR_IEEE_PEER_PFC: peer PFC configuration - get only
+ * @DCB_ATTR_IEEE_PEER_APP: peer APP tlv - get only
+ * @DCB_ATTR_DCB_APP_TRUST_TABLE: selector trust table
+ * @DCB_ATTR_DCB_REWR_TABLE: rewrite configuration
+ */
+enum ieee_attrs {
+ DCB_ATTR_IEEE_UNSPEC,
+ DCB_ATTR_IEEE_ETS,
+ DCB_ATTR_IEEE_PFC,
+ DCB_ATTR_IEEE_APP_TABLE,
+ DCB_ATTR_IEEE_PEER_ETS,
+ DCB_ATTR_IEEE_PEER_PFC,
+ DCB_ATTR_IEEE_PEER_APP,
+ DCB_ATTR_IEEE_MAXRATE,
+ DCB_ATTR_IEEE_QCN,
+ DCB_ATTR_IEEE_QCN_STATS,
+ DCB_ATTR_DCB_BUFFER,
+ DCB_ATTR_DCB_APP_TRUST_TABLE,
+ DCB_ATTR_DCB_REWR_TABLE,
+ __DCB_ATTR_IEEE_MAX
+};
+#define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1)
+
+enum ieee_attrs_app {
+ DCB_ATTR_IEEE_APP_UNSPEC,
+ DCB_ATTR_IEEE_APP,
+ DCB_ATTR_DCB_APP,
+ __DCB_ATTR_IEEE_APP_MAX
+};
+#define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1)
+
+/**
+ * enum cee_attrs - CEE DCBX get attributes.
+ *
+ * @DCB_ATTR_CEE_UNSPEC: unspecified
+ * @DCB_ATTR_CEE_PEER_PG: peer PG configuration - get only
+ * @DCB_ATTR_CEE_PEER_PFC: peer PFC configuration - get only
+ * @DCB_ATTR_CEE_PEER_APP_TABLE: peer APP tlv - get only
+ * @DCB_ATTR_CEE_TX_PG: TX PG configuration (DCB_CMD_PGTX_GCFG)
+ * @DCB_ATTR_CEE_RX_PG: RX PG configuration (DCB_CMD_PGRX_GCFG)
+ * @DCB_ATTR_CEE_PFC: PFC configuration (DCB_CMD_PFC_GCFG)
+ * @DCB_ATTR_CEE_APP_TABLE: APP configuration (multi DCB_CMD_GAPP)
+ * @DCB_ATTR_CEE_FEAT: DCBX features flags (DCB_CMD_GFEATCFG)
+ *
+ * An aggregated collection of the cee std negotiated parameters.
+ */
+enum cee_attrs {
+ DCB_ATTR_CEE_UNSPEC,
+ DCB_ATTR_CEE_PEER_PG,
+ DCB_ATTR_CEE_PEER_PFC,
+ DCB_ATTR_CEE_PEER_APP_TABLE,
+ DCB_ATTR_CEE_TX_PG,
+ DCB_ATTR_CEE_RX_PG,
+ DCB_ATTR_CEE_PFC,
+ DCB_ATTR_CEE_APP_TABLE,
+ DCB_ATTR_CEE_FEAT,
+ __DCB_ATTR_CEE_MAX
+};
+#define DCB_ATTR_CEE_MAX (__DCB_ATTR_CEE_MAX - 1)
+
+enum peer_app_attr {
+ DCB_ATTR_CEE_PEER_APP_UNSPEC,
+ DCB_ATTR_CEE_PEER_APP_INFO,
+ DCB_ATTR_CEE_PEER_APP,
+ __DCB_ATTR_CEE_PEER_APP_MAX
+};
+#define DCB_ATTR_CEE_PEER_APP_MAX (__DCB_ATTR_CEE_PEER_APP_MAX - 1)
+
+enum cee_attrs_app {
+ DCB_ATTR_CEE_APP_UNSPEC,
+ DCB_ATTR_CEE_APP,
+ __DCB_ATTR_CEE_APP_MAX
+};
+#define DCB_ATTR_CEE_APP_MAX (__DCB_ATTR_CEE_APP_MAX - 1)
+
+/**
+ * enum dcbnl_pfc_attrs - DCB Priority Flow Control user priority nested attrs
+ *
+ * @DCB_PFC_UP_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_PFC_UP_ATTR_0: Priority Flow Control value for User Priority 0 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_1: Priority Flow Control value for User Priority 1 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_2: Priority Flow Control value for User Priority 2 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_3: Priority Flow Control value for User Priority 3 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_4: Priority Flow Control value for User Priority 4 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_5: Priority Flow Control value for User Priority 5 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_6: Priority Flow Control value for User Priority 6 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_7: Priority Flow Control value for User Priority 7 (NLA_U8)
+ * @DCB_PFC_UP_ATTR_MAX: highest attribute number currently defined
+ * @DCB_PFC_UP_ATTR_ALL: apply to all priority flow control attrs (NLA_FLAG)
+ *
+ */
+enum dcbnl_pfc_up_attrs {
+ DCB_PFC_UP_ATTR_UNDEFINED,
+
+ DCB_PFC_UP_ATTR_0,
+ DCB_PFC_UP_ATTR_1,
+ DCB_PFC_UP_ATTR_2,
+ DCB_PFC_UP_ATTR_3,
+ DCB_PFC_UP_ATTR_4,
+ DCB_PFC_UP_ATTR_5,
+ DCB_PFC_UP_ATTR_6,
+ DCB_PFC_UP_ATTR_7,
+ DCB_PFC_UP_ATTR_ALL,
+
+ __DCB_PFC_UP_ATTR_ENUM_MAX,
+ DCB_PFC_UP_ATTR_MAX = __DCB_PFC_UP_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_pg_attrs - DCB Priority Group attributes
+ *
+ * @DCB_PG_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_PG_ATTR_TC_0: Priority Group Traffic Class 0 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_1: Priority Group Traffic Class 1 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_2: Priority Group Traffic Class 2 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_3: Priority Group Traffic Class 3 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_4: Priority Group Traffic Class 4 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_5: Priority Group Traffic Class 5 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_6: Priority Group Traffic Class 6 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_7: Priority Group Traffic Class 7 configuration (NLA_NESTED)
+ * @DCB_PG_ATTR_TC_MAX: highest attribute number currently defined
+ * @DCB_PG_ATTR_TC_ALL: apply to all traffic classes (NLA_NESTED)
+ * @DCB_PG_ATTR_BW_ID_0: Percent of link bandwidth for Priority Group 0 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_1: Percent of link bandwidth for Priority Group 1 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_2: Percent of link bandwidth for Priority Group 2 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_3: Percent of link bandwidth for Priority Group 3 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_4: Percent of link bandwidth for Priority Group 4 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_5: Percent of link bandwidth for Priority Group 5 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_6: Percent of link bandwidth for Priority Group 6 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_7: Percent of link bandwidth for Priority Group 7 (NLA_U8)
+ * @DCB_PG_ATTR_BW_ID_MAX: highest attribute number currently defined
+ * @DCB_PG_ATTR_BW_ID_ALL: apply to all priority groups (NLA_FLAG)
+ *
+ */
+enum dcbnl_pg_attrs {
+ DCB_PG_ATTR_UNDEFINED,
+
+ DCB_PG_ATTR_TC_0,
+ DCB_PG_ATTR_TC_1,
+ DCB_PG_ATTR_TC_2,
+ DCB_PG_ATTR_TC_3,
+ DCB_PG_ATTR_TC_4,
+ DCB_PG_ATTR_TC_5,
+ DCB_PG_ATTR_TC_6,
+ DCB_PG_ATTR_TC_7,
+ DCB_PG_ATTR_TC_MAX,
+ DCB_PG_ATTR_TC_ALL,
+
+ DCB_PG_ATTR_BW_ID_0,
+ DCB_PG_ATTR_BW_ID_1,
+ DCB_PG_ATTR_BW_ID_2,
+ DCB_PG_ATTR_BW_ID_3,
+ DCB_PG_ATTR_BW_ID_4,
+ DCB_PG_ATTR_BW_ID_5,
+ DCB_PG_ATTR_BW_ID_6,
+ DCB_PG_ATTR_BW_ID_7,
+ DCB_PG_ATTR_BW_ID_MAX,
+ DCB_PG_ATTR_BW_ID_ALL,
+
+ __DCB_PG_ATTR_ENUM_MAX,
+ DCB_PG_ATTR_MAX = __DCB_PG_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_tc_attrs - DCB Traffic Class attributes
+ *
+ * @DCB_TC_ATTR_PARAM_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_TC_ATTR_PARAM_PGID: (NLA_U8) Priority group the traffic class belongs to
+ * Valid values are: 0-7
+ * @DCB_TC_ATTR_PARAM_UP_MAPPING: (NLA_U8) Traffic class to user priority map
+ * Some devices may not support changing the
+ * user priority map of a TC.
+ * @DCB_TC_ATTR_PARAM_STRICT_PRIO: (NLA_U8) Strict priority setting
+ * 0 - none
+ * 1 - group strict
+ * 2 - link strict
+ * @DCB_TC_ATTR_PARAM_BW_PCT: optional - (NLA_U8) If supported by the device and
+ * not configured to use link strict priority,
+ * this is the percentage of bandwidth of the
+ * priority group this traffic class belongs to
+ * @DCB_TC_ATTR_PARAM_ALL: (NLA_FLAG) all traffic class parameters
+ *
+ */
+enum dcbnl_tc_attrs {
+ DCB_TC_ATTR_PARAM_UNDEFINED,
+
+ DCB_TC_ATTR_PARAM_PGID,
+ DCB_TC_ATTR_PARAM_UP_MAPPING,
+ DCB_TC_ATTR_PARAM_STRICT_PRIO,
+ DCB_TC_ATTR_PARAM_BW_PCT,
+ DCB_TC_ATTR_PARAM_ALL,
+
+ __DCB_TC_ATTR_PARAM_ENUM_MAX,
+ DCB_TC_ATTR_PARAM_MAX = __DCB_TC_ATTR_PARAM_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_cap_attrs - DCB Capability attributes
+ *
+ * @DCB_CAP_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_CAP_ATTR_ALL: (NLA_FLAG) all capability parameters
+ * @DCB_CAP_ATTR_PG: (NLA_U8) device supports Priority Groups
+ * @DCB_CAP_ATTR_PFC: (NLA_U8) device supports Priority Flow Control
+ * @DCB_CAP_ATTR_UP2TC: (NLA_U8) device supports user priority to
+ * traffic class mapping
+ * @DCB_CAP_ATTR_PG_TCS: (NLA_U8) bitmap where each bit represents a
+ * number of traffic classes the device
+ * can be configured to use for Priority Groups
+ * @DCB_CAP_ATTR_PFC_TCS: (NLA_U8) bitmap where each bit represents a
+ * number of traffic classes the device can be
+ * configured to use for Priority Flow Control
+ * @DCB_CAP_ATTR_GSP: (NLA_U8) device supports group strict priority
+ * @DCB_CAP_ATTR_BCN: (NLA_U8) device supports Backwards Congestion
+ * Notification
+ * @DCB_CAP_ATTR_DCBX: (NLA_U8) device supports DCBX engine
+ *
+ */
+enum dcbnl_cap_attrs {
+ DCB_CAP_ATTR_UNDEFINED,
+ DCB_CAP_ATTR_ALL,
+ DCB_CAP_ATTR_PG,
+ DCB_CAP_ATTR_PFC,
+ DCB_CAP_ATTR_UP2TC,
+ DCB_CAP_ATTR_PG_TCS,
+ DCB_CAP_ATTR_PFC_TCS,
+ DCB_CAP_ATTR_GSP,
+ DCB_CAP_ATTR_BCN,
+ DCB_CAP_ATTR_DCBX,
+
+ __DCB_CAP_ATTR_ENUM_MAX,
+ DCB_CAP_ATTR_MAX = __DCB_CAP_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * DCBX capability flags
+ *
+ * @DCB_CAP_DCBX_HOST: DCBX negotiation is performed by the host LLDP agent.
+ * 'set' routines are used to configure the device with
+ * the negotiated parameters
+ *
+ * @DCB_CAP_DCBX_LLD_MANAGED: DCBX negotiation is not performed in the host but
+ * by another entity
+ * 'get' routines are used to retrieve the
+ * negotiated parameters
+ * 'set' routines can be used to set the initial
+ * negotiation configuration
+ *
+ * @DCB_CAP_DCBX_VER_CEE: for a non-host DCBX engine, indicates the engine
+ * supports the CEE protocol flavor
+ *
+ * @DCB_CAP_DCBX_VER_IEEE: for a non-host DCBX engine, indicates the engine
+ * supports the IEEE protocol flavor
+ *
+ * @DCB_CAP_DCBX_STATIC: for a non-host DCBX engine, indicates the engine
+ * supports static configuration (i.e no actual
+ * negotiation is performed negotiated parameters equal
+ * the initial configuration)
+ *
+ */
+#define DCB_CAP_DCBX_HOST 0x01
+#define DCB_CAP_DCBX_LLD_MANAGED 0x02
+#define DCB_CAP_DCBX_VER_CEE 0x04
+#define DCB_CAP_DCBX_VER_IEEE 0x08
+#define DCB_CAP_DCBX_STATIC 0x10
+
+/**
+ * enum dcbnl_numtcs_attrs - number of traffic classes
+ *
+ * @DCB_NUMTCS_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_NUMTCS_ATTR_ALL: (NLA_FLAG) all traffic class attributes
+ * @DCB_NUMTCS_ATTR_PG: (NLA_U8) number of traffic classes used for
+ * priority groups
+ * @DCB_NUMTCS_ATTR_PFC: (NLA_U8) number of traffic classes which can
+ * support priority flow control
+ */
+enum dcbnl_numtcs_attrs {
+ DCB_NUMTCS_ATTR_UNDEFINED,
+ DCB_NUMTCS_ATTR_ALL,
+ DCB_NUMTCS_ATTR_PG,
+ DCB_NUMTCS_ATTR_PFC,
+
+ __DCB_NUMTCS_ATTR_ENUM_MAX,
+ DCB_NUMTCS_ATTR_MAX = __DCB_NUMTCS_ATTR_ENUM_MAX - 1,
+};
+
+enum dcbnl_bcn_attrs{
+ DCB_BCN_ATTR_UNDEFINED = 0,
+
+ DCB_BCN_ATTR_RP_0,
+ DCB_BCN_ATTR_RP_1,
+ DCB_BCN_ATTR_RP_2,
+ DCB_BCN_ATTR_RP_3,
+ DCB_BCN_ATTR_RP_4,
+ DCB_BCN_ATTR_RP_5,
+ DCB_BCN_ATTR_RP_6,
+ DCB_BCN_ATTR_RP_7,
+ DCB_BCN_ATTR_RP_ALL,
+
+ DCB_BCN_ATTR_BCNA_0,
+ DCB_BCN_ATTR_BCNA_1,
+ DCB_BCN_ATTR_ALPHA,
+ DCB_BCN_ATTR_BETA,
+ DCB_BCN_ATTR_GD,
+ DCB_BCN_ATTR_GI,
+ DCB_BCN_ATTR_TMAX,
+ DCB_BCN_ATTR_TD,
+ DCB_BCN_ATTR_RMIN,
+ DCB_BCN_ATTR_W,
+ DCB_BCN_ATTR_RD,
+ DCB_BCN_ATTR_RU,
+ DCB_BCN_ATTR_WRTT,
+ DCB_BCN_ATTR_RI,
+ DCB_BCN_ATTR_C,
+ DCB_BCN_ATTR_ALL,
+
+ __DCB_BCN_ATTR_ENUM_MAX,
+ DCB_BCN_ATTR_MAX = __DCB_BCN_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcb_general_attr_values - general DCB attribute values
+ *
+ * @DCB_ATTR_UNDEFINED: value used to indicate an attribute is not supported
+ *
+ */
+enum dcb_general_attr_values {
+ DCB_ATTR_VALUE_UNDEFINED = 0xff
+};
+
+#define DCB_APP_IDTYPE_ETHTYPE 0x00
+#define DCB_APP_IDTYPE_PORTNUM 0x01
+enum dcbnl_app_attrs {
+ DCB_APP_ATTR_UNDEFINED,
+
+ DCB_APP_ATTR_IDTYPE,
+ DCB_APP_ATTR_ID,
+ DCB_APP_ATTR_PRIORITY,
+
+ __DCB_APP_ATTR_ENUM_MAX,
+ DCB_APP_ATTR_MAX = __DCB_APP_ATTR_ENUM_MAX - 1,
+};
+
+/**
+ * enum dcbnl_featcfg_attrs - features conifiguration flags
+ *
+ * @DCB_FEATCFG_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_FEATCFG_ATTR_ALL: (NLA_FLAG) all features configuration attributes
+ * @DCB_FEATCFG_ATTR_PG: (NLA_U8) configuration flags for priority groups
+ * @DCB_FEATCFG_ATTR_PFC: (NLA_U8) configuration flags for priority
+ * flow control
+ * @DCB_FEATCFG_ATTR_APP: (NLA_U8) configuration flags for application TLV
+ *
+ */
+#define DCB_FEATCFG_ERROR 0x01 /* error in feature resolution */
+#define DCB_FEATCFG_ENABLE 0x02 /* enable feature */
+#define DCB_FEATCFG_WILLING 0x04 /* feature is willing */
+#define DCB_FEATCFG_ADVERTISE 0x08 /* advertise feature */
+enum dcbnl_featcfg_attrs {
+ DCB_FEATCFG_ATTR_UNDEFINED,
+ DCB_FEATCFG_ATTR_ALL,
+ DCB_FEATCFG_ATTR_PG,
+ DCB_FEATCFG_ATTR_PFC,
+ DCB_FEATCFG_ATTR_APP,
+
+ __DCB_FEATCFG_ATTR_ENUM_MAX,
+ DCB_FEATCFG_ATTR_MAX = __DCB_FEATCFG_ATTR_ENUM_MAX - 1,
+};
+
+#endif /* __LINUX_DCBNL_H__ */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
new file mode 100644
index 0000000..e771701
--- /dev/null
+++ b/include/uapi/linux/devlink.h
@@ -0,0 +1,709 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * include/uapi/linux/devlink.h - Network physical device Netlink interface
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _LINUX_DEVLINK_H_
+#define _LINUX_DEVLINK_H_
+
+#include <linux/const.h>
+
+#define DEVLINK_GENL_NAME "devlink"
+#define DEVLINK_GENL_VERSION 0x1
+#define DEVLINK_GENL_MCGRP_CONFIG_NAME "config"
+
+enum devlink_command {
+ /* don't change the order or add anything between, this is ABI! */
+ DEVLINK_CMD_UNSPEC,
+
+ DEVLINK_CMD_GET, /* can dump */
+ DEVLINK_CMD_SET,
+ DEVLINK_CMD_NEW,
+ DEVLINK_CMD_DEL,
+
+ DEVLINK_CMD_PORT_GET, /* can dump */
+ DEVLINK_CMD_PORT_SET,
+ DEVLINK_CMD_PORT_NEW,
+ DEVLINK_CMD_PORT_DEL,
+
+ DEVLINK_CMD_PORT_SPLIT,
+ DEVLINK_CMD_PORT_UNSPLIT,
+
+ DEVLINK_CMD_SB_GET, /* can dump */
+ DEVLINK_CMD_SB_SET,
+ DEVLINK_CMD_SB_NEW,
+ DEVLINK_CMD_SB_DEL,
+
+ DEVLINK_CMD_SB_POOL_GET, /* can dump */
+ DEVLINK_CMD_SB_POOL_SET,
+ DEVLINK_CMD_SB_POOL_NEW,
+ DEVLINK_CMD_SB_POOL_DEL,
+
+ DEVLINK_CMD_SB_PORT_POOL_GET, /* can dump */
+ DEVLINK_CMD_SB_PORT_POOL_SET,
+ DEVLINK_CMD_SB_PORT_POOL_NEW,
+ DEVLINK_CMD_SB_PORT_POOL_DEL,
+
+ DEVLINK_CMD_SB_TC_POOL_BIND_GET, /* can dump */
+ DEVLINK_CMD_SB_TC_POOL_BIND_SET,
+ DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
+ DEVLINK_CMD_SB_TC_POOL_BIND_DEL,
+
+ /* Shared buffer occupancy monitoring commands */
+ DEVLINK_CMD_SB_OCC_SNAPSHOT,
+ DEVLINK_CMD_SB_OCC_MAX_CLEAR,
+
+ DEVLINK_CMD_ESWITCH_GET,
+#define DEVLINK_CMD_ESWITCH_MODE_GET /* obsolete, never use this! */ \
+ DEVLINK_CMD_ESWITCH_GET
+
+ DEVLINK_CMD_ESWITCH_SET,
+#define DEVLINK_CMD_ESWITCH_MODE_SET /* obsolete, never use this! */ \
+ DEVLINK_CMD_ESWITCH_SET
+
+ DEVLINK_CMD_DPIPE_TABLE_GET,
+ DEVLINK_CMD_DPIPE_ENTRIES_GET,
+ DEVLINK_CMD_DPIPE_HEADERS_GET,
+ DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+ DEVLINK_CMD_RESOURCE_SET,
+ DEVLINK_CMD_RESOURCE_DUMP,
+
+ /* Hot driver reload, makes configuration changes take place. The
+ * devlink instance is not released during the process.
+ */
+ DEVLINK_CMD_RELOAD,
+
+ DEVLINK_CMD_PARAM_GET, /* can dump */
+ DEVLINK_CMD_PARAM_SET,
+ DEVLINK_CMD_PARAM_NEW,
+ DEVLINK_CMD_PARAM_DEL,
+
+ DEVLINK_CMD_REGION_GET,
+ DEVLINK_CMD_REGION_SET,
+ DEVLINK_CMD_REGION_NEW,
+ DEVLINK_CMD_REGION_DEL,
+ DEVLINK_CMD_REGION_READ,
+
+ DEVLINK_CMD_PORT_PARAM_GET, /* can dump */
+ DEVLINK_CMD_PORT_PARAM_SET,
+ DEVLINK_CMD_PORT_PARAM_NEW,
+ DEVLINK_CMD_PORT_PARAM_DEL,
+
+ DEVLINK_CMD_INFO_GET, /* can dump */
+
+ DEVLINK_CMD_HEALTH_REPORTER_GET,
+ DEVLINK_CMD_HEALTH_REPORTER_SET,
+ DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+ DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
+ DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
+ DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+
+ DEVLINK_CMD_FLASH_UPDATE,
+ DEVLINK_CMD_FLASH_UPDATE_END, /* notification only */
+ DEVLINK_CMD_FLASH_UPDATE_STATUS, /* notification only */
+
+ DEVLINK_CMD_TRAP_GET, /* can dump */
+ DEVLINK_CMD_TRAP_SET,
+ DEVLINK_CMD_TRAP_NEW,
+ DEVLINK_CMD_TRAP_DEL,
+
+ DEVLINK_CMD_TRAP_GROUP_GET, /* can dump */
+ DEVLINK_CMD_TRAP_GROUP_SET,
+ DEVLINK_CMD_TRAP_GROUP_NEW,
+ DEVLINK_CMD_TRAP_GROUP_DEL,
+
+ DEVLINK_CMD_TRAP_POLICER_GET, /* can dump */
+ DEVLINK_CMD_TRAP_POLICER_SET,
+ DEVLINK_CMD_TRAP_POLICER_NEW,
+ DEVLINK_CMD_TRAP_POLICER_DEL,
+
+ DEVLINK_CMD_HEALTH_REPORTER_TEST,
+
+ DEVLINK_CMD_RATE_GET, /* can dump */
+ DEVLINK_CMD_RATE_SET,
+ DEVLINK_CMD_RATE_NEW,
+ DEVLINK_CMD_RATE_DEL,
+
+ DEVLINK_CMD_LINECARD_GET, /* can dump */
+ DEVLINK_CMD_LINECARD_SET,
+ DEVLINK_CMD_LINECARD_NEW,
+ DEVLINK_CMD_LINECARD_DEL,
+
+ DEVLINK_CMD_SELFTESTS_GET, /* can dump */
+ DEVLINK_CMD_SELFTESTS_RUN,
+
+ DEVLINK_CMD_NOTIFY_FILTER_SET,
+
+ /* add new commands above here */
+ __DEVLINK_CMD_MAX,
+ DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
+};
+
+enum devlink_port_type {
+ DEVLINK_PORT_TYPE_NOTSET,
+ DEVLINK_PORT_TYPE_AUTO,
+ DEVLINK_PORT_TYPE_ETH,
+ DEVLINK_PORT_TYPE_IB,
+};
+
+enum devlink_sb_pool_type {
+ DEVLINK_SB_POOL_TYPE_INGRESS,
+ DEVLINK_SB_POOL_TYPE_EGRESS,
+};
+
+/* static threshold - limiting the maximum number of bytes.
+ * dynamic threshold - limiting the maximum number of bytes
+ * based on the currently available free space in the shared buffer pool.
+ * In this mode, the maximum quota is calculated based
+ * on the following formula:
+ * max_quota = alpha / (1 + alpha) * Free_Buffer
+ * While Free_Buffer is the amount of none-occupied buffer associated to
+ * the relevant pool.
+ * The value range which can be passed is 0-20 and serves
+ * for computation of alpha by following formula:
+ * alpha = 2 ^ (passed_value - 10)
+ */
+
+enum devlink_sb_threshold_type {
+ DEVLINK_SB_THRESHOLD_TYPE_STATIC,
+ DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC,
+};
+
+#define DEVLINK_SB_THRESHOLD_TO_ALPHA_MAX 20
+
+enum devlink_eswitch_mode {
+ DEVLINK_ESWITCH_MODE_LEGACY,
+ DEVLINK_ESWITCH_MODE_SWITCHDEV,
+};
+
+enum devlink_eswitch_inline_mode {
+ DEVLINK_ESWITCH_INLINE_MODE_NONE,
+ DEVLINK_ESWITCH_INLINE_MODE_LINK,
+ DEVLINK_ESWITCH_INLINE_MODE_NETWORK,
+ DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT,
+};
+
+enum devlink_eswitch_encap_mode {
+ DEVLINK_ESWITCH_ENCAP_MODE_NONE,
+ DEVLINK_ESWITCH_ENCAP_MODE_BASIC,
+};
+
+enum devlink_port_flavour {
+ DEVLINK_PORT_FLAVOUR_PHYSICAL, /* Any kind of a port physically
+ * facing the user.
+ */
+ DEVLINK_PORT_FLAVOUR_CPU, /* CPU port */
+ DEVLINK_PORT_FLAVOUR_DSA, /* Distributed switch architecture
+ * interconnect port.
+ */
+ DEVLINK_PORT_FLAVOUR_PCI_PF, /* Represents eswitch port for
+ * the PCI PF. It is an internal
+ * port that faces the PCI PF.
+ */
+ DEVLINK_PORT_FLAVOUR_PCI_VF, /* Represents eswitch port
+ * for the PCI VF. It is an internal
+ * port that faces the PCI VF.
+ */
+ DEVLINK_PORT_FLAVOUR_VIRTUAL, /* Any virtual port facing the user. */
+ DEVLINK_PORT_FLAVOUR_UNUSED, /* Port which exists in the switch, but
+ * is not used in any way.
+ */
+ DEVLINK_PORT_FLAVOUR_PCI_SF, /* Represents eswitch port
+ * for the PCI SF. It is an internal
+ * port that faces the PCI SF.
+ */
+};
+
+enum devlink_rate_type {
+ DEVLINK_RATE_TYPE_LEAF,
+ DEVLINK_RATE_TYPE_NODE,
+};
+
+enum devlink_param_cmode {
+ DEVLINK_PARAM_CMODE_RUNTIME,
+ DEVLINK_PARAM_CMODE_DRIVERINIT,
+ DEVLINK_PARAM_CMODE_PERMANENT,
+
+ /* Add new configuration modes above */
+ __DEVLINK_PARAM_CMODE_MAX,
+ DEVLINK_PARAM_CMODE_MAX = __DEVLINK_PARAM_CMODE_MAX - 1
+};
+
+enum devlink_param_fw_load_policy_value {
+ DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER,
+ DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH,
+ DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DISK,
+ DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_UNKNOWN,
+};
+
+enum devlink_param_reset_dev_on_drv_probe_value {
+ DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_UNKNOWN,
+ DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_ALWAYS,
+ DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_NEVER,
+ DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_DISK,
+};
+
+enum {
+ DEVLINK_ATTR_STATS_RX_PACKETS, /* u64 */
+ DEVLINK_ATTR_STATS_RX_BYTES, /* u64 */
+ DEVLINK_ATTR_STATS_RX_DROPPED, /* u64 */
+
+ __DEVLINK_ATTR_STATS_MAX,
+ DEVLINK_ATTR_STATS_MAX = __DEVLINK_ATTR_STATS_MAX - 1
+};
+
+/* Specify what sections of a flash component can be overwritten when
+ * performing an update. Overwriting of firmware binary sections is always
+ * implicitly assumed to be allowed.
+ *
+ * Each section must be documented in
+ * Documentation/networking/devlink/devlink-flash.rst
+ *
+ */
+enum devlink_flash_overwrite {
+ DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT,
+ DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT,
+
+ __DEVLINK_FLASH_OVERWRITE_MAX_BIT,
+ DEVLINK_FLASH_OVERWRITE_MAX_BIT = __DEVLINK_FLASH_OVERWRITE_MAX_BIT - 1
+};
+
+#define DEVLINK_FLASH_OVERWRITE_SETTINGS _BITUL(DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT)
+#define DEVLINK_FLASH_OVERWRITE_IDENTIFIERS _BITUL(DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT)
+
+#define DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS \
+ (_BITUL(__DEVLINK_FLASH_OVERWRITE_MAX_BIT) - 1)
+
+enum devlink_attr_selftest_id {
+ DEVLINK_ATTR_SELFTEST_ID_UNSPEC,
+ DEVLINK_ATTR_SELFTEST_ID_FLASH, /* flag */
+
+ __DEVLINK_ATTR_SELFTEST_ID_MAX,
+ DEVLINK_ATTR_SELFTEST_ID_MAX = __DEVLINK_ATTR_SELFTEST_ID_MAX - 1
+};
+
+enum devlink_selftest_status {
+ DEVLINK_SELFTEST_STATUS_SKIP,
+ DEVLINK_SELFTEST_STATUS_PASS,
+ DEVLINK_SELFTEST_STATUS_FAIL
+};
+
+enum devlink_attr_selftest_result {
+ DEVLINK_ATTR_SELFTEST_RESULT_UNSPEC,
+ DEVLINK_ATTR_SELFTEST_RESULT, /* nested */
+ DEVLINK_ATTR_SELFTEST_RESULT_ID, /* u32, enum devlink_attr_selftest_id */
+ DEVLINK_ATTR_SELFTEST_RESULT_STATUS, /* u8, enum devlink_selftest_status */
+
+ __DEVLINK_ATTR_SELFTEST_RESULT_MAX,
+ DEVLINK_ATTR_SELFTEST_RESULT_MAX = __DEVLINK_ATTR_SELFTEST_RESULT_MAX - 1
+};
+
+/**
+ * enum devlink_trap_action - Packet trap action.
+ * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not
+ * sent to the CPU.
+ * @DEVLINK_TRAP_ACTION_TRAP: The sole copy of the packet is sent to the CPU.
+ * @DEVLINK_TRAP_ACTION_MIRROR: Packet is forwarded by the device and a copy is
+ * sent to the CPU.
+ */
+enum devlink_trap_action {
+ DEVLINK_TRAP_ACTION_DROP,
+ DEVLINK_TRAP_ACTION_TRAP,
+ DEVLINK_TRAP_ACTION_MIRROR,
+};
+
+/**
+ * enum devlink_trap_type - Packet trap type.
+ * @DEVLINK_TRAP_TYPE_DROP: Trap reason is a drop. Trapped packets are only
+ * processed by devlink and not injected to the
+ * kernel's Rx path.
+ * @DEVLINK_TRAP_TYPE_EXCEPTION: Trap reason is an exception. Packet was not
+ * forwarded as intended due to an exception
+ * (e.g., missing neighbour entry) and trapped to
+ * control plane for resolution. Trapped packets
+ * are processed by devlink and injected to
+ * the kernel's Rx path.
+ * @DEVLINK_TRAP_TYPE_CONTROL: Packet was trapped because it is required for
+ * the correct functioning of the control plane.
+ * For example, an ARP request packet. Trapped
+ * packets are injected to the kernel's Rx path,
+ * but not reported to drop monitor.
+ */
+enum devlink_trap_type {
+ DEVLINK_TRAP_TYPE_DROP,
+ DEVLINK_TRAP_TYPE_EXCEPTION,
+ DEVLINK_TRAP_TYPE_CONTROL,
+};
+
+enum {
+ /* Trap can report input port as metadata */
+ DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT,
+ /* Trap can report flow action cookie as metadata */
+ DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE,
+};
+
+enum devlink_reload_action {
+ DEVLINK_RELOAD_ACTION_UNSPEC,
+ DEVLINK_RELOAD_ACTION_DRIVER_REINIT, /* Driver entities re-instantiation */
+ DEVLINK_RELOAD_ACTION_FW_ACTIVATE, /* FW activate */
+
+ /* Add new reload actions above */
+ __DEVLINK_RELOAD_ACTION_MAX,
+ DEVLINK_RELOAD_ACTION_MAX = __DEVLINK_RELOAD_ACTION_MAX - 1
+};
+
+enum devlink_reload_limit {
+ DEVLINK_RELOAD_LIMIT_UNSPEC, /* unspecified, no constraints */
+ DEVLINK_RELOAD_LIMIT_NO_RESET, /* No reset allowed, no down time allowed,
+ * no link flap and no configuration is lost.
+ */
+
+ /* Add new reload limit above */
+ __DEVLINK_RELOAD_LIMIT_MAX,
+ DEVLINK_RELOAD_LIMIT_MAX = __DEVLINK_RELOAD_LIMIT_MAX - 1
+};
+
+#define DEVLINK_RELOAD_LIMITS_VALID_MASK (_BITUL(__DEVLINK_RELOAD_LIMIT_MAX) - 1)
+
+enum devlink_linecard_state {
+ DEVLINK_LINECARD_STATE_UNSPEC,
+ DEVLINK_LINECARD_STATE_UNPROVISIONED,
+ DEVLINK_LINECARD_STATE_UNPROVISIONING,
+ DEVLINK_LINECARD_STATE_PROVISIONING,
+ DEVLINK_LINECARD_STATE_PROVISIONING_FAILED,
+ DEVLINK_LINECARD_STATE_PROVISIONED,
+ DEVLINK_LINECARD_STATE_ACTIVE,
+
+ __DEVLINK_LINECARD_STATE_MAX,
+ DEVLINK_LINECARD_STATE_MAX = __DEVLINK_LINECARD_STATE_MAX - 1
+};
+
+enum devlink_attr {
+ /* don't change the order or add anything between, this is ABI! */
+ DEVLINK_ATTR_UNSPEC,
+
+ /* bus name + dev name together are a handle for devlink entity */
+ DEVLINK_ATTR_BUS_NAME, /* string */
+ DEVLINK_ATTR_DEV_NAME, /* string */
+
+ DEVLINK_ATTR_PORT_INDEX, /* u32 */
+ DEVLINK_ATTR_PORT_TYPE, /* u16 */
+ DEVLINK_ATTR_PORT_DESIRED_TYPE, /* u16 */
+ DEVLINK_ATTR_PORT_NETDEV_IFINDEX, /* u32 */
+ DEVLINK_ATTR_PORT_NETDEV_NAME, /* string */
+ DEVLINK_ATTR_PORT_IBDEV_NAME, /* string */
+ DEVLINK_ATTR_PORT_SPLIT_COUNT, /* u32 */
+ DEVLINK_ATTR_PORT_SPLIT_GROUP, /* u32 */
+ DEVLINK_ATTR_SB_INDEX, /* u32 */
+ DEVLINK_ATTR_SB_SIZE, /* u32 */
+ DEVLINK_ATTR_SB_INGRESS_POOL_COUNT, /* u16 */
+ DEVLINK_ATTR_SB_EGRESS_POOL_COUNT, /* u16 */
+ DEVLINK_ATTR_SB_INGRESS_TC_COUNT, /* u16 */
+ DEVLINK_ATTR_SB_EGRESS_TC_COUNT, /* u16 */
+ DEVLINK_ATTR_SB_POOL_INDEX, /* u16 */
+ DEVLINK_ATTR_SB_POOL_TYPE, /* u8 */
+ DEVLINK_ATTR_SB_POOL_SIZE, /* u32 */
+ DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, /* u8 */
+ DEVLINK_ATTR_SB_THRESHOLD, /* u32 */
+ DEVLINK_ATTR_SB_TC_INDEX, /* u16 */
+ DEVLINK_ATTR_SB_OCC_CUR, /* u32 */
+ DEVLINK_ATTR_SB_OCC_MAX, /* u32 */
+ DEVLINK_ATTR_ESWITCH_MODE, /* u16 */
+ DEVLINK_ATTR_ESWITCH_INLINE_MODE, /* u8 */
+
+ DEVLINK_ATTR_DPIPE_TABLES, /* nested */
+ DEVLINK_ATTR_DPIPE_TABLE, /* nested */
+ DEVLINK_ATTR_DPIPE_TABLE_NAME, /* string */
+ DEVLINK_ATTR_DPIPE_TABLE_SIZE, /* u64 */
+ DEVLINK_ATTR_DPIPE_TABLE_MATCHES, /* nested */
+ DEVLINK_ATTR_DPIPE_TABLE_ACTIONS, /* nested */
+ DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, /* u8 */
+
+ DEVLINK_ATTR_DPIPE_ENTRIES, /* nested */
+ DEVLINK_ATTR_DPIPE_ENTRY, /* nested */
+ DEVLINK_ATTR_DPIPE_ENTRY_INDEX, /* u64 */
+ DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES, /* nested */
+ DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES, /* nested */
+ DEVLINK_ATTR_DPIPE_ENTRY_COUNTER, /* u64 */
+
+ DEVLINK_ATTR_DPIPE_MATCH, /* nested */
+ DEVLINK_ATTR_DPIPE_MATCH_VALUE, /* nested */
+ DEVLINK_ATTR_DPIPE_MATCH_TYPE, /* u32 */
+
+ DEVLINK_ATTR_DPIPE_ACTION, /* nested */
+ DEVLINK_ATTR_DPIPE_ACTION_VALUE, /* nested */
+ DEVLINK_ATTR_DPIPE_ACTION_TYPE, /* u32 */
+
+ DEVLINK_ATTR_DPIPE_VALUE,
+ DEVLINK_ATTR_DPIPE_VALUE_MASK,
+ DEVLINK_ATTR_DPIPE_VALUE_MAPPING, /* u32 */
+
+ DEVLINK_ATTR_DPIPE_HEADERS, /* nested */
+ DEVLINK_ATTR_DPIPE_HEADER, /* nested */
+ DEVLINK_ATTR_DPIPE_HEADER_NAME, /* string */
+ DEVLINK_ATTR_DPIPE_HEADER_ID, /* u32 */
+ DEVLINK_ATTR_DPIPE_HEADER_FIELDS, /* nested */
+ DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, /* u8 */
+ DEVLINK_ATTR_DPIPE_HEADER_INDEX, /* u32 */
+
+ DEVLINK_ATTR_DPIPE_FIELD, /* nested */
+ DEVLINK_ATTR_DPIPE_FIELD_NAME, /* string */
+ DEVLINK_ATTR_DPIPE_FIELD_ID, /* u32 */
+ DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, /* u32 */
+ DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, /* u32 */
+
+ DEVLINK_ATTR_PAD,
+
+ DEVLINK_ATTR_ESWITCH_ENCAP_MODE, /* u8 */
+ DEVLINK_ATTR_RESOURCE_LIST, /* nested */
+ DEVLINK_ATTR_RESOURCE, /* nested */
+ DEVLINK_ATTR_RESOURCE_NAME, /* string */
+ DEVLINK_ATTR_RESOURCE_ID, /* u64 */
+ DEVLINK_ATTR_RESOURCE_SIZE, /* u64 */
+ DEVLINK_ATTR_RESOURCE_SIZE_NEW, /* u64 */
+ DEVLINK_ATTR_RESOURCE_SIZE_VALID, /* u8 */
+ DEVLINK_ATTR_RESOURCE_SIZE_MIN, /* u64 */
+ DEVLINK_ATTR_RESOURCE_SIZE_MAX, /* u64 */
+ DEVLINK_ATTR_RESOURCE_SIZE_GRAN, /* u64 */
+ DEVLINK_ATTR_RESOURCE_UNIT, /* u8 */
+ DEVLINK_ATTR_RESOURCE_OCC, /* u64 */
+ DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, /* u64 */
+ DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS,/* u64 */
+
+ DEVLINK_ATTR_PORT_FLAVOUR, /* u16 */
+ DEVLINK_ATTR_PORT_NUMBER, /* u32 */
+ DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, /* u32 */
+
+ DEVLINK_ATTR_PARAM, /* nested */
+ DEVLINK_ATTR_PARAM_NAME, /* string */
+ DEVLINK_ATTR_PARAM_GENERIC, /* flag */
+ DEVLINK_ATTR_PARAM_TYPE, /* u8 */
+ DEVLINK_ATTR_PARAM_VALUES_LIST, /* nested */
+ DEVLINK_ATTR_PARAM_VALUE, /* nested */
+ DEVLINK_ATTR_PARAM_VALUE_DATA, /* dynamic */
+ DEVLINK_ATTR_PARAM_VALUE_CMODE, /* u8 */
+
+ DEVLINK_ATTR_REGION_NAME, /* string */
+ DEVLINK_ATTR_REGION_SIZE, /* u64 */
+ DEVLINK_ATTR_REGION_SNAPSHOTS, /* nested */
+ DEVLINK_ATTR_REGION_SNAPSHOT, /* nested */
+ DEVLINK_ATTR_REGION_SNAPSHOT_ID, /* u32 */
+
+ DEVLINK_ATTR_REGION_CHUNKS, /* nested */
+ DEVLINK_ATTR_REGION_CHUNK, /* nested */
+ DEVLINK_ATTR_REGION_CHUNK_DATA, /* binary */
+ DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */
+ DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */
+
+ DEVLINK_ATTR_INFO_DRIVER_NAME, /* string */
+ DEVLINK_ATTR_INFO_SERIAL_NUMBER, /* string */
+ DEVLINK_ATTR_INFO_VERSION_FIXED, /* nested */
+ DEVLINK_ATTR_INFO_VERSION_RUNNING, /* nested */
+ DEVLINK_ATTR_INFO_VERSION_STORED, /* nested */
+ DEVLINK_ATTR_INFO_VERSION_NAME, /* string */
+ DEVLINK_ATTR_INFO_VERSION_VALUE, /* string */
+
+ DEVLINK_ATTR_SB_POOL_CELL_SIZE, /* u32 */
+
+ DEVLINK_ATTR_FMSG, /* nested */
+ DEVLINK_ATTR_FMSG_OBJ_NEST_START, /* flag */
+ DEVLINK_ATTR_FMSG_PAIR_NEST_START, /* flag */
+ DEVLINK_ATTR_FMSG_ARR_NEST_START, /* flag */
+ DEVLINK_ATTR_FMSG_NEST_END, /* flag */
+ DEVLINK_ATTR_FMSG_OBJ_NAME, /* string */
+ DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE, /* u8 */
+ DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA, /* dynamic */
+
+ DEVLINK_ATTR_HEALTH_REPORTER, /* nested */
+ DEVLINK_ATTR_HEALTH_REPORTER_NAME, /* string */
+ DEVLINK_ATTR_HEALTH_REPORTER_STATE, /* u8 */
+ DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT, /* u64 */
+ DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT, /* u64 */
+ DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, /* u64 */
+ DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, /* u64 */
+ DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, /* u8 */
+
+ DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME, /* string */
+ DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, /* string */
+ DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, /* string */
+ DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, /* u64 */
+ DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, /* u64 */
+
+ DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u16 */
+ DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u16 */
+
+ DEVLINK_ATTR_STATS, /* nested */
+
+ DEVLINK_ATTR_TRAP_NAME, /* string */
+ /* enum devlink_trap_action */
+ DEVLINK_ATTR_TRAP_ACTION, /* u8 */
+ /* enum devlink_trap_type */
+ DEVLINK_ATTR_TRAP_TYPE, /* u8 */
+ DEVLINK_ATTR_TRAP_GENERIC, /* flag */
+ DEVLINK_ATTR_TRAP_METADATA, /* nested */
+ DEVLINK_ATTR_TRAP_GROUP_NAME, /* string */
+
+ DEVLINK_ATTR_RELOAD_FAILED, /* u8 0 or 1 */
+
+ DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, /* u64 */
+
+ DEVLINK_ATTR_NETNS_FD, /* u32 */
+ DEVLINK_ATTR_NETNS_PID, /* u32 */
+ DEVLINK_ATTR_NETNS_ID, /* u32 */
+
+ DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, /* u8 */
+
+ DEVLINK_ATTR_TRAP_POLICER_ID, /* u32 */
+ DEVLINK_ATTR_TRAP_POLICER_RATE, /* u64 */
+ DEVLINK_ATTR_TRAP_POLICER_BURST, /* u64 */
+
+ DEVLINK_ATTR_PORT_FUNCTION, /* nested */
+
+ DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, /* string */
+
+ DEVLINK_ATTR_PORT_LANES, /* u32 */
+ DEVLINK_ATTR_PORT_SPLITTABLE, /* u8 */
+
+ DEVLINK_ATTR_PORT_EXTERNAL, /* u8 */
+ DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, /* u32 */
+
+ DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, /* u64 */
+ DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK, /* bitfield32 */
+
+ DEVLINK_ATTR_RELOAD_ACTION, /* u8 */
+ DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, /* bitfield32 */
+ DEVLINK_ATTR_RELOAD_LIMITS, /* bitfield32 */
+
+ DEVLINK_ATTR_DEV_STATS, /* nested */
+ DEVLINK_ATTR_RELOAD_STATS, /* nested */
+ DEVLINK_ATTR_RELOAD_STATS_ENTRY, /* nested */
+ DEVLINK_ATTR_RELOAD_STATS_LIMIT, /* u8 */
+ DEVLINK_ATTR_RELOAD_STATS_VALUE, /* u32 */
+ DEVLINK_ATTR_REMOTE_RELOAD_STATS, /* nested */
+ DEVLINK_ATTR_RELOAD_ACTION_INFO, /* nested */
+ DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */
+
+ DEVLINK_ATTR_PORT_PCI_SF_NUMBER, /* u32 */
+
+ DEVLINK_ATTR_RATE_TYPE, /* u16 */
+ DEVLINK_ATTR_RATE_TX_SHARE, /* u64 */
+ DEVLINK_ATTR_RATE_TX_MAX, /* u64 */
+ DEVLINK_ATTR_RATE_NODE_NAME, /* string */
+ DEVLINK_ATTR_RATE_PARENT_NODE_NAME, /* string */
+
+ DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, /* u32 */
+
+ DEVLINK_ATTR_LINECARD_INDEX, /* u32 */
+ DEVLINK_ATTR_LINECARD_STATE, /* u8 */
+ DEVLINK_ATTR_LINECARD_TYPE, /* string */
+ DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES, /* nested */
+
+ DEVLINK_ATTR_NESTED_DEVLINK, /* nested */
+
+ DEVLINK_ATTR_SELFTESTS, /* nested */
+
+ DEVLINK_ATTR_RATE_TX_PRIORITY, /* u32 */
+ DEVLINK_ATTR_RATE_TX_WEIGHT, /* u32 */
+
+ DEVLINK_ATTR_REGION_DIRECT, /* flag */
+
+ /* add new attributes above here, update the policy in devlink.c */
+
+ __DEVLINK_ATTR_MAX,
+ DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1
+};
+
+/* Mapping between internal resource described by the field and system
+ * structure
+ */
+enum devlink_dpipe_field_mapping_type {
+ DEVLINK_DPIPE_FIELD_MAPPING_TYPE_NONE,
+ DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX,
+};
+
+/* Match type - specify the type of the match */
+enum devlink_dpipe_match_type {
+ DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT,
+};
+
+/* Action type - specify the action type */
+enum devlink_dpipe_action_type {
+ DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY,
+};
+
+enum devlink_dpipe_field_ethernet_id {
+ DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC,
+};
+
+enum devlink_dpipe_field_ipv4_id {
+ DEVLINK_DPIPE_FIELD_IPV4_DST_IP,
+};
+
+enum devlink_dpipe_field_ipv6_id {
+ DEVLINK_DPIPE_FIELD_IPV6_DST_IP,
+};
+
+enum devlink_dpipe_header_id {
+ DEVLINK_DPIPE_HEADER_ETHERNET,
+ DEVLINK_DPIPE_HEADER_IPV4,
+ DEVLINK_DPIPE_HEADER_IPV6,
+};
+
+enum devlink_resource_unit {
+ DEVLINK_RESOURCE_UNIT_ENTRY,
+};
+
+enum devlink_port_fn_attr_cap {
+ DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT,
+ DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT,
+ DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT,
+ DEVLINK_PORT_FN_ATTR_CAP_IPSEC_PACKET_BIT,
+
+ /* Add new caps above */
+ __DEVLINK_PORT_FN_ATTR_CAPS_MAX,
+};
+
+#define DEVLINK_PORT_FN_CAP_ROCE _BITUL(DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT)
+#define DEVLINK_PORT_FN_CAP_MIGRATABLE \
+ _BITUL(DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT)
+#define DEVLINK_PORT_FN_CAP_IPSEC_CRYPTO _BITUL(DEVLINK_PORT_FN_ATTR_CAP_IPSEC_CRYPTO_BIT)
+#define DEVLINK_PORT_FN_CAP_IPSEC_PACKET _BITUL(DEVLINK_PORT_FN_ATTR_CAP_IPSEC_PACKET_BIT)
+
+enum devlink_port_function_attr {
+ DEVLINK_PORT_FUNCTION_ATTR_UNSPEC,
+ DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, /* binary */
+ DEVLINK_PORT_FN_ATTR_STATE, /* u8 */
+ DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */
+ DEVLINK_PORT_FN_ATTR_CAPS, /* bitfield32 */
+ DEVLINK_PORT_FN_ATTR_DEVLINK, /* nested */
+
+ __DEVLINK_PORT_FUNCTION_ATTR_MAX,
+ DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1
+};
+
+enum devlink_port_fn_state {
+ DEVLINK_PORT_FN_STATE_INACTIVE,
+ DEVLINK_PORT_FN_STATE_ACTIVE,
+};
+
+/**
+ * enum devlink_port_fn_opstate - indicates operational state of the function
+ * @DEVLINK_PORT_FN_OPSTATE_ATTACHED: Driver is attached to the function.
+ * For graceful tear down of the function, after inactivation of the
+ * function, user should wait for operational state to turn DETACHED.
+ * @DEVLINK_PORT_FN_OPSTATE_DETACHED: Driver is detached from the function.
+ * It is safe to delete the port.
+ */
+enum devlink_port_fn_opstate {
+ DEVLINK_PORT_FN_OPSTATE_DETACHED,
+ DEVLINK_PORT_FN_OPSTATE_ATTACHED,
+};
+
+#endif /* _LINUX_DEVLINK_H_ */
diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h
new file mode 100644
index 0000000..ef38c2b
--- /dev/null
+++ b/include/uapi/linux/elf-em.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_ELF_EM_H
+#define _LINUX_ELF_EM_H
+
+/* These constants define the various ELF target machines */
+#define EM_NONE 0
+#define EM_M32 1
+#define EM_SPARC 2
+#define EM_386 3
+#define EM_68K 4
+#define EM_88K 5
+#define EM_486 6 /* Perhaps disused */
+#define EM_860 7
+#define EM_MIPS 8 /* MIPS R3000 (officially, big-endian only) */
+ /* Next two are historical and binaries and
+ modules of these types will be rejected by
+ Linux. */
+#define EM_MIPS_RS3_LE 10 /* MIPS R3000 little-endian */
+#define EM_MIPS_RS4_BE 10 /* MIPS R4000 big-endian */
+
+#define EM_PARISC 15 /* HPPA */
+#define EM_SPARC32PLUS 18 /* Sun's "v8plus" */
+#define EM_PPC 20 /* PowerPC */
+#define EM_PPC64 21 /* PowerPC64 */
+#define EM_SPU 23 /* Cell BE SPU */
+#define EM_ARM 40 /* ARM 32 bit */
+#define EM_SH 42 /* SuperH */
+#define EM_SPARCV9 43 /* SPARC v9 64-bit */
+#define EM_H8_300 46 /* Renesas H8/300 */
+#define EM_IA_64 50 /* HP/Intel IA-64 */
+#define EM_X86_64 62 /* AMD x86-64 */
+#define EM_S390 22 /* IBM S/390 */
+#define EM_CRIS 76 /* Axis Communications 32-bit embedded processor */
+#define EM_M32R 88 /* Renesas M32R */
+#define EM_MN10300 89 /* Panasonic/MEI MN10300, AM33 */
+#define EM_OPENRISC 92 /* OpenRISC 32-bit embedded processor */
+#define EM_ARCOMPACT 93 /* ARCompact processor */
+#define EM_XTENSA 94 /* Tensilica Xtensa Architecture */
+#define EM_BLACKFIN 106 /* ADI Blackfin Processor */
+#define EM_UNICORE 110 /* UniCore-32 */
+#define EM_ALTERA_NIOS2 113 /* Altera Nios II soft-core processor */
+#define EM_TI_C6000 140 /* TI C6X DSPs */
+#define EM_HEXAGON 164 /* QUALCOMM Hexagon */
+#define EM_NDS32 167 /* Andes Technology compact code size
+ embedded RISC processor family */
+#define EM_AARCH64 183 /* ARM 64 bit */
+#define EM_TILEPRO 188 /* Tilera TILEPro */
+#define EM_MICROBLAZE 189 /* Xilinx MicroBlaze */
+#define EM_TILEGX 191 /* Tilera TILE-Gx */
+#define EM_ARCV2 195 /* ARCv2 Cores */
+#define EM_RISCV 243 /* RISC-V */
+#define EM_BPF 247 /* Linux BPF - in-kernel virtual machine */
+#define EM_CSKY 252 /* C-SKY */
+#define EM_LOONGARCH 258 /* LoongArch */
+#define EM_FRV 0x5441 /* Fujitsu FR-V */
+
+/*
+ * This is an interim value that we will use until the committee comes
+ * up with a final number.
+ */
+#define EM_ALPHA 0x9026
+
+/* Bogus old m32r magic number, used by old tools. */
+#define EM_CYGNUS_M32R 0x9041
+/* This is the old interim value for S/390 architecture */
+#define EM_S390_OLD 0xA390
+/* Also Panasonic/MEI MN10300, AM33 */
+#define EM_CYGNUS_MN10300 0xbeef
+
+
+#endif /* _LINUX_ELF_EM_H */
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
new file mode 100644
index 0000000..232df14
--- /dev/null
+++ b/include/uapi/linux/fib_rules.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_FIB_RULES_H
+#define __LINUX_FIB_RULES_H
+
+#include <linux/types.h>
+#include <linux/rtnetlink.h>
+
+/* rule is permanent, and cannot be deleted */
+#define FIB_RULE_PERMANENT 0x00000001
+#define FIB_RULE_INVERT 0x00000002
+#define FIB_RULE_UNRESOLVED 0x00000004
+#define FIB_RULE_IIF_DETACHED 0x00000008
+#define FIB_RULE_DEV_DETACHED FIB_RULE_IIF_DETACHED
+#define FIB_RULE_OIF_DETACHED 0x00000010
+
+/* try to find source address in routing lookups */
+#define FIB_RULE_FIND_SADDR 0x00010000
+
+struct fib_rule_hdr {
+ __u8 family;
+ __u8 dst_len;
+ __u8 src_len;
+ __u8 tos;
+
+ __u8 table;
+ __u8 res1; /* reserved */
+ __u8 res2; /* reserved */
+ __u8 action;
+
+ __u32 flags;
+};
+
+struct fib_rule_uid_range {
+ __u32 start;
+ __u32 end;
+};
+
+struct fib_rule_port_range {
+ __u16 start;
+ __u16 end;
+};
+
+enum {
+ FRA_UNSPEC,
+ FRA_DST, /* destination address */
+ FRA_SRC, /* source address */
+ FRA_IIFNAME, /* interface name */
+#define FRA_IFNAME FRA_IIFNAME
+ FRA_GOTO, /* target to jump to (FR_ACT_GOTO) */
+ FRA_UNUSED2,
+ FRA_PRIORITY, /* priority/preference */
+ FRA_UNUSED3,
+ FRA_UNUSED4,
+ FRA_UNUSED5,
+ FRA_FWMARK, /* mark */
+ FRA_FLOW, /* flow/class id */
+ FRA_TUN_ID,
+ FRA_SUPPRESS_IFGROUP,
+ FRA_SUPPRESS_PREFIXLEN,
+ FRA_TABLE, /* Extended table id */
+ FRA_FWMASK, /* mask for netfilter mark */
+ FRA_OIFNAME,
+ FRA_PAD,
+ FRA_L3MDEV, /* iif or oif is l3mdev goto its table */
+ FRA_UID_RANGE, /* UID range */
+ FRA_PROTOCOL, /* Originator of the rule */
+ FRA_IP_PROTO, /* ip proto */
+ FRA_SPORT_RANGE, /* sport */
+ FRA_DPORT_RANGE, /* dport */
+ __FRA_MAX
+};
+
+#define FRA_MAX (__FRA_MAX - 1)
+
+enum {
+ FR_ACT_UNSPEC,
+ FR_ACT_TO_TBL, /* Pass to fixed table */
+ FR_ACT_GOTO, /* Jump to another rule */
+ FR_ACT_NOP, /* No operation */
+ FR_ACT_RES3,
+ FR_ACT_RES4,
+ FR_ACT_BLACKHOLE, /* Drop without notification */
+ FR_ACT_UNREACHABLE, /* Drop with ENETUNREACH */
+ FR_ACT_PROHIBIT, /* Drop with EACCES */
+ __FR_ACT_MAX,
+};
+
+#define FR_ACT_MAX (__FR_ACT_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h
new file mode 100644
index 0000000..eaef459
--- /dev/null
+++ b/include/uapi/linux/filter.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Linux Socket Filter Data Structures
+ */
+
+#ifndef __LINUX_FILTER_H__
+#define __LINUX_FILTER_H__
+
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/*
+ * Current version of the filter code architecture.
+ */
+#define BPF_MAJOR_VERSION 1
+#define BPF_MINOR_VERSION 1
+
+/*
+ * Try and keep these values and structures similar to BSD, especially
+ * the BPF code definitions which need to match so you can share filters
+ */
+
+struct sock_filter { /* Filter block */
+ __u16 code; /* Actual filter code */
+ __u8 jt; /* Jump true */
+ __u8 jf; /* Jump false */
+ __u32 k; /* Generic multiuse field */
+};
+
+struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
+ unsigned short len; /* Number of filter blocks */
+ struct sock_filter *filter;
+};
+
+/* ret - BPF_K and BPF_X also apply */
+#define BPF_RVAL(code) ((code) & 0x18)
+#define BPF_A 0x10
+
+/* misc */
+#define BPF_MISCOP(code) ((code) & 0xf8)
+#define BPF_TAX 0x00
+#define BPF_TXA 0x80
+
+/*
+ * Macros for filter block array initializers.
+ */
+#ifndef BPF_STMT
+#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k }
+#endif
+#ifndef BPF_JUMP
+#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k }
+#endif
+
+/*
+ * Number of scratch memory words for: BPF_ST and BPF_STX
+ */
+#define BPF_MEMWORDS 16
+
+/* RATIONALE. Negative offsets are invalid in BPF.
+ We use them to reference ancillary data.
+ Unlike introduction new instructions, it does not break
+ existing compilers/optimizers.
+ */
+#define SKF_AD_OFF (-0x1000)
+#define SKF_AD_PROTOCOL 0
+#define SKF_AD_PKTTYPE 4
+#define SKF_AD_IFINDEX 8
+#define SKF_AD_NLATTR 12
+#define SKF_AD_NLATTR_NEST 16
+#define SKF_AD_MARK 20
+#define SKF_AD_QUEUE 24
+#define SKF_AD_HATYPE 28
+#define SKF_AD_RXHASH 32
+#define SKF_AD_CPU 36
+#define SKF_AD_ALU_XOR_X 40
+#define SKF_AD_VLAN_TAG 44
+#define SKF_AD_VLAN_TAG_PRESENT 48
+#define SKF_AD_PAY_OFFSET 52
+#define SKF_AD_RANDOM 56
+#define SKF_AD_VLAN_TPID 60
+#define SKF_AD_MAX 64
+
+#define SKF_NET_OFF (-0x100000)
+#define SKF_LL_OFF (-0x200000)
+
+#define BPF_NET_OFF SKF_NET_OFF
+#define BPF_LL_OFF SKF_LL_OFF
+
+#endif /* __LINUX_FILTER_H__ */
diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h
new file mode 100644
index 0000000..1c2b680
--- /dev/null
+++ b/include/uapi/linux/fou.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/fou.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _LINUX_FOU_H
+#define _LINUX_FOU_H
+
+#define FOU_GENL_NAME "fou"
+#define FOU_GENL_VERSION 1
+
+enum {
+ FOU_ENCAP_UNSPEC,
+ FOU_ENCAP_DIRECT,
+ FOU_ENCAP_GUE,
+};
+
+enum {
+ FOU_ATTR_UNSPEC,
+ FOU_ATTR_PORT,
+ FOU_ATTR_AF,
+ FOU_ATTR_IPPROTO,
+ FOU_ATTR_TYPE,
+ FOU_ATTR_REMCSUM_NOPARTIAL,
+ FOU_ATTR_LOCAL_V4,
+ FOU_ATTR_LOCAL_V6,
+ FOU_ATTR_PEER_V4,
+ FOU_ATTR_PEER_V6,
+ FOU_ATTR_PEER_PORT,
+ FOU_ATTR_IFINDEX,
+
+ __FOU_ATTR_MAX
+};
+#define FOU_ATTR_MAX (__FOU_ATTR_MAX - 1)
+
+enum {
+ FOU_CMD_UNSPEC,
+ FOU_CMD_ADD,
+ FOU_CMD_DEL,
+ FOU_CMD_GET,
+
+ __FOU_CMD_MAX
+};
+#define FOU_CMD_MAX (__FOU_CMD_MAX - 1)
+
+#endif /* _LINUX_FOU_H */
diff --git a/include/uapi/linux/gen_stats.h b/include/uapi/linux/gen_stats.h
new file mode 100644
index 0000000..852f234
--- /dev/null
+++ b/include/uapi/linux/gen_stats.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_GEN_STATS_H
+#define __LINUX_GEN_STATS_H
+
+#include <linux/types.h>
+
+enum {
+ TCA_STATS_UNSPEC,
+ TCA_STATS_BASIC,
+ TCA_STATS_RATE_EST,
+ TCA_STATS_QUEUE,
+ TCA_STATS_APP,
+ TCA_STATS_RATE_EST64,
+ TCA_STATS_PAD,
+ TCA_STATS_BASIC_HW,
+ TCA_STATS_PKT64,
+ __TCA_STATS_MAX,
+};
+#define TCA_STATS_MAX (__TCA_STATS_MAX - 1)
+
+/**
+ * struct gnet_stats_basic - byte/packet throughput statistics
+ * @bytes: number of seen bytes
+ * @packets: number of seen packets
+ */
+struct gnet_stats_basic {
+ __u64 bytes;
+ __u32 packets;
+};
+
+/**
+ * struct gnet_stats_rate_est - rate estimator
+ * @bps: current byte rate
+ * @pps: current packet rate
+ */
+struct gnet_stats_rate_est {
+ __u32 bps;
+ __u32 pps;
+};
+
+/**
+ * struct gnet_stats_rate_est64 - rate estimator
+ * @bps: current byte rate
+ * @pps: current packet rate
+ */
+struct gnet_stats_rate_est64 {
+ __u64 bps;
+ __u64 pps;
+};
+
+/**
+ * struct gnet_stats_queue - queuing statistics
+ * @qlen: queue length
+ * @backlog: backlog size of queue
+ * @drops: number of dropped packets
+ * @requeues: number of requeues
+ * @overlimits: number of enqueues over the limit
+ */
+struct gnet_stats_queue {
+ __u32 qlen;
+ __u32 backlog;
+ __u32 drops;
+ __u32 requeues;
+ __u32 overlimits;
+};
+
+/**
+ * struct gnet_estimator - rate estimator configuration
+ * @interval: sampling period
+ * @ewma_log: the log of measurement window weight
+ */
+struct gnet_estimator {
+ signed char interval;
+ unsigned char ewma_log;
+};
+
+
+#endif /* __LINUX_GEN_STATS_H */
diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h
new file mode 100644
index 0000000..e9b8117
--- /dev/null
+++ b/include/uapi/linux/genetlink.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_GENERIC_NETLINK_H
+#define __LINUX_GENERIC_NETLINK_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+#define GENL_NAMSIZ 16 /* length of family name */
+
+#define GENL_MIN_ID NLMSG_MIN_TYPE
+#define GENL_MAX_ID 1023
+
+struct genlmsghdr {
+ __u8 cmd;
+ __u8 version;
+ __u16 reserved;
+};
+
+#define GENL_HDRLEN NLMSG_ALIGN(sizeof(struct genlmsghdr))
+
+#define GENL_ADMIN_PERM 0x01
+#define GENL_CMD_CAP_DO 0x02
+#define GENL_CMD_CAP_DUMP 0x04
+#define GENL_CMD_CAP_HASPOL 0x08
+#define GENL_UNS_ADMIN_PERM 0x10
+
+/*
+ * List of reserved static generic netlink identifiers:
+ */
+#define GENL_ID_CTRL NLMSG_MIN_TYPE
+#define GENL_ID_VFS_DQUOT (NLMSG_MIN_TYPE + 1)
+#define GENL_ID_PMCRAID (NLMSG_MIN_TYPE + 2)
+/* must be last reserved + 1 */
+#define GENL_START_ALLOC (NLMSG_MIN_TYPE + 3)
+
+/**************************************************************************
+ * Controller
+ **************************************************************************/
+
+enum {
+ CTRL_CMD_UNSPEC,
+ CTRL_CMD_NEWFAMILY,
+ CTRL_CMD_DELFAMILY,
+ CTRL_CMD_GETFAMILY,
+ CTRL_CMD_NEWOPS,
+ CTRL_CMD_DELOPS,
+ CTRL_CMD_GETOPS,
+ CTRL_CMD_NEWMCAST_GRP,
+ CTRL_CMD_DELMCAST_GRP,
+ CTRL_CMD_GETMCAST_GRP, /* unused */
+ CTRL_CMD_GETPOLICY,
+ __CTRL_CMD_MAX,
+};
+
+#define CTRL_CMD_MAX (__CTRL_CMD_MAX - 1)
+
+enum {
+ CTRL_ATTR_UNSPEC,
+ CTRL_ATTR_FAMILY_ID,
+ CTRL_ATTR_FAMILY_NAME,
+ CTRL_ATTR_VERSION,
+ CTRL_ATTR_HDRSIZE,
+ CTRL_ATTR_MAXATTR,
+ CTRL_ATTR_OPS,
+ CTRL_ATTR_MCAST_GROUPS,
+ CTRL_ATTR_POLICY,
+ CTRL_ATTR_OP_POLICY,
+ CTRL_ATTR_OP,
+ __CTRL_ATTR_MAX,
+};
+
+#define CTRL_ATTR_MAX (__CTRL_ATTR_MAX - 1)
+
+enum {
+ CTRL_ATTR_OP_UNSPEC,
+ CTRL_ATTR_OP_ID,
+ CTRL_ATTR_OP_FLAGS,
+ __CTRL_ATTR_OP_MAX,
+};
+
+#define CTRL_ATTR_OP_MAX (__CTRL_ATTR_OP_MAX - 1)
+
+enum {
+ CTRL_ATTR_MCAST_GRP_UNSPEC,
+ CTRL_ATTR_MCAST_GRP_NAME,
+ CTRL_ATTR_MCAST_GRP_ID,
+ __CTRL_ATTR_MCAST_GRP_MAX,
+};
+
+#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
+
+enum {
+ CTRL_ATTR_POLICY_UNSPEC,
+ CTRL_ATTR_POLICY_DO,
+ CTRL_ATTR_POLICY_DUMP,
+
+ __CTRL_ATTR_POLICY_DUMP_MAX,
+ CTRL_ATTR_POLICY_DUMP_MAX = __CTRL_ATTR_POLICY_DUMP_MAX - 1
+};
+
+#define CTRL_ATTR_POLICY_MAX (__CTRL_ATTR_POLICY_DUMP_MAX - 1)
+
+#endif /* __LINUX_GENERIC_NETLINK_H */
diff --git a/include/uapi/linux/hdlc/ioctl.h b/include/uapi/linux/hdlc/ioctl.h
new file mode 100644
index 0000000..b06341a
--- /dev/null
+++ b/include/uapi/linux/hdlc/ioctl.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __HDLC_IOCTL_H__
+#define __HDLC_IOCTL_H__
+
+
+#define GENERIC_HDLC_VERSION 4 /* For synchronization with sethdlc utility */
+
+#define CLOCK_DEFAULT 0 /* Default setting */
+#define CLOCK_EXT 1 /* External TX and RX clock - DTE */
+#define CLOCK_INT 2 /* Internal TX and RX clock - DCE */
+#define CLOCK_TXINT 3 /* Internal TX and external RX clock */
+#define CLOCK_TXFROMRX 4 /* TX clock derived from external RX clock */
+
+
+#define ENCODING_DEFAULT 0 /* Default setting */
+#define ENCODING_NRZ 1
+#define ENCODING_NRZI 2
+#define ENCODING_FM_MARK 3
+#define ENCODING_FM_SPACE 4
+#define ENCODING_MANCHESTER 5
+
+
+#define PARITY_DEFAULT 0 /* Default setting */
+#define PARITY_NONE 1 /* No parity */
+#define PARITY_CRC16_PR0 2 /* CRC16, initial value 0x0000 */
+#define PARITY_CRC16_PR1 3 /* CRC16, initial value 0xFFFF */
+#define PARITY_CRC16_PR0_CCITT 4 /* CRC16, initial 0x0000, ITU-T version */
+#define PARITY_CRC16_PR1_CCITT 5 /* CRC16, initial 0xFFFF, ITU-T version */
+#define PARITY_CRC32_PR0_CCITT 6 /* CRC32, initial value 0x00000000 */
+#define PARITY_CRC32_PR1_CCITT 7 /* CRC32, initial value 0xFFFFFFFF */
+
+#define LMI_DEFAULT 0 /* Default setting */
+#define LMI_NONE 1 /* No LMI, all PVCs are static */
+#define LMI_ANSI 2 /* ANSI Annex D */
+#define LMI_CCITT 3 /* ITU-T Annex A */
+#define LMI_CISCO 4 /* The "original" LMI, aka Gang of Four */
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+ unsigned int clock_rate; /* bits per second */
+ unsigned int clock_type; /* internal, external, TX-internal etc. */
+ unsigned short loopback;
+} sync_serial_settings; /* V.35, V.24, X.21 */
+
+typedef struct {
+ unsigned int clock_rate; /* bits per second */
+ unsigned int clock_type; /* internal, external, TX-internal etc. */
+ unsigned short loopback;
+ unsigned int slot_map;
+} te1_settings; /* T1, E1 */
+
+typedef struct {
+ unsigned short encoding;
+ unsigned short parity;
+} raw_hdlc_proto;
+
+typedef struct {
+ unsigned int t391;
+ unsigned int t392;
+ unsigned int n391;
+ unsigned int n392;
+ unsigned int n393;
+ unsigned short lmi;
+ unsigned short dce; /* 1 for DCE (network side) operation */
+} fr_proto;
+
+typedef struct {
+ unsigned int dlci;
+} fr_proto_pvc; /* for creating/deleting FR PVCs */
+
+typedef struct {
+ unsigned int dlci;
+ char master[IFNAMSIZ]; /* Name of master FRAD device */
+}fr_proto_pvc_info; /* for returning PVC information only */
+
+typedef struct {
+ unsigned int interval;
+ unsigned int timeout;
+} cisco_proto;
+
+typedef struct {
+ unsigned short dce; /* 1 for DCE (network side) operation */
+ unsigned int modulo; /* modulo (8 = basic / 128 = extended) */
+ unsigned int window; /* frame window size */
+ unsigned int t1; /* timeout t1 */
+ unsigned int t2; /* timeout t2 */
+ unsigned int n2; /* frame retry counter */
+} x25_hdlc_proto;
+
+/* PPP doesn't need any info now - supply length = 0 to ioctl */
+
+#endif /* __ASSEMBLY__ */
+#endif /* __HDLC_IOCTL_H__ */
diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h
new file mode 100644
index 0000000..fa6388c
--- /dev/null
+++ b/include/uapi/linux/icmpv6.h
@@ -0,0 +1,178 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_ICMPV6_H
+#define _LINUX_ICMPV6_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+struct icmp6hdr {
+
+ __u8 icmp6_type;
+ __u8 icmp6_code;
+ __sum16 icmp6_cksum;
+
+
+ union {
+ __be32 un_data32[1];
+ __be16 un_data16[2];
+ __u8 un_data8[4];
+
+ struct icmpv6_echo {
+ __be16 identifier;
+ __be16 sequence;
+ } u_echo;
+
+ struct icmpv6_nd_advt {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u32 reserved:5,
+ override:1,
+ solicited:1,
+ router:1,
+ reserved2:24;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u32 router:1,
+ solicited:1,
+ override:1,
+ reserved:29;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+ } u_nd_advt;
+
+ struct icmpv6_nd_ra {
+ __u8 hop_limit;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u8 reserved:3,
+ router_pref:2,
+ home_agent:1,
+ other:1,
+ managed:1;
+
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u8 managed:1,
+ other:1,
+ home_agent:1,
+ router_pref:2,
+ reserved:3;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+ __be16 rt_lifetime;
+ } u_nd_ra;
+
+ } icmp6_dataun;
+
+#define icmp6_identifier icmp6_dataun.u_echo.identifier
+#define icmp6_sequence icmp6_dataun.u_echo.sequence
+#define icmp6_pointer icmp6_dataun.un_data32[0]
+#define icmp6_mtu icmp6_dataun.un_data32[0]
+#define icmp6_unused icmp6_dataun.un_data32[0]
+#define icmp6_maxdelay icmp6_dataun.un_data16[0]
+#define icmp6_datagram_len icmp6_dataun.un_data8[0]
+#define icmp6_router icmp6_dataun.u_nd_advt.router
+#define icmp6_solicited icmp6_dataun.u_nd_advt.solicited
+#define icmp6_override icmp6_dataun.u_nd_advt.override
+#define icmp6_ndiscreserved icmp6_dataun.u_nd_advt.reserved
+#define icmp6_hop_limit icmp6_dataun.u_nd_ra.hop_limit
+#define icmp6_addrconf_managed icmp6_dataun.u_nd_ra.managed
+#define icmp6_addrconf_other icmp6_dataun.u_nd_ra.other
+#define icmp6_rt_lifetime icmp6_dataun.u_nd_ra.rt_lifetime
+#define icmp6_router_pref icmp6_dataun.u_nd_ra.router_pref
+};
+
+
+#define ICMPV6_ROUTER_PREF_LOW 0x3
+#define ICMPV6_ROUTER_PREF_MEDIUM 0x0
+#define ICMPV6_ROUTER_PREF_HIGH 0x1
+#define ICMPV6_ROUTER_PREF_INVALID 0x2
+
+#define ICMPV6_DEST_UNREACH 1
+#define ICMPV6_PKT_TOOBIG 2
+#define ICMPV6_TIME_EXCEED 3
+#define ICMPV6_PARAMPROB 4
+
+#define ICMPV6_ERRMSG_MAX 127
+
+#define ICMPV6_INFOMSG_MASK 0x80
+
+#define ICMPV6_ECHO_REQUEST 128
+#define ICMPV6_ECHO_REPLY 129
+#define ICMPV6_MGM_QUERY 130
+#define ICMPV6_MGM_REPORT 131
+#define ICMPV6_MGM_REDUCTION 132
+
+#define ICMPV6_NI_QUERY 139
+#define ICMPV6_NI_REPLY 140
+
+#define ICMPV6_MLD2_REPORT 143
+
+#define ICMPV6_DHAAD_REQUEST 144
+#define ICMPV6_DHAAD_REPLY 145
+#define ICMPV6_MOBILE_PREFIX_SOL 146
+#define ICMPV6_MOBILE_PREFIX_ADV 147
+
+#define ICMPV6_MRDISC_ADV 151
+
+#define ICMPV6_MSG_MAX 255
+
+/*
+ * Codes for Destination Unreachable
+ */
+#define ICMPV6_NOROUTE 0
+#define ICMPV6_ADM_PROHIBITED 1
+#define ICMPV6_NOT_NEIGHBOUR 2
+#define ICMPV6_ADDR_UNREACH 3
+#define ICMPV6_PORT_UNREACH 4
+#define ICMPV6_POLICY_FAIL 5
+#define ICMPV6_REJECT_ROUTE 6
+
+/*
+ * Codes for Time Exceeded
+ */
+#define ICMPV6_EXC_HOPLIMIT 0
+#define ICMPV6_EXC_FRAGTIME 1
+
+/*
+ * Codes for Parameter Problem
+ */
+#define ICMPV6_HDR_FIELD 0
+#define ICMPV6_UNK_NEXTHDR 1
+#define ICMPV6_UNK_OPTION 2
+#define ICMPV6_HDR_INCOMP 3
+
+/* Codes for EXT_ECHO (PROBE) */
+#define ICMPV6_EXT_ECHO_REQUEST 160
+#define ICMPV6_EXT_ECHO_REPLY 161
+/*
+ * constants for (set|get)sockopt
+ */
+
+#define ICMPV6_FILTER 1
+
+/*
+ * ICMPV6 filter
+ */
+
+#define ICMPV6_FILTER_BLOCK 1
+#define ICMPV6_FILTER_PASS 2
+#define ICMPV6_FILTER_BLOCKOTHERS 3
+#define ICMPV6_FILTER_PASSONLY 4
+
+struct icmp6_filter {
+ __u32 data[8];
+};
+
+/*
+ * Definitions for MLDv2
+ */
+#define MLD2_MODE_IS_INCLUDE 1
+#define MLD2_MODE_IS_EXCLUDE 2
+#define MLD2_CHANGE_TO_INCLUDE 3
+#define MLD2_CHANGE_TO_EXCLUDE 4
+#define MLD2_ALLOW_NEW_SOURCES 5
+#define MLD2_BLOCK_OLD_SOURCES 6
+
+#define MLD2_ALL_MCR_INIT { { { 0xff,0x02,0,0,0,0,0,0,0,0,0,0,0,0,0,0x16 } } }
+
+
+#endif /* _LINUX_ICMPV6_H */
diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
new file mode 100644
index 0000000..b287b2a
--- /dev/null
+++ b/include/uapi/linux/if.h
@@ -0,0 +1,296 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Global definitions for the INET interface module.
+ *
+ * Version: @(#)if.h 1.0.2 04/18/93
+ *
+ * Authors: Original taken from Berkeley UNIX 4.3, (c) UCB 1982-1988
+ * Ross Biro
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_IF_H
+#define _LINUX_IF_H
+
+#include <linux/libc-compat.h> /* for compatibility with glibc */
+#include <linux/types.h> /* for "__kernel_caddr_t" et al */
+#include <linux/socket.h> /* for "struct sockaddr" et al */
+ /* for "__user" et al */
+
+#include <sys/socket.h> /* for struct sockaddr. */
+
+#if __UAPI_DEF_IF_IFNAMSIZ
+#define IFNAMSIZ 16
+#endif /* __UAPI_DEF_IF_IFNAMSIZ */
+#define IFALIASZ 256
+#define ALTIFNAMSIZ 128
+#include <linux/hdlc/ioctl.h>
+
+/* For glibc compatibility. An empty enum does not compile. */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 || \
+ __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0
+/**
+ * enum net_device_flags - &struct net_device flags
+ *
+ * These are the &struct net_device flags, they can be set by drivers, the
+ * kernel and some can be triggered by userspace. Userspace can query and
+ * set these flags using userspace utilities but there is also a sysfs
+ * entry available for all dev flags which can be queried and set. These flags
+ * are shared for all types of net_devices. The sysfs entries are available
+ * via /sys/class/net/<dev>/flags. Flags which can be toggled through sysfs
+ * are annotated below, note that only a few flags can be toggled and some
+ * other flags are always preserved from the original net_device flags
+ * even if you try to set them via sysfs. Flags which are always preserved
+ * are kept under the flag grouping @IFF_VOLATILE. Flags which are __volatile__
+ * are annotated below as such.
+ *
+ * You should have a pretty good reason to be extending these flags.
+ *
+ * @IFF_UP: interface is up. Can be toggled through sysfs.
+ * @IFF_BROADCAST: broadcast address valid. Volatile.
+ * @IFF_DEBUG: turn on debugging. Can be toggled through sysfs.
+ * @IFF_LOOPBACK: is a loopback net. Volatile.
+ * @IFF_POINTOPOINT: interface is has p-p link. Volatile.
+ * @IFF_NOTRAILERS: avoid use of trailers. Can be toggled through sysfs.
+ * Volatile.
+ * @IFF_RUNNING: interface RFC2863 OPER_UP. Volatile.
+ * @IFF_NOARP: no ARP protocol. Can be toggled through sysfs. Volatile.
+ * @IFF_PROMISC: receive all packets. Can be toggled through sysfs.
+ * @IFF_ALLMULTI: receive all multicast packets. Can be toggled through
+ * sysfs.
+ * @IFF_MASTER: master of a load balancer. Volatile.
+ * @IFF_SLAVE: slave of a load balancer. Volatile.
+ * @IFF_MULTICAST: Supports multicast. Can be toggled through sysfs.
+ * @IFF_PORTSEL: can set media type. Can be toggled through sysfs.
+ * @IFF_AUTOMEDIA: auto media select active. Can be toggled through sysfs.
+ * @IFF_DYNAMIC: dialup device with changing addresses. Can be toggled
+ * through sysfs.
+ * @IFF_LOWER_UP: driver signals L1 up. Volatile.
+ * @IFF_DORMANT: driver signals dormant. Volatile.
+ * @IFF_ECHO: echo sent packets. Volatile.
+ */
+enum net_device_flags {
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS
+ IFF_UP = 1<<0, /* sysfs */
+ IFF_BROADCAST = 1<<1, /* __volatile__ */
+ IFF_DEBUG = 1<<2, /* sysfs */
+ IFF_LOOPBACK = 1<<3, /* __volatile__ */
+ IFF_POINTOPOINT = 1<<4, /* __volatile__ */
+ IFF_NOTRAILERS = 1<<5, /* sysfs */
+ IFF_RUNNING = 1<<6, /* __volatile__ */
+ IFF_NOARP = 1<<7, /* sysfs */
+ IFF_PROMISC = 1<<8, /* sysfs */
+ IFF_ALLMULTI = 1<<9, /* sysfs */
+ IFF_MASTER = 1<<10, /* __volatile__ */
+ IFF_SLAVE = 1<<11, /* __volatile__ */
+ IFF_MULTICAST = 1<<12, /* sysfs */
+ IFF_PORTSEL = 1<<13, /* sysfs */
+ IFF_AUTOMEDIA = 1<<14, /* sysfs */
+ IFF_DYNAMIC = 1<<15, /* sysfs */
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
+ IFF_LOWER_UP = 1<<16, /* __volatile__ */
+ IFF_DORMANT = 1<<17, /* __volatile__ */
+ IFF_ECHO = 1<<18, /* __volatile__ */
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
+};
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 || __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */
+
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS
+#define IFF_UP IFF_UP
+#define IFF_BROADCAST IFF_BROADCAST
+#define IFF_DEBUG IFF_DEBUG
+#define IFF_LOOPBACK IFF_LOOPBACK
+#define IFF_POINTOPOINT IFF_POINTOPOINT
+#define IFF_NOTRAILERS IFF_NOTRAILERS
+#define IFF_RUNNING IFF_RUNNING
+#define IFF_NOARP IFF_NOARP
+#define IFF_PROMISC IFF_PROMISC
+#define IFF_ALLMULTI IFF_ALLMULTI
+#define IFF_MASTER IFF_MASTER
+#define IFF_SLAVE IFF_SLAVE
+#define IFF_MULTICAST IFF_MULTICAST
+#define IFF_PORTSEL IFF_PORTSEL
+#define IFF_AUTOMEDIA IFF_AUTOMEDIA
+#define IFF_DYNAMIC IFF_DYNAMIC
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */
+
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
+#define IFF_LOWER_UP IFF_LOWER_UP
+#define IFF_DORMANT IFF_DORMANT
+#define IFF_ECHO IFF_ECHO
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
+
+#define IFF_VOLATILE (IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\
+ IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT)
+
+#define IF_GET_IFACE 0x0001 /* for querying only */
+#define IF_GET_PROTO 0x0002
+
+/* For definitions see hdlc.h */
+#define IF_IFACE_V35 0x1000 /* V.35 serial interface */
+#define IF_IFACE_V24 0x1001 /* V.24 serial interface */
+#define IF_IFACE_X21 0x1002 /* X.21 serial interface */
+#define IF_IFACE_T1 0x1003 /* T1 telco serial interface */
+#define IF_IFACE_E1 0x1004 /* E1 telco serial interface */
+#define IF_IFACE_SYNC_SERIAL 0x1005 /* can't be set by software */
+#define IF_IFACE_X21D 0x1006 /* X.21 Dual Clocking (FarSite) */
+
+/* For definitions see hdlc.h */
+#define IF_PROTO_HDLC 0x2000 /* raw HDLC protocol */
+#define IF_PROTO_PPP 0x2001 /* PPP protocol */
+#define IF_PROTO_CISCO 0x2002 /* Cisco HDLC protocol */
+#define IF_PROTO_FR 0x2003 /* Frame Relay protocol */
+#define IF_PROTO_FR_ADD_PVC 0x2004 /* Create FR PVC */
+#define IF_PROTO_FR_DEL_PVC 0x2005 /* Delete FR PVC */
+#define IF_PROTO_X25 0x2006 /* X.25 */
+#define IF_PROTO_HDLC_ETH 0x2007 /* raw HDLC, Ethernet emulation */
+#define IF_PROTO_FR_ADD_ETH_PVC 0x2008 /* Create FR Ethernet-bridged PVC */
+#define IF_PROTO_FR_DEL_ETH_PVC 0x2009 /* Delete FR Ethernet-bridged PVC */
+#define IF_PROTO_FR_PVC 0x200A /* for reading PVC status */
+#define IF_PROTO_FR_ETH_PVC 0x200B
+#define IF_PROTO_RAW 0x200C /* RAW Socket */
+
+/* RFC 2863 operational status */
+enum {
+ IF_OPER_UNKNOWN,
+ IF_OPER_NOTPRESENT,
+ IF_OPER_DOWN,
+ IF_OPER_LOWERLAYERDOWN,
+ IF_OPER_TESTING,
+ IF_OPER_DORMANT,
+ IF_OPER_UP,
+};
+
+/* link modes */
+enum {
+ IF_LINK_MODE_DEFAULT,
+ IF_LINK_MODE_DORMANT, /* limit upward transition to dormant */
+ IF_LINK_MODE_TESTING, /* limit upward transition to testing */
+};
+
+/*
+ * Device mapping structure. I'd just gone off and designed a
+ * beautiful scheme using only loadable modules with arguments
+ * for driver options and along come the PCMCIA people 8)
+ *
+ * Ah well. The get() side of this is good for WDSETUP, and it'll
+ * be handy for debugging things. The set side is fine for now and
+ * being very small might be worth keeping for clean configuration.
+ */
+
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFMAP
+struct ifmap {
+ unsigned long mem_start;
+ unsigned long mem_end;
+ unsigned short base_addr;
+ unsigned char irq;
+ unsigned char dma;
+ unsigned char port;
+ /* 3 bytes spare */
+};
+#endif /* __UAPI_DEF_IF_IFMAP */
+
+struct if_settings {
+ unsigned int type; /* Type of physical device or protocol */
+ unsigned int size; /* Size of the data allocated by the caller */
+ union {
+ /* {atm/eth/dsl}_settings anyone ? */
+ raw_hdlc_proto *raw_hdlc;
+ cisco_proto *cisco;
+ fr_proto *fr;
+ fr_proto_pvc *fr_pvc;
+ fr_proto_pvc_info *fr_pvc_info;
+ x25_hdlc_proto *x25;
+
+ /* interface settings */
+ sync_serial_settings *sync;
+ te1_settings *te1;
+ } ifs_ifsu;
+};
+
+/*
+ * Interface request structure used for socket
+ * ioctl's. All interface ioctl's must have parameter
+ * definitions which begin with ifr_name. The
+ * remainder may be interface specific.
+ */
+
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFREQ
+struct ifreq {
+#define IFHWADDRLEN 6
+ union
+ {
+ char ifrn_name[IFNAMSIZ]; /* if name, e.g. "en0" */
+ } ifr_ifrn;
+
+ union {
+ struct sockaddr ifru_addr;
+ struct sockaddr ifru_dstaddr;
+ struct sockaddr ifru_broadaddr;
+ struct sockaddr ifru_netmask;
+ struct sockaddr ifru_hwaddr;
+ short ifru_flags;
+ int ifru_ivalue;
+ int ifru_mtu;
+ struct ifmap ifru_map;
+ char ifru_slave[IFNAMSIZ]; /* Just fits the size */
+ char ifru_newname[IFNAMSIZ];
+ void * ifru_data;
+ struct if_settings ifru_settings;
+ } ifr_ifru;
+};
+#endif /* __UAPI_DEF_IF_IFREQ */
+
+#define ifr_name ifr_ifrn.ifrn_name /* interface name */
+#define ifr_hwaddr ifr_ifru.ifru_hwaddr /* MAC address */
+#define ifr_addr ifr_ifru.ifru_addr /* address */
+#define ifr_dstaddr ifr_ifru.ifru_dstaddr /* other end of p-p lnk */
+#define ifr_broadaddr ifr_ifru.ifru_broadaddr /* broadcast address */
+#define ifr_netmask ifr_ifru.ifru_netmask /* interface net mask */
+#define ifr_flags ifr_ifru.ifru_flags /* flags */
+#define ifr_metric ifr_ifru.ifru_ivalue /* metric */
+#define ifr_mtu ifr_ifru.ifru_mtu /* mtu */
+#define ifr_map ifr_ifru.ifru_map /* device map */
+#define ifr_slave ifr_ifru.ifru_slave /* slave device */
+#define ifr_data ifr_ifru.ifru_data /* for use by interface */
+#define ifr_ifindex ifr_ifru.ifru_ivalue /* interface index */
+#define ifr_bandwidth ifr_ifru.ifru_ivalue /* link bandwidth */
+#define ifr_qlen ifr_ifru.ifru_ivalue /* Queue length */
+#define ifr_newname ifr_ifru.ifru_newname /* New name */
+#define ifr_settings ifr_ifru.ifru_settings /* Device/proto settings*/
+
+/*
+ * Structure used in SIOCGIFCONF request.
+ * Used to retrieve interface configuration
+ * for machine (useful for programs which
+ * must know all networks accessible).
+ */
+
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFCONF
+struct ifconf {
+ int ifc_len; /* size of buffer */
+ union {
+ char *ifcu_buf;
+ struct ifreq *ifcu_req;
+ } ifc_ifcu;
+};
+#endif /* __UAPI_DEF_IF_IFCONF */
+
+#define ifc_buf ifc_ifcu.ifcu_buf /* buffer address */
+#define ifc_req ifc_ifcu.ifcu_req /* array of structures */
+
+#endif /* _LINUX_IF_H */
diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h
new file mode 100644
index 0000000..d6db3ff
--- /dev/null
+++ b/include/uapi/linux/if_addr.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_IF_ADDR_H
+#define __LINUX_IF_ADDR_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+struct ifaddrmsg {
+ __u8 ifa_family;
+ __u8 ifa_prefixlen; /* The prefix length */
+ __u8 ifa_flags; /* Flags */
+ __u8 ifa_scope; /* Address scope */
+ __u32 ifa_index; /* Link index */
+};
+
+/*
+ * Important comment:
+ * IFA_ADDRESS is prefix address, rather than local interface address.
+ * It makes no difference for normally configured broadcast interfaces,
+ * but for point-to-point IFA_ADDRESS is DESTINATION address,
+ * local address is supplied in IFA_LOCAL attribute.
+ *
+ * IFA_FLAGS is a u32 attribute that extends the u8 field ifa_flags.
+ * If present, the value from struct ifaddrmsg will be ignored.
+ */
+enum {
+ IFA_UNSPEC,
+ IFA_ADDRESS,
+ IFA_LOCAL,
+ IFA_LABEL,
+ IFA_BROADCAST,
+ IFA_ANYCAST,
+ IFA_CACHEINFO,
+ IFA_MULTICAST,
+ IFA_FLAGS,
+ IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */
+ IFA_TARGET_NETNSID,
+ IFA_PROTO, /* u8, address protocol */
+ __IFA_MAX,
+};
+
+#define IFA_MAX (__IFA_MAX - 1)
+
+/* ifa_flags */
+#define IFA_F_SECONDARY 0x01
+#define IFA_F_TEMPORARY IFA_F_SECONDARY
+
+#define IFA_F_NODAD 0x02
+#define IFA_F_OPTIMISTIC 0x04
+#define IFA_F_DADFAILED 0x08
+#define IFA_F_HOMEADDRESS 0x10
+#define IFA_F_DEPRECATED 0x20
+#define IFA_F_TENTATIVE 0x40
+#define IFA_F_PERMANENT 0x80
+#define IFA_F_MANAGETEMPADDR 0x100
+#define IFA_F_NOPREFIXROUTE 0x200
+#define IFA_F_MCAUTOJOIN 0x400
+#define IFA_F_STABLE_PRIVACY 0x800
+
+struct ifa_cacheinfo {
+ __u32 ifa_prefered;
+ __u32 ifa_valid;
+ __u32 cstamp; /* created timestamp, hundredths of seconds */
+ __u32 tstamp; /* updated timestamp, hundredths of seconds */
+};
+
+/* backwards compatibility for userspace */
+#define IFA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg))))
+#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg))
+
+/* ifa_proto */
+#define IFAPROT_UNSPEC 0
+#define IFAPROT_KERNEL_LO 1 /* loopback */
+#define IFAPROT_KERNEL_RA 2 /* set by kernel from router announcement */
+#define IFAPROT_KERNEL_LL 3 /* link-local set by kernel */
+
+#endif
diff --git a/include/uapi/linux/if_addrlabel.h b/include/uapi/linux/if_addrlabel.h
new file mode 100644
index 0000000..d1f5974
--- /dev/null
+++ b/include/uapi/linux/if_addrlabel.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * if_addrlabel.h - netlink interface for address labels
+ *
+ * Copyright (C)2007 USAGI/WIDE Project, All Rights Reserved.
+ *
+ * Authors:
+ * YOSHIFUJI Hideaki @ USAGI/WIDE <yoshfuji@linux-ipv6.org>
+ */
+
+#ifndef __LINUX_IF_ADDRLABEL_H
+#define __LINUX_IF_ADDRLABEL_H
+
+#include <linux/types.h>
+
+struct ifaddrlblmsg {
+ __u8 ifal_family; /* Address family */
+ __u8 __ifal_reserved; /* Reserved */
+ __u8 ifal_prefixlen; /* Prefix length */
+ __u8 ifal_flags; /* Flags */
+ __u32 ifal_index; /* Link index */
+ __u32 ifal_seq; /* sequence number */
+};
+
+enum {
+ IFAL_ADDRESS = 1,
+ IFAL_LABEL = 2,
+ __IFAL_MAX
+};
+
+#define IFAL_MAX (__IFAL_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h
new file mode 100644
index 0000000..0824fbc
--- /dev/null
+++ b/include/uapi/linux/if_alg.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * if_alg: User-space algorithm interface
+ *
+ * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _LINUX_IF_ALG_H
+#define _LINUX_IF_ALG_H
+
+#include <linux/types.h>
+
+struct sockaddr_alg {
+ __u16 salg_family;
+ __u8 salg_type[14];
+ __u32 salg_feat;
+ __u32 salg_mask;
+ __u8 salg_name[64];
+};
+
+/*
+ * Linux v4.12 and later removed the 64-byte limit on salg_name[]; it's now an
+ * arbitrary-length field. We had to keep the original struct above for source
+ * compatibility with existing userspace programs, though. Use the new struct
+ * below if support for very long algorithm names is needed. To do this,
+ * allocate 'sizeof(struct sockaddr_alg_new) + strlen(algname) + 1' bytes, and
+ * copy algname (including the null terminator) into salg_name.
+ */
+struct sockaddr_alg_new {
+ __u16 salg_family;
+ __u8 salg_type[14];
+ __u32 salg_feat;
+ __u32 salg_mask;
+ __u8 salg_name[];
+};
+
+struct af_alg_iv {
+ __u32 ivlen;
+ __u8 iv[];
+};
+
+/* Socket options */
+#define ALG_SET_KEY 1
+#define ALG_SET_IV 2
+#define ALG_SET_OP 3
+#define ALG_SET_AEAD_ASSOCLEN 4
+#define ALG_SET_AEAD_AUTHSIZE 5
+#define ALG_SET_DRBG_ENTROPY 6
+#define ALG_SET_KEY_BY_KEY_SERIAL 7
+
+/* Operations */
+#define ALG_OP_DECRYPT 0
+#define ALG_OP_ENCRYPT 1
+
+#endif /* _LINUX_IF_ALG_H */
diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h
new file mode 100644
index 0000000..12d06bb
--- /dev/null
+++ b/include/uapi/linux/if_arp.h
@@ -0,0 +1,165 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Global definitions for the ARP (RFC 826) protocol.
+ *
+ * Version: @(#)if_arp.h 1.0.1 04/16/93
+ *
+ * Authors: Original taken from Berkeley UNIX 4.3, (c) UCB 1986-1988
+ * Portions taken from the KA9Q/NOS (v2.00m PA0GRI) source.
+ * Ross Biro
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ * Florian La Roche,
+ * Jonathan Layes <layes@loran.com>
+ * Arnaldo Carvalho de Melo <acme@conectiva.com.br> ARPHRD_HWX25
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_IF_ARP_H
+#define _LINUX_IF_ARP_H
+
+#include <linux/netdevice.h>
+
+/* ARP protocol HARDWARE identifiers. */
+#define ARPHRD_NETROM 0 /* from KA9Q: NET/ROM pseudo */
+#define ARPHRD_ETHER 1 /* Ethernet 10Mbps */
+#define ARPHRD_EETHER 2 /* Experimental Ethernet */
+#define ARPHRD_AX25 3 /* AX.25 Level 2 */
+#define ARPHRD_PRONET 4 /* PROnet token ring */
+#define ARPHRD_CHAOS 5 /* Chaosnet */
+#define ARPHRD_IEEE802 6 /* IEEE 802.2 Ethernet/TR/TB */
+#define ARPHRD_ARCNET 7 /* ARCnet */
+#define ARPHRD_APPLETLK 8 /* APPLEtalk */
+#define ARPHRD_DLCI 15 /* Frame Relay DLCI */
+#define ARPHRD_ATM 19 /* ATM */
+#define ARPHRD_METRICOM 23 /* Metricom STRIP (new IANA id) */
+#define ARPHRD_IEEE1394 24 /* IEEE 1394 IPv4 - RFC 2734 */
+#define ARPHRD_EUI64 27 /* EUI-64 */
+#define ARPHRD_INFINIBAND 32 /* InfiniBand */
+
+/* Dummy types for non ARP hardware */
+#define ARPHRD_SLIP 256
+#define ARPHRD_CSLIP 257
+#define ARPHRD_SLIP6 258
+#define ARPHRD_CSLIP6 259
+#define ARPHRD_RSRVD 260 /* Notional KISS type */
+#define ARPHRD_ADAPT 264
+#define ARPHRD_ROSE 270
+#define ARPHRD_X25 271 /* CCITT X.25 */
+#define ARPHRD_HWX25 272 /* Boards with X.25 in firmware */
+#define ARPHRD_CAN 280 /* Controller Area Network */
+#define ARPHRD_MCTP 290
+#define ARPHRD_PPP 512
+#define ARPHRD_CISCO 513 /* Cisco HDLC */
+#define ARPHRD_HDLC ARPHRD_CISCO
+#define ARPHRD_LAPB 516 /* LAPB */
+#define ARPHRD_DDCMP 517 /* Digital's DDCMP protocol */
+#define ARPHRD_RAWHDLC 518 /* Raw HDLC */
+#define ARPHRD_RAWIP 519 /* Raw IP */
+
+#define ARPHRD_TUNNEL 768 /* IPIP tunnel */
+#define ARPHRD_TUNNEL6 769 /* IP6IP6 tunnel */
+#define ARPHRD_FRAD 770 /* Frame Relay Access Device */
+#define ARPHRD_SKIP 771 /* SKIP vif */
+#define ARPHRD_LOOPBACK 772 /* Loopback device */
+#define ARPHRD_LOCALTLK 773 /* Localtalk device */
+#define ARPHRD_FDDI 774 /* Fiber Distributed Data Interface */
+#define ARPHRD_BIF 775 /* AP1000 BIF */
+#define ARPHRD_SIT 776 /* sit0 device - IPv6-in-IPv4 */
+#define ARPHRD_IPDDP 777 /* IP over DDP tunneller */
+#define ARPHRD_IPGRE 778 /* GRE over IP */
+#define ARPHRD_PIMREG 779 /* PIMSM register interface */
+#define ARPHRD_HIPPI 780 /* High Performance Parallel Interface */
+#define ARPHRD_ASH 781 /* Nexus 64Mbps Ash */
+#define ARPHRD_ECONET 782 /* Acorn Econet */
+#define ARPHRD_IRDA 783 /* Linux-IrDA */
+/* ARP works differently on different FC media .. so */
+#define ARPHRD_FCPP 784 /* Point to point fibrechannel */
+#define ARPHRD_FCAL 785 /* Fibrechannel arbitrated loop */
+#define ARPHRD_FCPL 786 /* Fibrechannel public loop */
+#define ARPHRD_FCFABRIC 787 /* Fibrechannel fabric */
+ /* 787->799 reserved for fibrechannel media types */
+#define ARPHRD_IEEE802_TR 800 /* Magic type ident for TR */
+#define ARPHRD_IEEE80211 801 /* IEEE 802.11 */
+#define ARPHRD_IEEE80211_PRISM 802 /* IEEE 802.11 + Prism2 header */
+#define ARPHRD_IEEE80211_RADIOTAP 803 /* IEEE 802.11 + radiotap header */
+#define ARPHRD_IEEE802154 804
+#define ARPHRD_IEEE802154_MONITOR 805 /* IEEE 802.15.4 network monitor */
+
+#define ARPHRD_PHONET 820 /* PhoNet media type */
+#define ARPHRD_PHONET_PIPE 821 /* PhoNet pipe header */
+#define ARPHRD_CAIF 822 /* CAIF media type */
+#define ARPHRD_IP6GRE 823 /* GRE over IPv6 */
+#define ARPHRD_NETLINK 824 /* Netlink header */
+#define ARPHRD_6LOWPAN 825 /* IPv6 over LoWPAN */
+#define ARPHRD_VSOCKMON 826 /* Vsock monitor header */
+
+#define ARPHRD_VOID 0xFFFF /* Void type, nothing is known */
+#define ARPHRD_NONE 0xFFFE /* zero header length */
+
+/* ARP protocol opcodes. */
+#define ARPOP_REQUEST 1 /* ARP request */
+#define ARPOP_REPLY 2 /* ARP reply */
+#define ARPOP_RREQUEST 3 /* RARP request */
+#define ARPOP_RREPLY 4 /* RARP reply */
+#define ARPOP_InREQUEST 8 /* InARP request */
+#define ARPOP_InREPLY 9 /* InARP reply */
+#define ARPOP_NAK 10 /* (ATM)ARP NAK */
+
+
+/* ARP ioctl request. */
+struct arpreq {
+ struct sockaddr arp_pa; /* protocol address */
+ struct sockaddr arp_ha; /* hardware address */
+ int arp_flags; /* flags */
+ struct sockaddr arp_netmask; /* netmask (only for proxy arps) */
+ char arp_dev[IFNAMSIZ];
+};
+
+struct arpreq_old {
+ struct sockaddr arp_pa; /* protocol address */
+ struct sockaddr arp_ha; /* hardware address */
+ int arp_flags; /* flags */
+ struct sockaddr arp_netmask; /* netmask (only for proxy arps) */
+};
+
+/* ARP Flag values. */
+#define ATF_COM 0x02 /* completed entry (ha valid) */
+#define ATF_PERM 0x04 /* permanent entry */
+#define ATF_PUBL 0x08 /* publish entry */
+#define ATF_USETRAILERS 0x10 /* has requested trailers */
+#define ATF_NETMASK 0x20 /* want to use a netmask (only
+ for proxy entries) */
+#define ATF_DONTPUB 0x40 /* don't answer this addresses */
+
+/*
+ * This structure defines an ethernet arp header.
+ */
+
+struct arphdr {
+ __be16 ar_hrd; /* format of hardware address */
+ __be16 ar_pro; /* format of protocol address */
+ unsigned char ar_hln; /* length of hardware address */
+ unsigned char ar_pln; /* length of protocol address */
+ __be16 ar_op; /* ARP opcode (command) */
+
+#if 0
+ /*
+ * Ethernet looks like this : This bit is variable sized however...
+ */
+ unsigned char ar_sha[ETH_ALEN]; /* sender hardware address */
+ unsigned char ar_sip[4]; /* sender IP address */
+ unsigned char ar_tha[ETH_ALEN]; /* target hardware address */
+ unsigned char ar_tip[4]; /* target IP address */
+#endif
+
+};
+
+
+#endif /* _LINUX_IF_ARP_H */
diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h
new file mode 100644
index 0000000..d174914
--- /dev/null
+++ b/include/uapi/linux/if_bonding.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */
+/*
+ * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'.
+ *
+ *
+ * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes
+ * NCM: Network and Communications Management, Inc.
+ *
+ * BUT, I'm the one who modified it for ethernet, so:
+ * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov
+ *
+ * This software may be used and distributed according to the terms
+ * of the GNU Public License, incorporated herein by reference.
+ *
+ * 2003/03/18 - Amir Noam <amir.noam at intel dot com>
+ * - Added support for getting slave's speed and duplex via ethtool.
+ * Needed for 802.3ad and other future modes.
+ *
+ * 2003/03/18 - Tsippy Mendelson <tsippy.mendelson at intel dot com> and
+ * Shmulik Hen <shmulik.hen at intel dot com>
+ * - Enable support of modes that need to use the unique mac address of
+ * each slave.
+ *
+ * 2003/03/18 - Tsippy Mendelson <tsippy.mendelson at intel dot com> and
+ * Amir Noam <amir.noam at intel dot com>
+ * - Moved driver's private data types to bonding.h
+ *
+ * 2003/03/18 - Amir Noam <amir.noam at intel dot com>,
+ * Tsippy Mendelson <tsippy.mendelson at intel dot com> and
+ * Shmulik Hen <shmulik.hen at intel dot com>
+ * - Added support for IEEE 802.3ad Dynamic link aggregation mode.
+ *
+ * 2003/05/01 - Amir Noam <amir.noam at intel dot com>
+ * - Added ABI version control to restore compatibility between
+ * new/old ifenslave and new/old bonding.
+ *
+ * 2003/12/01 - Shmulik Hen <shmulik.hen at intel dot com>
+ * - Code cleanup and style changes
+ *
+ * 2005/05/05 - Jason Gabler <jygabler at lbl dot gov>
+ * - added definitions for various XOR hashing policies
+ */
+
+#ifndef _LINUX_IF_BONDING_H
+#define _LINUX_IF_BONDING_H
+
+#include <linux/if.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+/* userland - kernel ABI version (2003/05/08) */
+#define BOND_ABI_VERSION 2
+
+/*
+ * We can remove these ioctl definitions in 2.5. People should use the
+ * SIOC*** versions of them instead
+ */
+#define BOND_ENSLAVE_OLD (SIOCDEVPRIVATE)
+#define BOND_RELEASE_OLD (SIOCDEVPRIVATE + 1)
+#define BOND_SETHWADDR_OLD (SIOCDEVPRIVATE + 2)
+#define BOND_SLAVE_INFO_QUERY_OLD (SIOCDEVPRIVATE + 11)
+#define BOND_INFO_QUERY_OLD (SIOCDEVPRIVATE + 12)
+#define BOND_CHANGE_ACTIVE_OLD (SIOCDEVPRIVATE + 13)
+
+#define BOND_CHECK_MII_STATUS (SIOCGMIIPHY)
+
+#define BOND_MODE_ROUNDROBIN 0
+#define BOND_MODE_ACTIVEBACKUP 1
+#define BOND_MODE_XOR 2
+#define BOND_MODE_BROADCAST 3
+#define BOND_MODE_8023AD 4
+#define BOND_MODE_TLB 5
+#define BOND_MODE_ALB 6 /* TLB + RLB (receive load balancing) */
+
+/* each slave's link has 4 states */
+#define BOND_LINK_UP 0 /* link is up and running */
+#define BOND_LINK_FAIL 1 /* link has just gone down */
+#define BOND_LINK_DOWN 2 /* link has been down for too long time */
+#define BOND_LINK_BACK 3 /* link is going back */
+
+/* each slave has several states */
+#define BOND_STATE_ACTIVE 0 /* link is active */
+#define BOND_STATE_BACKUP 1 /* link is backup */
+
+#define BOND_DEFAULT_MAX_BONDS 1 /* Default maximum number of devices to support */
+
+#define BOND_DEFAULT_TX_QUEUES 16 /* Default number of tx queues per device */
+
+#define BOND_DEFAULT_RESEND_IGMP 1 /* Default number of IGMP membership reports */
+
+/* hashing types */
+#define BOND_XMIT_POLICY_LAYER2 0 /* layer 2 (MAC only), default */
+#define BOND_XMIT_POLICY_LAYER34 1 /* layer 3+4 (IP ^ (TCP || UDP)) */
+#define BOND_XMIT_POLICY_LAYER23 2 /* layer 2+3 (IP ^ MAC) */
+#define BOND_XMIT_POLICY_ENCAP23 3 /* encapsulated layer 2+3 */
+#define BOND_XMIT_POLICY_ENCAP34 4 /* encapsulated layer 3+4 */
+#define BOND_XMIT_POLICY_VLAN_SRCMAC 5 /* vlan + source MAC */
+
+/* 802.3ad port state definitions (43.4.2.2 in the 802.3ad standard) */
+#define LACP_STATE_LACP_ACTIVITY 0x1
+#define LACP_STATE_LACP_TIMEOUT 0x2
+#define LACP_STATE_AGGREGATION 0x4
+#define LACP_STATE_SYNCHRONIZATION 0x8
+#define LACP_STATE_COLLECTING 0x10
+#define LACP_STATE_DISTRIBUTING 0x20
+#define LACP_STATE_DEFAULTED 0x40
+#define LACP_STATE_EXPIRED 0x80
+
+typedef struct ifbond {
+ __s32 bond_mode;
+ __s32 num_slaves;
+ __s32 miimon;
+} ifbond;
+
+typedef struct ifslave {
+ __s32 slave_id; /* Used as an IN param to the BOND_SLAVE_INFO_QUERY ioctl */
+ char slave_name[IFNAMSIZ];
+ __s8 link;
+ __s8 state;
+ __u32 link_failure_count;
+} ifslave;
+
+struct ad_info {
+ __u16 aggregator_id;
+ __u16 ports;
+ __u16 actor_key;
+ __u16 partner_key;
+ __u8 partner_system[ETH_ALEN];
+};
+
+/* Embedded inside LINK_XSTATS_TYPE_BOND */
+enum {
+ BOND_XSTATS_UNSPEC,
+ BOND_XSTATS_3AD,
+ __BOND_XSTATS_MAX
+};
+#define BOND_XSTATS_MAX (__BOND_XSTATS_MAX - 1)
+
+/* Embedded inside BOND_XSTATS_3AD */
+enum {
+ BOND_3AD_STAT_LACPDU_RX,
+ BOND_3AD_STAT_LACPDU_TX,
+ BOND_3AD_STAT_LACPDU_UNKNOWN_RX,
+ BOND_3AD_STAT_LACPDU_ILLEGAL_RX,
+ BOND_3AD_STAT_MARKER_RX,
+ BOND_3AD_STAT_MARKER_TX,
+ BOND_3AD_STAT_MARKER_RESP_RX,
+ BOND_3AD_STAT_MARKER_RESP_TX,
+ BOND_3AD_STAT_MARKER_UNKNOWN_RX,
+ BOND_3AD_STAT_PAD,
+ __BOND_3AD_STAT_MAX
+};
+#define BOND_3AD_STAT_MAX (__BOND_3AD_STAT_MAX - 1)
+
+#endif /* _LINUX_IF_BONDING_H */
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
new file mode 100644
index 0000000..c206cf6
--- /dev/null
+++ b/include/uapi/linux/if_bridge.h
@@ -0,0 +1,858 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Linux ethernet bridge
+ *
+ * Authors:
+ * Lennert Buytenhek <buytenh@gnu.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_IF_BRIDGE_H
+#define _LINUX_IF_BRIDGE_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+
+#define SYSFS_BRIDGE_ATTR "bridge"
+#define SYSFS_BRIDGE_FDB "brforward"
+#define SYSFS_BRIDGE_PORT_SUBDIR "brif"
+#define SYSFS_BRIDGE_PORT_ATTR "brport"
+#define SYSFS_BRIDGE_PORT_LINK "bridge"
+
+#define BRCTL_VERSION 1
+
+#define BRCTL_GET_VERSION 0
+#define BRCTL_GET_BRIDGES 1
+#define BRCTL_ADD_BRIDGE 2
+#define BRCTL_DEL_BRIDGE 3
+#define BRCTL_ADD_IF 4
+#define BRCTL_DEL_IF 5
+#define BRCTL_GET_BRIDGE_INFO 6
+#define BRCTL_GET_PORT_LIST 7
+#define BRCTL_SET_BRIDGE_FORWARD_DELAY 8
+#define BRCTL_SET_BRIDGE_HELLO_TIME 9
+#define BRCTL_SET_BRIDGE_MAX_AGE 10
+#define BRCTL_SET_AGEING_TIME 11
+#define BRCTL_SET_GC_INTERVAL 12
+#define BRCTL_GET_PORT_INFO 13
+#define BRCTL_SET_BRIDGE_STP_STATE 14
+#define BRCTL_SET_BRIDGE_PRIORITY 15
+#define BRCTL_SET_PORT_PRIORITY 16
+#define BRCTL_SET_PATH_COST 17
+#define BRCTL_GET_FDB_ENTRIES 18
+
+#define BR_STATE_DISABLED 0
+#define BR_STATE_LISTENING 1
+#define BR_STATE_LEARNING 2
+#define BR_STATE_FORWARDING 3
+#define BR_STATE_BLOCKING 4
+
+struct __bridge_info {
+ __u64 designated_root;
+ __u64 bridge_id;
+ __u32 root_path_cost;
+ __u32 max_age;
+ __u32 hello_time;
+ __u32 forward_delay;
+ __u32 bridge_max_age;
+ __u32 bridge_hello_time;
+ __u32 bridge_forward_delay;
+ __u8 topology_change;
+ __u8 topology_change_detected;
+ __u8 root_port;
+ __u8 stp_enabled;
+ __u32 ageing_time;
+ __u32 gc_interval;
+ __u32 hello_timer_value;
+ __u32 tcn_timer_value;
+ __u32 topology_change_timer_value;
+ __u32 gc_timer_value;
+};
+
+struct __port_info {
+ __u64 designated_root;
+ __u64 designated_bridge;
+ __u16 port_id;
+ __u16 designated_port;
+ __u32 path_cost;
+ __u32 designated_cost;
+ __u8 state;
+ __u8 top_change_ack;
+ __u8 config_pending;
+ __u8 unused0;
+ __u32 message_age_timer_value;
+ __u32 forward_delay_timer_value;
+ __u32 hold_timer_value;
+};
+
+struct __fdb_entry {
+ __u8 mac_addr[ETH_ALEN];
+ __u8 port_no;
+ __u8 is_local;
+ __u32 ageing_timer_value;
+ __u8 port_hi;
+ __u8 pad0;
+ __u16 unused;
+};
+
+/* Bridge Flags */
+#define BRIDGE_FLAGS_MASTER 1 /* Bridge command to/from master */
+#define BRIDGE_FLAGS_SELF 2 /* Bridge command to/from lowerdev */
+
+#define BRIDGE_MODE_VEB 0 /* Default loopback mode */
+#define BRIDGE_MODE_VEPA 1 /* 802.1Qbg defined VEPA mode */
+#define BRIDGE_MODE_UNDEF 0xFFFF /* mode undefined */
+
+/* Bridge management nested attributes
+ * [IFLA_AF_SPEC] = {
+ * [IFLA_BRIDGE_FLAGS]
+ * [IFLA_BRIDGE_MODE]
+ * [IFLA_BRIDGE_VLAN_INFO]
+ * }
+ */
+enum {
+ IFLA_BRIDGE_FLAGS,
+ IFLA_BRIDGE_MODE,
+ IFLA_BRIDGE_VLAN_INFO,
+ IFLA_BRIDGE_VLAN_TUNNEL_INFO,
+ IFLA_BRIDGE_MRP,
+ IFLA_BRIDGE_CFM,
+ IFLA_BRIDGE_MST,
+ __IFLA_BRIDGE_MAX,
+};
+#define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1)
+
+#define BRIDGE_VLAN_INFO_MASTER (1<<0) /* Operate on Bridge device as well */
+#define BRIDGE_VLAN_INFO_PVID (1<<1) /* VLAN is PVID, ingress untagged */
+#define BRIDGE_VLAN_INFO_UNTAGGED (1<<2) /* VLAN egresses untagged */
+#define BRIDGE_VLAN_INFO_RANGE_BEGIN (1<<3) /* VLAN is start of vlan range */
+#define BRIDGE_VLAN_INFO_RANGE_END (1<<4) /* VLAN is end of vlan range */
+#define BRIDGE_VLAN_INFO_BRENTRY (1<<5) /* Global bridge VLAN entry */
+#define BRIDGE_VLAN_INFO_ONLY_OPTS (1<<6) /* Skip create/delete/flags */
+
+struct bridge_vlan_info {
+ __u16 flags;
+ __u16 vid;
+};
+
+enum {
+ IFLA_BRIDGE_VLAN_TUNNEL_UNSPEC,
+ IFLA_BRIDGE_VLAN_TUNNEL_ID,
+ IFLA_BRIDGE_VLAN_TUNNEL_VID,
+ IFLA_BRIDGE_VLAN_TUNNEL_FLAGS,
+ __IFLA_BRIDGE_VLAN_TUNNEL_MAX,
+};
+
+#define IFLA_BRIDGE_VLAN_TUNNEL_MAX (__IFLA_BRIDGE_VLAN_TUNNEL_MAX - 1)
+
+struct bridge_vlan_xstats {
+ __u64 rx_bytes;
+ __u64 rx_packets;
+ __u64 tx_bytes;
+ __u64 tx_packets;
+ __u16 vid;
+ __u16 flags;
+ __u32 pad2;
+};
+
+enum {
+ IFLA_BRIDGE_MRP_UNSPEC,
+ IFLA_BRIDGE_MRP_INSTANCE,
+ IFLA_BRIDGE_MRP_PORT_STATE,
+ IFLA_BRIDGE_MRP_PORT_ROLE,
+ IFLA_BRIDGE_MRP_RING_STATE,
+ IFLA_BRIDGE_MRP_RING_ROLE,
+ IFLA_BRIDGE_MRP_START_TEST,
+ IFLA_BRIDGE_MRP_INFO,
+ IFLA_BRIDGE_MRP_IN_ROLE,
+ IFLA_BRIDGE_MRP_IN_STATE,
+ IFLA_BRIDGE_MRP_START_IN_TEST,
+ __IFLA_BRIDGE_MRP_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_MAX (__IFLA_BRIDGE_MRP_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_INSTANCE_UNSPEC,
+ IFLA_BRIDGE_MRP_INSTANCE_RING_ID,
+ IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX,
+ IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX,
+ IFLA_BRIDGE_MRP_INSTANCE_PRIO,
+ __IFLA_BRIDGE_MRP_INSTANCE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_INSTANCE_MAX (__IFLA_BRIDGE_MRP_INSTANCE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_PORT_STATE_UNSPEC,
+ IFLA_BRIDGE_MRP_PORT_STATE_STATE,
+ __IFLA_BRIDGE_MRP_PORT_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_PORT_STATE_MAX (__IFLA_BRIDGE_MRP_PORT_STATE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_PORT_ROLE_UNSPEC,
+ IFLA_BRIDGE_MRP_PORT_ROLE_ROLE,
+ __IFLA_BRIDGE_MRP_PORT_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_PORT_ROLE_MAX (__IFLA_BRIDGE_MRP_PORT_ROLE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_RING_STATE_UNSPEC,
+ IFLA_BRIDGE_MRP_RING_STATE_RING_ID,
+ IFLA_BRIDGE_MRP_RING_STATE_STATE,
+ __IFLA_BRIDGE_MRP_RING_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_RING_STATE_MAX (__IFLA_BRIDGE_MRP_RING_STATE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_RING_ROLE_UNSPEC,
+ IFLA_BRIDGE_MRP_RING_ROLE_RING_ID,
+ IFLA_BRIDGE_MRP_RING_ROLE_ROLE,
+ __IFLA_BRIDGE_MRP_RING_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_RING_ROLE_MAX (__IFLA_BRIDGE_MRP_RING_ROLE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_START_TEST_UNSPEC,
+ IFLA_BRIDGE_MRP_START_TEST_RING_ID,
+ IFLA_BRIDGE_MRP_START_TEST_INTERVAL,
+ IFLA_BRIDGE_MRP_START_TEST_MAX_MISS,
+ IFLA_BRIDGE_MRP_START_TEST_PERIOD,
+ IFLA_BRIDGE_MRP_START_TEST_MONITOR,
+ __IFLA_BRIDGE_MRP_START_TEST_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_START_TEST_MAX (__IFLA_BRIDGE_MRP_START_TEST_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_INFO_UNSPEC,
+ IFLA_BRIDGE_MRP_INFO_RING_ID,
+ IFLA_BRIDGE_MRP_INFO_P_IFINDEX,
+ IFLA_BRIDGE_MRP_INFO_S_IFINDEX,
+ IFLA_BRIDGE_MRP_INFO_PRIO,
+ IFLA_BRIDGE_MRP_INFO_RING_STATE,
+ IFLA_BRIDGE_MRP_INFO_RING_ROLE,
+ IFLA_BRIDGE_MRP_INFO_TEST_INTERVAL,
+ IFLA_BRIDGE_MRP_INFO_TEST_MAX_MISS,
+ IFLA_BRIDGE_MRP_INFO_TEST_MONITOR,
+ IFLA_BRIDGE_MRP_INFO_I_IFINDEX,
+ IFLA_BRIDGE_MRP_INFO_IN_STATE,
+ IFLA_BRIDGE_MRP_INFO_IN_ROLE,
+ IFLA_BRIDGE_MRP_INFO_IN_TEST_INTERVAL,
+ IFLA_BRIDGE_MRP_INFO_IN_TEST_MAX_MISS,
+ __IFLA_BRIDGE_MRP_INFO_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_INFO_MAX (__IFLA_BRIDGE_MRP_INFO_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_IN_STATE_UNSPEC,
+ IFLA_BRIDGE_MRP_IN_STATE_IN_ID,
+ IFLA_BRIDGE_MRP_IN_STATE_STATE,
+ __IFLA_BRIDGE_MRP_IN_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_IN_STATE_MAX (__IFLA_BRIDGE_MRP_IN_STATE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_IN_ROLE_UNSPEC,
+ IFLA_BRIDGE_MRP_IN_ROLE_RING_ID,
+ IFLA_BRIDGE_MRP_IN_ROLE_IN_ID,
+ IFLA_BRIDGE_MRP_IN_ROLE_ROLE,
+ IFLA_BRIDGE_MRP_IN_ROLE_I_IFINDEX,
+ __IFLA_BRIDGE_MRP_IN_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_IN_ROLE_MAX (__IFLA_BRIDGE_MRP_IN_ROLE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_START_IN_TEST_UNSPEC,
+ IFLA_BRIDGE_MRP_START_IN_TEST_IN_ID,
+ IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL,
+ IFLA_BRIDGE_MRP_START_IN_TEST_MAX_MISS,
+ IFLA_BRIDGE_MRP_START_IN_TEST_PERIOD,
+ __IFLA_BRIDGE_MRP_START_IN_TEST_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_START_IN_TEST_MAX (__IFLA_BRIDGE_MRP_START_IN_TEST_MAX - 1)
+
+struct br_mrp_instance {
+ __u32 ring_id;
+ __u32 p_ifindex;
+ __u32 s_ifindex;
+ __u16 prio;
+};
+
+struct br_mrp_ring_state {
+ __u32 ring_id;
+ __u32 ring_state;
+};
+
+struct br_mrp_ring_role {
+ __u32 ring_id;
+ __u32 ring_role;
+};
+
+struct br_mrp_start_test {
+ __u32 ring_id;
+ __u32 interval;
+ __u32 max_miss;
+ __u32 period;
+ __u32 monitor;
+};
+
+struct br_mrp_in_state {
+ __u32 in_state;
+ __u16 in_id;
+};
+
+struct br_mrp_in_role {
+ __u32 ring_id;
+ __u32 in_role;
+ __u32 i_ifindex;
+ __u16 in_id;
+};
+
+struct br_mrp_start_in_test {
+ __u32 interval;
+ __u32 max_miss;
+ __u32 period;
+ __u16 in_id;
+};
+
+enum {
+ IFLA_BRIDGE_CFM_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_CREATE,
+ IFLA_BRIDGE_CFM_MEP_DELETE,
+ IFLA_BRIDGE_CFM_MEP_CONFIG,
+ IFLA_BRIDGE_CFM_CC_CONFIG,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE,
+ IFLA_BRIDGE_CFM_CC_RDI,
+ IFLA_BRIDGE_CFM_CC_CCM_TX,
+ IFLA_BRIDGE_CFM_MEP_CREATE_INFO,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_INFO,
+ IFLA_BRIDGE_CFM_CC_CONFIG_INFO,
+ IFLA_BRIDGE_CFM_CC_RDI_INFO,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_INFO,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO,
+ IFLA_BRIDGE_CFM_MEP_STATUS_INFO,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO,
+ __IFLA_BRIDGE_CFM_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MAX (__IFLA_BRIDGE_CFM_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE,
+ IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN,
+ IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION,
+ IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX,
+ __IFLA_BRIDGE_CFM_MEP_CREATE_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_CREATE_MAX (__IFLA_BRIDGE_CFM_MEP_CREATE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE,
+ __IFLA_BRIDGE_CFM_MEP_DELETE_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_DELETE_MAX (__IFLA_BRIDGE_CFM_MEP_DELETE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL,
+ IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID,
+ __IFLA_BRIDGE_CFM_MEP_CONFIG_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_CONFIG_MAX (__IFLA_BRIDGE_CFM_MEP_CONFIG_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE,
+ IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL,
+ IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID,
+ __IFLA_BRIDGE_CFM_CC_CONFIG_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_CONFIG_MAX (__IFLA_BRIDGE_CFM_CC_CONFIG_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_PEER_MEPID,
+ __IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX (__IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_RDI_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_RDI_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_RDI_RDI,
+ __IFLA_BRIDGE_CFM_CC_RDI_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_RDI_MAX (__IFLA_BRIDGE_CFM_CC_RDI_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV,
+ IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE,
+ __IFLA_BRIDGE_CFM_CC_CCM_TX_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_CCM_TX_MAX (__IFLA_BRIDGE_CFM_CC_CCM_TX_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_MEP_STATUS_UNSPEC,
+ IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE,
+ IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN,
+ IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN,
+ IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN,
+ __IFLA_BRIDGE_CFM_MEP_STATUS_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_MEP_STATUS_MAX (__IFLA_BRIDGE_CFM_MEP_STATUS_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_UNSPEC,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN,
+ __IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX,
+};
+
+#define IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX (__IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MST_UNSPEC,
+ IFLA_BRIDGE_MST_ENTRY,
+ __IFLA_BRIDGE_MST_MAX,
+};
+#define IFLA_BRIDGE_MST_MAX (__IFLA_BRIDGE_MST_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MST_ENTRY_UNSPEC,
+ IFLA_BRIDGE_MST_ENTRY_MSTI,
+ IFLA_BRIDGE_MST_ENTRY_STATE,
+ __IFLA_BRIDGE_MST_ENTRY_MAX,
+};
+#define IFLA_BRIDGE_MST_ENTRY_MAX (__IFLA_BRIDGE_MST_ENTRY_MAX - 1)
+
+struct bridge_stp_xstats {
+ __u64 transition_blk;
+ __u64 transition_fwd;
+ __u64 rx_bpdu;
+ __u64 tx_bpdu;
+ __u64 rx_tcn;
+ __u64 tx_tcn;
+};
+
+/* Bridge vlan RTM header */
+struct br_vlan_msg {
+ __u8 family;
+ __u8 reserved1;
+ __u16 reserved2;
+ __u32 ifindex;
+};
+
+enum {
+ BRIDGE_VLANDB_DUMP_UNSPEC,
+ BRIDGE_VLANDB_DUMP_FLAGS,
+ __BRIDGE_VLANDB_DUMP_MAX,
+};
+#define BRIDGE_VLANDB_DUMP_MAX (__BRIDGE_VLANDB_DUMP_MAX - 1)
+
+/* flags used in BRIDGE_VLANDB_DUMP_FLAGS attribute to affect dumps */
+#define BRIDGE_VLANDB_DUMPF_STATS (1 << 0) /* Include stats in the dump */
+#define BRIDGE_VLANDB_DUMPF_GLOBAL (1 << 1) /* Dump global vlan options only */
+
+/* Bridge vlan RTM attributes
+ * [BRIDGE_VLANDB_ENTRY] = {
+ * [BRIDGE_VLANDB_ENTRY_INFO]
+ * ...
+ * }
+ * [BRIDGE_VLANDB_GLOBAL_OPTIONS] = {
+ * [BRIDGE_VLANDB_GOPTS_ID]
+ * ...
+ * }
+ */
+enum {
+ BRIDGE_VLANDB_UNSPEC,
+ BRIDGE_VLANDB_ENTRY,
+ BRIDGE_VLANDB_GLOBAL_OPTIONS,
+ __BRIDGE_VLANDB_MAX,
+};
+#define BRIDGE_VLANDB_MAX (__BRIDGE_VLANDB_MAX - 1)
+
+enum {
+ BRIDGE_VLANDB_ENTRY_UNSPEC,
+ BRIDGE_VLANDB_ENTRY_INFO,
+ BRIDGE_VLANDB_ENTRY_RANGE,
+ BRIDGE_VLANDB_ENTRY_STATE,
+ BRIDGE_VLANDB_ENTRY_TUNNEL_INFO,
+ BRIDGE_VLANDB_ENTRY_STATS,
+ BRIDGE_VLANDB_ENTRY_MCAST_ROUTER,
+ BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS,
+ BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS,
+ BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS,
+ __BRIDGE_VLANDB_ENTRY_MAX,
+};
+#define BRIDGE_VLANDB_ENTRY_MAX (__BRIDGE_VLANDB_ENTRY_MAX - 1)
+
+/* [BRIDGE_VLANDB_ENTRY] = {
+ * [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = {
+ * [BRIDGE_VLANDB_TINFO_ID]
+ * ...
+ * }
+ * }
+ */
+enum {
+ BRIDGE_VLANDB_TINFO_UNSPEC,
+ BRIDGE_VLANDB_TINFO_ID,
+ BRIDGE_VLANDB_TINFO_CMD,
+ __BRIDGE_VLANDB_TINFO_MAX,
+};
+#define BRIDGE_VLANDB_TINFO_MAX (__BRIDGE_VLANDB_TINFO_MAX - 1)
+
+/* [BRIDGE_VLANDB_ENTRY] = {
+ * [BRIDGE_VLANDB_ENTRY_STATS] = {
+ * [BRIDGE_VLANDB_STATS_RX_BYTES]
+ * ...
+ * }
+ * ...
+ * }
+ */
+enum {
+ BRIDGE_VLANDB_STATS_UNSPEC,
+ BRIDGE_VLANDB_STATS_RX_BYTES,
+ BRIDGE_VLANDB_STATS_RX_PACKETS,
+ BRIDGE_VLANDB_STATS_TX_BYTES,
+ BRIDGE_VLANDB_STATS_TX_PACKETS,
+ BRIDGE_VLANDB_STATS_PAD,
+ __BRIDGE_VLANDB_STATS_MAX,
+};
+#define BRIDGE_VLANDB_STATS_MAX (__BRIDGE_VLANDB_STATS_MAX - 1)
+
+enum {
+ BRIDGE_VLANDB_GOPTS_UNSPEC,
+ BRIDGE_VLANDB_GOPTS_ID,
+ BRIDGE_VLANDB_GOPTS_RANGE,
+ BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING,
+ BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION,
+ BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION,
+ BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT,
+ BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT,
+ BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL,
+ BRIDGE_VLANDB_GOPTS_PAD,
+ BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL,
+ BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL,
+ BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL,
+ BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL,
+ BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL,
+ BRIDGE_VLANDB_GOPTS_MCAST_QUERIER,
+ BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS,
+ BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_STATE,
+ BRIDGE_VLANDB_GOPTS_MSTI,
+ __BRIDGE_VLANDB_GOPTS_MAX
+};
+#define BRIDGE_VLANDB_GOPTS_MAX (__BRIDGE_VLANDB_GOPTS_MAX - 1)
+
+/* Bridge multicast database attributes
+ * [MDBA_MDB] = {
+ * [MDBA_MDB_ENTRY] = {
+ * [MDBA_MDB_ENTRY_INFO] {
+ * struct br_mdb_entry
+ * [MDBA_MDB_EATTR attributes]
+ * }
+ * }
+ * }
+ * [MDBA_ROUTER] = {
+ * [MDBA_ROUTER_PORT] = {
+ * u32 ifindex
+ * [MDBA_ROUTER_PATTR attributes]
+ * }
+ * }
+ */
+enum {
+ MDBA_UNSPEC,
+ MDBA_MDB,
+ MDBA_ROUTER,
+ __MDBA_MAX,
+};
+#define MDBA_MAX (__MDBA_MAX - 1)
+
+enum {
+ MDBA_MDB_UNSPEC,
+ MDBA_MDB_ENTRY,
+ __MDBA_MDB_MAX,
+};
+#define MDBA_MDB_MAX (__MDBA_MDB_MAX - 1)
+
+enum {
+ MDBA_MDB_ENTRY_UNSPEC,
+ MDBA_MDB_ENTRY_INFO,
+ __MDBA_MDB_ENTRY_MAX,
+};
+#define MDBA_MDB_ENTRY_MAX (__MDBA_MDB_ENTRY_MAX - 1)
+
+/* per mdb entry additional attributes */
+enum {
+ MDBA_MDB_EATTR_UNSPEC,
+ MDBA_MDB_EATTR_TIMER,
+ MDBA_MDB_EATTR_SRC_LIST,
+ MDBA_MDB_EATTR_GROUP_MODE,
+ MDBA_MDB_EATTR_SOURCE,
+ MDBA_MDB_EATTR_RTPROT,
+ MDBA_MDB_EATTR_DST,
+ MDBA_MDB_EATTR_DST_PORT,
+ MDBA_MDB_EATTR_VNI,
+ MDBA_MDB_EATTR_IFINDEX,
+ MDBA_MDB_EATTR_SRC_VNI,
+ __MDBA_MDB_EATTR_MAX
+};
+#define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1)
+
+/* per mdb entry source */
+enum {
+ MDBA_MDB_SRCLIST_UNSPEC,
+ MDBA_MDB_SRCLIST_ENTRY,
+ __MDBA_MDB_SRCLIST_MAX
+};
+#define MDBA_MDB_SRCLIST_MAX (__MDBA_MDB_SRCLIST_MAX - 1)
+
+/* per mdb entry per source attributes
+ * these are embedded in MDBA_MDB_SRCLIST_ENTRY
+ */
+enum {
+ MDBA_MDB_SRCATTR_UNSPEC,
+ MDBA_MDB_SRCATTR_ADDRESS,
+ MDBA_MDB_SRCATTR_TIMER,
+ __MDBA_MDB_SRCATTR_MAX
+};
+#define MDBA_MDB_SRCATTR_MAX (__MDBA_MDB_SRCATTR_MAX - 1)
+
+/* multicast router types */
+enum {
+ MDB_RTR_TYPE_DISABLED,
+ MDB_RTR_TYPE_TEMP_QUERY,
+ MDB_RTR_TYPE_PERM,
+ MDB_RTR_TYPE_TEMP
+};
+
+enum {
+ MDBA_ROUTER_UNSPEC,
+ MDBA_ROUTER_PORT,
+ __MDBA_ROUTER_MAX,
+};
+#define MDBA_ROUTER_MAX (__MDBA_ROUTER_MAX - 1)
+
+/* router port attributes */
+enum {
+ MDBA_ROUTER_PATTR_UNSPEC,
+ MDBA_ROUTER_PATTR_TIMER,
+ MDBA_ROUTER_PATTR_TYPE,
+ MDBA_ROUTER_PATTR_INET_TIMER,
+ MDBA_ROUTER_PATTR_INET6_TIMER,
+ MDBA_ROUTER_PATTR_VID,
+ __MDBA_ROUTER_PATTR_MAX
+};
+#define MDBA_ROUTER_PATTR_MAX (__MDBA_ROUTER_PATTR_MAX - 1)
+
+struct br_port_msg {
+ __u8 family;
+ __u32 ifindex;
+};
+
+struct br_mdb_entry {
+ __u32 ifindex;
+#define MDB_TEMPORARY 0
+#define MDB_PERMANENT 1
+ __u8 state;
+#define MDB_FLAGS_OFFLOAD (1 << 0)
+#define MDB_FLAGS_FAST_LEAVE (1 << 1)
+#define MDB_FLAGS_STAR_EXCL (1 << 2)
+#define MDB_FLAGS_BLOCKED (1 << 3)
+ __u8 flags;
+ __u16 vid;
+ struct {
+ union {
+ __be32 ip4;
+ struct in6_addr ip6;
+ unsigned char mac_addr[ETH_ALEN];
+ } u;
+ __be16 proto;
+ } addr;
+};
+
+enum {
+ MDBA_SET_ENTRY_UNSPEC,
+ MDBA_SET_ENTRY,
+ MDBA_SET_ENTRY_ATTRS,
+ __MDBA_SET_ENTRY_MAX,
+};
+#define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1)
+
+/* [MDBA_GET_ENTRY] = {
+ * struct br_mdb_entry
+ * [MDBA_GET_ENTRY_ATTRS] = {
+ * [MDBE_ATTR_SOURCE]
+ * struct in_addr / struct in6_addr
+ * [MDBE_ATTR_SRC_VNI]
+ * u32
+ * }
+ * }
+ */
+enum {
+ MDBA_GET_ENTRY_UNSPEC,
+ MDBA_GET_ENTRY,
+ MDBA_GET_ENTRY_ATTRS,
+ __MDBA_GET_ENTRY_MAX,
+};
+#define MDBA_GET_ENTRY_MAX (__MDBA_GET_ENTRY_MAX - 1)
+
+/* [MDBA_SET_ENTRY_ATTRS] = {
+ * [MDBE_ATTR_xxx]
+ * ...
+ * }
+ */
+enum {
+ MDBE_ATTR_UNSPEC,
+ MDBE_ATTR_SOURCE,
+ MDBE_ATTR_SRC_LIST,
+ MDBE_ATTR_GROUP_MODE,
+ MDBE_ATTR_RTPROT,
+ MDBE_ATTR_DST,
+ MDBE_ATTR_DST_PORT,
+ MDBE_ATTR_VNI,
+ MDBE_ATTR_IFINDEX,
+ MDBE_ATTR_SRC_VNI,
+ MDBE_ATTR_STATE_MASK,
+ __MDBE_ATTR_MAX,
+};
+#define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1)
+
+/* per mdb entry source */
+enum {
+ MDBE_SRC_LIST_UNSPEC,
+ MDBE_SRC_LIST_ENTRY,
+ __MDBE_SRC_LIST_MAX,
+};
+#define MDBE_SRC_LIST_MAX (__MDBE_SRC_LIST_MAX - 1)
+
+/* per mdb entry per source attributes
+ * these are embedded in MDBE_SRC_LIST_ENTRY
+ */
+enum {
+ MDBE_SRCATTR_UNSPEC,
+ MDBE_SRCATTR_ADDRESS,
+ __MDBE_SRCATTR_MAX,
+};
+#define MDBE_SRCATTR_MAX (__MDBE_SRCATTR_MAX - 1)
+
+/* Embedded inside LINK_XSTATS_TYPE_BRIDGE */
+enum {
+ BRIDGE_XSTATS_UNSPEC,
+ BRIDGE_XSTATS_VLAN,
+ BRIDGE_XSTATS_MCAST,
+ BRIDGE_XSTATS_PAD,
+ BRIDGE_XSTATS_STP,
+ __BRIDGE_XSTATS_MAX
+};
+#define BRIDGE_XSTATS_MAX (__BRIDGE_XSTATS_MAX - 1)
+
+enum {
+ BR_MCAST_DIR_RX,
+ BR_MCAST_DIR_TX,
+ BR_MCAST_DIR_SIZE
+};
+
+/* IGMP/MLD statistics */
+struct br_mcast_stats {
+ __u64 igmp_v1queries[BR_MCAST_DIR_SIZE];
+ __u64 igmp_v2queries[BR_MCAST_DIR_SIZE];
+ __u64 igmp_v3queries[BR_MCAST_DIR_SIZE];
+ __u64 igmp_leaves[BR_MCAST_DIR_SIZE];
+ __u64 igmp_v1reports[BR_MCAST_DIR_SIZE];
+ __u64 igmp_v2reports[BR_MCAST_DIR_SIZE];
+ __u64 igmp_v3reports[BR_MCAST_DIR_SIZE];
+ __u64 igmp_parse_errors;
+
+ __u64 mld_v1queries[BR_MCAST_DIR_SIZE];
+ __u64 mld_v2queries[BR_MCAST_DIR_SIZE];
+ __u64 mld_leaves[BR_MCAST_DIR_SIZE];
+ __u64 mld_v1reports[BR_MCAST_DIR_SIZE];
+ __u64 mld_v2reports[BR_MCAST_DIR_SIZE];
+ __u64 mld_parse_errors;
+
+ __u64 mcast_bytes[BR_MCAST_DIR_SIZE];
+ __u64 mcast_packets[BR_MCAST_DIR_SIZE];
+};
+
+/* bridge boolean options
+ * BR_BOOLOPT_NO_LL_LEARN - disable learning from link-local packets
+ * BR_BOOLOPT_MCAST_VLAN_SNOOPING - control vlan multicast snooping
+ *
+ * IMPORTANT: if adding a new option do not forget to handle
+ * it in br_boolopt_toggle/get and bridge sysfs
+ */
+enum br_boolopt_id {
+ BR_BOOLOPT_NO_LL_LEARN,
+ BR_BOOLOPT_MCAST_VLAN_SNOOPING,
+ BR_BOOLOPT_MST_ENABLE,
+ BR_BOOLOPT_MAX
+};
+
+/* struct br_boolopt_multi - change multiple bridge boolean options
+ *
+ * @optval: new option values (bit per option)
+ * @optmask: options to change (bit per option)
+ */
+struct br_boolopt_multi {
+ __u32 optval;
+ __u32 optmask;
+};
+
+enum {
+ BRIDGE_QUERIER_UNSPEC,
+ BRIDGE_QUERIER_IP_ADDRESS,
+ BRIDGE_QUERIER_IP_PORT,
+ BRIDGE_QUERIER_IP_OTHER_TIMER,
+ BRIDGE_QUERIER_PAD,
+ BRIDGE_QUERIER_IPV6_ADDRESS,
+ BRIDGE_QUERIER_IPV6_PORT,
+ BRIDGE_QUERIER_IPV6_OTHER_TIMER,
+ __BRIDGE_QUERIER_MAX
+};
+#define BRIDGE_QUERIER_MAX (__BRIDGE_QUERIER_MAX - 1)
+#endif /* _LINUX_IF_BRIDGE_H */
diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
new file mode 100644
index 0000000..a1aff8e
--- /dev/null
+++ b/include/uapi/linux/if_ether.h
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Global definitions for the Ethernet IEEE 802.3 interface.
+ *
+ * Version: @(#)if_ether.h 1.0.1a 02/08/94
+ *
+ * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ * Donald Becker, <becker@super.org>
+ * Alan Cox, <alan@lxorguk.ukuu.org.uk>
+ * Steve Whitehouse, <gw7rrm@eeshack3.swan.ac.uk>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_IF_ETHER_H
+#define _LINUX_IF_ETHER_H
+
+#include <linux/types.h>
+
+/*
+ * IEEE 802.3 Ethernet magic constants. The frame sizes omit the preamble
+ * and FCS/CRC (frame check sequence).
+ */
+
+#define ETH_ALEN 6 /* Octets in one ethernet addr */
+#define ETH_TLEN 2 /* Octets in ethernet type field */
+#define ETH_HLEN 14 /* Total octets in header. */
+#define ETH_ZLEN 60 /* Min. octets in frame sans FCS */
+#define ETH_DATA_LEN 1500 /* Max. octets in payload */
+#define ETH_FRAME_LEN 1514 /* Max. octets in frame sans FCS */
+#define ETH_FCS_LEN 4 /* Octets in the FCS */
+
+#define ETH_MIN_MTU 68 /* Min IPv4 MTU per RFC791 */
+#define ETH_MAX_MTU 0xFFFFU /* 65535, same as IP_MAX_MTU */
+
+/*
+ * These are the defined Ethernet Protocol ID's.
+ */
+
+#define ETH_P_LOOP 0x0060 /* Ethernet Loopback packet */
+#define ETH_P_PUP 0x0200 /* Xerox PUP packet */
+#define ETH_P_PUPAT 0x0201 /* Xerox PUP Addr Trans packet */
+#define ETH_P_TSN 0x22F0 /* TSN (IEEE 1722) packet */
+#define ETH_P_ERSPAN2 0x22EB /* ERSPAN version 2 (type III) */
+#define ETH_P_IP 0x0800 /* Internet Protocol packet */
+#define ETH_P_X25 0x0805 /* CCITT X.25 */
+#define ETH_P_ARP 0x0806 /* Address Resolution packet */
+#define ETH_P_BPQ 0x08FF /* G8BPQ AX.25 Ethernet Packet [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_IEEEPUP 0x0a00 /* Xerox IEEE802.3 PUP packet */
+#define ETH_P_IEEEPUPAT 0x0a01 /* Xerox IEEE802.3 PUP Addr Trans packet */
+#define ETH_P_BATMAN 0x4305 /* B.A.T.M.A.N.-Advanced packet [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_DEC 0x6000 /* DEC Assigned proto */
+#define ETH_P_DNA_DL 0x6001 /* DEC DNA Dump/Load */
+#define ETH_P_DNA_RC 0x6002 /* DEC DNA Remote Console */
+#define ETH_P_DNA_RT 0x6003 /* DEC DNA Routing */
+#define ETH_P_LAT 0x6004 /* DEC LAT */
+#define ETH_P_DIAG 0x6005 /* DEC Diagnostics */
+#define ETH_P_CUST 0x6006 /* DEC Customer use */
+#define ETH_P_SCA 0x6007 /* DEC Systems Comms Arch */
+#define ETH_P_TEB 0x6558 /* Trans Ether Bridging */
+#define ETH_P_RARP 0x8035 /* Reverse Addr Res packet */
+#define ETH_P_ATALK 0x809B /* Appletalk DDP */
+#define ETH_P_AARP 0x80F3 /* Appletalk AARP */
+#define ETH_P_8021Q 0x8100 /* 802.1Q VLAN Extended Header */
+#define ETH_P_ERSPAN 0x88BE /* ERSPAN type II */
+#define ETH_P_IPX 0x8137 /* IPX over DIX */
+#define ETH_P_IPV6 0x86DD /* IPv6 over bluebook */
+#define ETH_P_PAUSE 0x8808 /* IEEE Pause frames. See 802.3 31B */
+#define ETH_P_SLOW 0x8809 /* Slow Protocol. See 802.3ad 43B */
+#define ETH_P_WCCP 0x883E /* Web-cache coordination protocol
+ * defined in draft-wilson-wrec-wccp-v2-00.txt */
+#define ETH_P_MPLS_UC 0x8847 /* MPLS Unicast traffic */
+#define ETH_P_MPLS_MC 0x8848 /* MPLS Multicast traffic */
+#define ETH_P_ATMMPOA 0x884c /* MultiProtocol Over ATM */
+#define ETH_P_PPP_DISC 0x8863 /* PPPoE discovery messages */
+#define ETH_P_PPP_SES 0x8864 /* PPPoE session messages */
+#define ETH_P_LINK_CTL 0x886c /* HPNA, wlan link local tunnel */
+#define ETH_P_ATMFATE 0x8884 /* Frame-based ATM Transport
+ * over Ethernet
+ */
+#define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */
+#define ETH_P_PROFINET 0x8892 /* PROFINET */
+#define ETH_P_REALTEK 0x8899 /* Multiple proprietary protocols */
+#define ETH_P_AOE 0x88A2 /* ATA over Ethernet */
+#define ETH_P_ETHERCAT 0x88A4 /* EtherCAT */
+#define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */
+#define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */
+#define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */
+#define ETH_P_TIPC 0x88CA /* TIPC */
+#define ETH_P_LLDP 0x88CC /* Link Layer Discovery Protocol */
+#define ETH_P_MRP 0x88E3 /* Media Redundancy Protocol */
+#define ETH_P_MACSEC 0x88E5 /* 802.1ae MACsec */
+#define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */
+#define ETH_P_MVRP 0x88F5 /* 802.1Q MVRP */
+#define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */
+#define ETH_P_NCSI 0x88F8 /* NCSI protocol */
+#define ETH_P_PRP 0x88FB /* IEC 62439-3 PRP/HSRv0 */
+#define ETH_P_CFM 0x8902 /* Connectivity Fault Management */
+#define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */
+#define ETH_P_IBOE 0x8915 /* Infiniband over Ethernet */
+#define ETH_P_TDLS 0x890D /* TDLS */
+#define ETH_P_FIP 0x8914 /* FCoE Initialization Protocol */
+#define ETH_P_80221 0x8917 /* IEEE 802.21 Media Independent Handover Protocol */
+#define ETH_P_HSR 0x892F /* IEC 62439-3 HSRv1 */
+#define ETH_P_NSH 0x894F /* Network Service Header */
+#define ETH_P_LOOPBACK 0x9000 /* Ethernet loopback packet, per IEEE 802.3 */
+#define ETH_P_QINQ1 0x9100 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_EDSA 0xDADA /* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_DSA_8021Q 0xDADB /* Fake VLAN Header for DSA [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_DSA_A5PSW 0xE001 /* A5PSW Tag Value [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_IFE 0xED3E /* ForCES inter-FE LFB type */
+#define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */
+
+#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is more than this value
+ * then the frame is Ethernet II. Else it is 802.3 */
+
+/*
+ * Non DIX types. Won't clash for 1500 types.
+ */
+
+#define ETH_P_802_3 0x0001 /* Dummy type for 802.3 frames */
+#define ETH_P_AX25 0x0002 /* Dummy protocol id for AX.25 */
+#define ETH_P_ALL 0x0003 /* Every packet (be careful!!!) */
+#define ETH_P_802_2 0x0004 /* 802.2 frames */
+#define ETH_P_SNAP 0x0005 /* Internal only */
+#define ETH_P_DDCMP 0x0006 /* DEC DDCMP: Internal only */
+#define ETH_P_WAN_PPP 0x0007 /* Dummy type for WAN PPP frames*/
+#define ETH_P_PPP_MP 0x0008 /* Dummy type for PPP MP frames */
+#define ETH_P_LOCALTALK 0x0009 /* Localtalk pseudo type */
+#define ETH_P_CAN 0x000C /* CAN: Controller Area Network */
+#define ETH_P_CANFD 0x000D /* CANFD: CAN flexible data rate*/
+#define ETH_P_CANXL 0x000E /* CANXL: eXtended frame Length */
+#define ETH_P_PPPTALK 0x0010 /* Dummy type for Atalk over PPP*/
+#define ETH_P_TR_802_2 0x0011 /* 802.2 frames */
+#define ETH_P_MOBITEX 0x0015 /* Mobitex (kaz@cafe.net) */
+#define ETH_P_CONTROL 0x0016 /* Card specific control frames */
+#define ETH_P_IRDA 0x0017 /* Linux-IrDA */
+#define ETH_P_ECONET 0x0018 /* Acorn Econet */
+#define ETH_P_HDLC 0x0019 /* HDLC frames */
+#define ETH_P_ARCNET 0x001A /* 1A for ArcNet :-) */
+#define ETH_P_DSA 0x001B /* Distributed Switch Arch. */
+#define ETH_P_TRAILER 0x001C /* Trailer switch tagging */
+#define ETH_P_PHONET 0x00F5 /* Nokia Phonet frames */
+#define ETH_P_IEEE802154 0x00F6 /* IEEE802.15.4 frame */
+#define ETH_P_CAIF 0x00F7 /* ST-Ericsson CAIF protocol */
+#define ETH_P_XDSA 0x00F8 /* Multiplexed DSA protocol */
+#define ETH_P_MAP 0x00F9 /* Qualcomm multiplexing and
+ * aggregation protocol
+ */
+#define ETH_P_MCTP 0x00FA /* Management component transport
+ * protocol packets
+ */
+
+/*
+ * This is an Ethernet frame header.
+ */
+
+/* allow libcs like musl to deactivate this, glibc does not implement this. */
+#ifndef __UAPI_DEF_ETHHDR
+#define __UAPI_DEF_ETHHDR 1
+#endif
+
+#if __UAPI_DEF_ETHHDR
+struct ethhdr {
+ unsigned char h_dest[ETH_ALEN]; /* destination eth addr */
+ unsigned char h_source[ETH_ALEN]; /* source ether addr */
+ __be16 h_proto; /* packet type ID field */
+} __attribute__((packed));
+#endif
+
+
+#endif /* _LINUX_IF_ETHER_H */
diff --git a/include/uapi/linux/if_infiniband.h b/include/uapi/linux/if_infiniband.h
new file mode 100644
index 0000000..0fc33bf
--- /dev/null
+++ b/include/uapi/linux/if_infiniband.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
+/*
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available at
+ * <http://www.fsf.org/copyleft/gpl.html>, or the OpenIB.org BSD
+ * license, available in the LICENSE.TXT file accompanying this
+ * software. These details are also available at
+ * <http://www.openfabrics.org/software_license.htm>.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * Copyright (c) 2004 Topspin Communications. All rights reserved.
+ *
+ * $Id$
+ */
+
+#ifndef _LINUX_IF_INFINIBAND_H
+#define _LINUX_IF_INFINIBAND_H
+
+#define INFINIBAND_ALEN 20 /* Octets in IPoIB HW addr */
+
+#endif /* _LINUX_IF_INFINIBAND_H */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
new file mode 100644
index 0000000..d17271f
--- /dev/null
+++ b/include/uapi/linux/if_link.h
@@ -0,0 +1,1956 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_IF_LINK_H
+#define _LINUX_IF_LINK_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+/* This struct should be in sync with struct rtnl_link_stats64 */
+struct rtnl_link_stats {
+ __u32 rx_packets;
+ __u32 tx_packets;
+ __u32 rx_bytes;
+ __u32 tx_bytes;
+ __u32 rx_errors;
+ __u32 tx_errors;
+ __u32 rx_dropped;
+ __u32 tx_dropped;
+ __u32 multicast;
+ __u32 collisions;
+ /* detailed rx_errors: */
+ __u32 rx_length_errors;
+ __u32 rx_over_errors;
+ __u32 rx_crc_errors;
+ __u32 rx_frame_errors;
+ __u32 rx_fifo_errors;
+ __u32 rx_missed_errors;
+
+ /* detailed tx_errors */
+ __u32 tx_aborted_errors;
+ __u32 tx_carrier_errors;
+ __u32 tx_fifo_errors;
+ __u32 tx_heartbeat_errors;
+ __u32 tx_window_errors;
+
+ /* for cslip etc */
+ __u32 rx_compressed;
+ __u32 tx_compressed;
+
+ __u32 rx_nohandler;
+};
+
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ * For hardware interfaces counts all good packets received from the device
+ * by the host, including packets which host had to drop at various stages
+ * of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ * For hardware interfaces counts packets which host was able to successfully
+ * hand over to the device, which does not necessarily mean that packets
+ * had been successfully transmitted out of the device, only that device
+ * acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ * For IEEE 802.3 devices should count the length of Ethernet Frames
+ * excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ * For IEEE 802.3 devices should count the length of Ethernet Frames
+ * excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ * This counter must include events counted by @rx_length_errors,
+ * @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ * counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ * This counter must include events counter by @tx_aborted_errors,
+ * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ * @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ * e.g. due to lack of resources or unsupported protocol.
+ * For hardware interfaces this counter may include packets discarded
+ * due to L2 address filtering but should not include packets dropped
+ * by the device due to buffer exhaustion which are counted separately in
+ * @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ * e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ * For hardware interfaces this statistic is commonly calculated
+ * at the device level (unlike @rx_packets) and therefore may include
+ * packets which did not reach the host.
+ *
+ * For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ * - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter should be equivalent to a sum
+ * of the following attributes:
+ *
+ * - 30.3.1.1.23 aInRangeLengthErrors
+ * - 30.3.1.1.24 aOutOfRangeLengthField
+ * - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ * Historically the count of overflow events. Such events may be
+ * reported in the receive descriptors or via interrupts, and may
+ * not correspond one-to-one with dropped packets.
+ *
+ * The recommended interpretation for high speed interfaces is -
+ * number of packets dropped because they did not fit into buffers
+ * provided by the host, e.g. packets larger than MTU or next buffer
+ * in the ring was not available for a scatter transfer.
+ *
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * This statistics was historically used interchangeably with
+ * @rx_fifo_errors.
+ *
+ * This statistic corresponds to hardware events and is not commonly used
+ * on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ * - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ * - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ * Historically the count of overflow events. Those events may be
+ * reported in the receive descriptors or via interrupts, and may
+ * not correspond one-to-one with dropped packets.
+ *
+ * This statistics was used interchangeably with @rx_over_errors.
+ * Not recommended for use in drivers for high speed interfaces.
+ *
+ * This statistic is used on software devices, e.g. to count software
+ * packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ * Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ * Counts number of packets dropped by the device due to lack
+ * of buffer space. This usually indicates that the host interface
+ * is slower than the network interface, or host is not keeping up
+ * with the receive packet rate.
+ *
+ * This statistic corresponds to hardware events and is not used
+ * on software devices.
+ *
+ * @tx_aborted_errors:
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ * For IEEE 802.3 devices capable of half-duplex operation this counter
+ * must be equivalent to:
+ *
+ * - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ * High speed interfaces may use this counter as a general device
+ * discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ * of carrier during transmission.
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ * - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ * FIFO underrun / underflow. This condition occurs when the device
+ * begins transmission of a frame but is unable to deliver the
+ * entire frame to the transmitter in time for transmission.
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ * old half-duplex Ethernet.
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices possibly equivalent to:
+ *
+ * - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ * to late collisions (for Ethernet - after the first 64B of transmission).
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ * - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ * This counters is only meaningful for interfaces which support
+ * packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ * This counters is only meaningful for interfaces which support
+ * packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ * but dropped by the networking stack because the device is
+ * not designated to receive packets (e.g. backup link in a bond).
+ *
+ * @rx_otherhost_dropped: Number of packets dropped due to mismatch
+ * in destination MAC address.
+ */
+struct rtnl_link_stats64 {
+ __u64 rx_packets;
+ __u64 tx_packets;
+ __u64 rx_bytes;
+ __u64 tx_bytes;
+ __u64 rx_errors;
+ __u64 tx_errors;
+ __u64 rx_dropped;
+ __u64 tx_dropped;
+ __u64 multicast;
+ __u64 collisions;
+
+ /* detailed rx_errors: */
+ __u64 rx_length_errors;
+ __u64 rx_over_errors;
+ __u64 rx_crc_errors;
+ __u64 rx_frame_errors;
+ __u64 rx_fifo_errors;
+ __u64 rx_missed_errors;
+
+ /* detailed tx_errors */
+ __u64 tx_aborted_errors;
+ __u64 tx_carrier_errors;
+ __u64 tx_fifo_errors;
+ __u64 tx_heartbeat_errors;
+ __u64 tx_window_errors;
+
+ /* for cslip etc */
+ __u64 rx_compressed;
+ __u64 tx_compressed;
+ __u64 rx_nohandler;
+
+ __u64 rx_otherhost_dropped;
+};
+
+/* Subset of link stats useful for in-HW collection. Meaning of the fields is as
+ * for struct rtnl_link_stats64.
+ */
+struct rtnl_hw_stats64 {
+ __u64 rx_packets;
+ __u64 tx_packets;
+ __u64 rx_bytes;
+ __u64 tx_bytes;
+ __u64 rx_errors;
+ __u64 tx_errors;
+ __u64 rx_dropped;
+ __u64 tx_dropped;
+ __u64 multicast;
+};
+
+/* The struct should be in sync with struct ifmap */
+struct rtnl_link_ifmap {
+ __u64 mem_start;
+ __u64 mem_end;
+ __u64 base_addr;
+ __u16 irq;
+ __u8 dma;
+ __u8 port;
+};
+
+/*
+ * IFLA_AF_SPEC
+ * Contains nested attributes for address family specific attributes.
+ * Each address family may create a attribute with the address family
+ * number as type and create its own attribute structure in it.
+ *
+ * Example:
+ * [IFLA_AF_SPEC] = {
+ * [AF_INET] = {
+ * [IFLA_INET_CONF] = ...,
+ * },
+ * [AF_INET6] = {
+ * [IFLA_INET6_FLAGS] = ...,
+ * [IFLA_INET6_CONF] = ...,
+ * }
+ * }
+ */
+
+enum {
+ IFLA_UNSPEC,
+ IFLA_ADDRESS,
+ IFLA_BROADCAST,
+ IFLA_IFNAME,
+ IFLA_MTU,
+ IFLA_LINK,
+ IFLA_QDISC,
+ IFLA_STATS,
+ IFLA_COST,
+#define IFLA_COST IFLA_COST
+ IFLA_PRIORITY,
+#define IFLA_PRIORITY IFLA_PRIORITY
+ IFLA_MASTER,
+#define IFLA_MASTER IFLA_MASTER
+ IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */
+#define IFLA_WIRELESS IFLA_WIRELESS
+ IFLA_PROTINFO, /* Protocol specific information for a link */
+#define IFLA_PROTINFO IFLA_PROTINFO
+ IFLA_TXQLEN,
+#define IFLA_TXQLEN IFLA_TXQLEN
+ IFLA_MAP,
+#define IFLA_MAP IFLA_MAP
+ IFLA_WEIGHT,
+#define IFLA_WEIGHT IFLA_WEIGHT
+ IFLA_OPERSTATE,
+ IFLA_LINKMODE,
+ IFLA_LINKINFO,
+#define IFLA_LINKINFO IFLA_LINKINFO
+ IFLA_NET_NS_PID,
+ IFLA_IFALIAS,
+ IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */
+ IFLA_VFINFO_LIST,
+ IFLA_STATS64,
+ IFLA_VF_PORTS,
+ IFLA_PORT_SELF,
+ IFLA_AF_SPEC,
+ IFLA_GROUP, /* Group the device belongs to */
+ IFLA_NET_NS_FD,
+ IFLA_EXT_MASK, /* Extended info mask, VFs, etc */
+ IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */
+#define IFLA_PROMISCUITY IFLA_PROMISCUITY
+ IFLA_NUM_TX_QUEUES,
+ IFLA_NUM_RX_QUEUES,
+ IFLA_CARRIER,
+ IFLA_PHYS_PORT_ID,
+ IFLA_CARRIER_CHANGES,
+ IFLA_PHYS_SWITCH_ID,
+ IFLA_LINK_NETNSID,
+ IFLA_PHYS_PORT_NAME,
+ IFLA_PROTO_DOWN,
+ IFLA_GSO_MAX_SEGS,
+ IFLA_GSO_MAX_SIZE,
+ IFLA_PAD,
+ IFLA_XDP,
+ IFLA_EVENT,
+ IFLA_NEW_NETNSID,
+ IFLA_IF_NETNSID,
+ IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */
+ IFLA_CARRIER_UP_COUNT,
+ IFLA_CARRIER_DOWN_COUNT,
+ IFLA_NEW_IFINDEX,
+ IFLA_MIN_MTU,
+ IFLA_MAX_MTU,
+ IFLA_PROP_LIST,
+ IFLA_ALT_IFNAME, /* Alternative ifname */
+ IFLA_PERM_ADDRESS,
+ IFLA_PROTO_DOWN_REASON,
+
+ /* device (sysfs) name as parent, used instead
+ * of IFLA_LINK where there's no parent netdev
+ */
+ IFLA_PARENT_DEV_NAME,
+ IFLA_PARENT_DEV_BUS_NAME,
+ IFLA_GRO_MAX_SIZE,
+ IFLA_TSO_MAX_SIZE,
+ IFLA_TSO_MAX_SEGS,
+ IFLA_ALLMULTI, /* Allmulti count: > 0 means acts ALLMULTI */
+
+ IFLA_DEVLINK_PORT,
+
+ IFLA_GSO_IPV4_MAX_SIZE,
+ IFLA_GRO_IPV4_MAX_SIZE,
+ IFLA_DPLL_PIN,
+ __IFLA_MAX
+};
+
+
+#define IFLA_MAX (__IFLA_MAX - 1)
+
+enum {
+ IFLA_PROTO_DOWN_REASON_UNSPEC,
+ IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */
+ IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */
+
+ __IFLA_PROTO_DOWN_REASON_CNT,
+ IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1
+};
+
+/* backwards compatibility for userspace */
+#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
+#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg))
+
+enum {
+ IFLA_INET_UNSPEC,
+ IFLA_INET_CONF,
+ __IFLA_INET_MAX,
+};
+
+#define IFLA_INET_MAX (__IFLA_INET_MAX - 1)
+
+/* ifi_flags.
+
+ IFF_* flags.
+
+ The only change is:
+ IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are
+ more not changeable by user. They describe link media
+ characteristics and set by device driver.
+
+ Comments:
+ - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid
+ - If neither of these three flags are set;
+ the interface is NBMA.
+
+ - IFF_MULTICAST does not mean anything special:
+ multicasts can be used on all not-NBMA links.
+ IFF_MULTICAST means that this media uses special encapsulation
+ for multicast frames. Apparently, all IFF_POINTOPOINT and
+ IFF_BROADCAST devices are able to use multicasts too.
+ */
+
+/* IFLA_LINK.
+ For usual devices it is equal ifi_index.
+ If it is a "virtual interface" (f.e. tunnel), ifi_link
+ can point to real physical interface (f.e. for bandwidth calculations),
+ or maybe 0, what means, that real media is unknown (usual
+ for IPIP tunnels, when route to endpoint is allowed to change)
+ */
+
+/* Subtype attributes for IFLA_PROTINFO */
+enum {
+ IFLA_INET6_UNSPEC,
+ IFLA_INET6_FLAGS, /* link flags */
+ IFLA_INET6_CONF, /* sysctl parameters */
+ IFLA_INET6_STATS, /* statistics */
+ IFLA_INET6_MCAST, /* MC things. What of them? */
+ IFLA_INET6_CACHEINFO, /* time values and max reasm size */
+ IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */
+ IFLA_INET6_TOKEN, /* device token */
+ IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */
+ IFLA_INET6_RA_MTU, /* mtu carried in the RA message */
+ __IFLA_INET6_MAX
+};
+
+#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1)
+
+enum in6_addr_gen_mode {
+ IN6_ADDR_GEN_MODE_EUI64,
+ IN6_ADDR_GEN_MODE_NONE,
+ IN6_ADDR_GEN_MODE_STABLE_PRIVACY,
+ IN6_ADDR_GEN_MODE_RANDOM,
+};
+
+/* Bridge section */
+
+/**
+ * DOC: Bridge enum definition
+ *
+ * Please *note* that the timer values in the following section are expected
+ * in clock_t format, which is seconds multiplied by USER_HZ (generally
+ * defined as 100).
+ *
+ * @IFLA_BR_FORWARD_DELAY
+ * The bridge forwarding delay is the time spent in LISTENING state
+ * (before moving to LEARNING) and in LEARNING state (before moving
+ * to FORWARDING). Only relevant if STP is enabled.
+ *
+ * The valid values are between (2 * USER_HZ) and (30 * USER_HZ).
+ * The default value is (15 * USER_HZ).
+ *
+ * @IFLA_BR_HELLO_TIME
+ * The time between hello packets sent by the bridge, when it is a root
+ * bridge or a designated bridge. Only relevant if STP is enabled.
+ *
+ * The valid values are between (1 * USER_HZ) and (10 * USER_HZ).
+ * The default value is (2 * USER_HZ).
+ *
+ * @IFLA_BR_MAX_AGE
+ * The hello packet timeout is the time until another bridge in the
+ * spanning tree is assumed to be dead, after reception of its last hello
+ * message. Only relevant if STP is enabled.
+ *
+ * The valid values are between (6 * USER_HZ) and (40 * USER_HZ).
+ * The default value is (20 * USER_HZ).
+ *
+ * @IFLA_BR_AGEING_TIME
+ * Configure the bridge's FDB entries aging time. It is the time a MAC
+ * address will be kept in the FDB after a packet has been received from
+ * that address. After this time has passed, entries are cleaned up.
+ * Allow values outside the 802.1 standard specification for special cases:
+ *
+ * * 0 - entry never ages (all permanent)
+ * * 1 - entry disappears (no persistence)
+ *
+ * The default value is (300 * USER_HZ).
+ *
+ * @IFLA_BR_STP_STATE
+ * Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off
+ * (*IFLA_BR_STP_STATE* == 0) for this bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_PRIORITY
+ * Set this bridge's spanning tree priority, used during STP root bridge
+ * election.
+ *
+ * The valid values are between 0 and 65535.
+ *
+ * @IFLA_BR_VLAN_FILTERING
+ * Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off
+ * (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not
+ * consider the VLAN tag when handling packets.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_PROTOCOL
+ * Set the protocol used for VLAN filtering.
+ *
+ * The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value
+ * is 0x8100(802.1Q).
+ *
+ * @IFLA_BR_GROUP_FWD_MASK
+ * The group forwarding mask. This is the bitmask that is applied to
+ * decide whether to forward incoming frames destined to link-local
+ * addresses (of the form 01:80:C2:00:00:0X).
+ *
+ * The default value is 0, which means the bridge does not forward any
+ * link-local frames coming on this port.
+ *
+ * @IFLA_BR_ROOT_ID
+ * The bridge root id, read only.
+ *
+ * @IFLA_BR_BRIDGE_ID
+ * The bridge id, read only.
+ *
+ * @IFLA_BR_ROOT_PORT
+ * The bridge root port, read only.
+ *
+ * @IFLA_BR_ROOT_PATH_COST
+ * The bridge root path cost, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE
+ * The bridge topology change, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED
+ * The bridge topology change detected, read only.
+ *
+ * @IFLA_BR_HELLO_TIMER
+ * The bridge hello timer, read only.
+ *
+ * @IFLA_BR_TCN_TIMER
+ * The bridge tcn timer, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_TIMER
+ * The bridge topology change timer, read only.
+ *
+ * @IFLA_BR_GC_TIMER
+ * The bridge gc timer, read only.
+ *
+ * @IFLA_BR_GROUP_ADDR
+ * Set the MAC address of the multicast group this bridge uses for STP.
+ * The address must be a link-local address in standard Ethernet MAC address
+ * format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f].
+ *
+ * The default value is 0.
+ *
+ * @IFLA_BR_FDB_FLUSH
+ * Flush bridge's fdb dynamic entries.
+ *
+ * @IFLA_BR_MCAST_ROUTER
+ * Set bridge's multicast router if IGMP snooping is enabled.
+ * The valid values are:
+ *
+ * * 0 - disabled.
+ * * 1 - automatic (queried).
+ * * 2 - permanently enabled.
+ *
+ * The default value is 1.
+ *
+ * @IFLA_BR_MCAST_SNOOPING
+ * Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off
+ * (*IFLA_BR_MCAST_SNOOPING* == 0).
+ *
+ * The default value is 1.
+ *
+ * @IFLA_BR_MCAST_QUERY_USE_IFADDR
+ * If enabled use the bridge's own IP address as source address for IGMP
+ * queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0
+ * (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0).
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_QUERIER
+ * Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable
+ * (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast
+ * queries by the bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_HASH_ELASTICITY
+ * Set multicast database hash elasticity, It is the maximum chain length in
+ * the multicast hash table. This attribute is *deprecated* and the value
+ * is always 16.
+ *
+ * @IFLA_BR_MCAST_HASH_MAX
+ * Set maximum size of the multicast hash table
+ *
+ * The default value is 4096, the value must be a power of 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_CNT
+ * The Last Member Query Count is the number of Group-Specific Queries
+ * sent before the router assumes there are no local members. The Last
+ * Member Query Count is also the number of Group-and-Source-Specific
+ * Queries sent before the router assumes there are no listeners for a
+ * particular source.
+ *
+ * The default value is 2.
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_CNT
+ * The Startup Query Count is the number of Queries sent out on startup,
+ * separated by the Startup Query Interval.
+ *
+ * The default value is 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_INTVL
+ * The Last Member Query Interval is the Max Response Time inserted into
+ * Group-Specific Queries sent in response to Leave Group messages, and
+ * is also the amount of time between Group-Specific Query messages.
+ *
+ * The default value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_MEMBERSHIP_INTVL
+ * The interval after which the bridge will leave a group, if no membership
+ * reports for this group are received.
+ *
+ * The default value is (260 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERIER_INTVL
+ * The interval between queries sent by other routers. if no queries are
+ * seen after this delay has passed, the bridge will start to send its own
+ * queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled).
+ *
+ * The default value is (255 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_INTVL
+ * The Query Interval is the interval between General Queries sent by
+ * the Querier.
+ *
+ * The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL
+ * The Max Response Time used to calculate the Max Resp Code inserted
+ * into the periodic General Queries.
+ *
+ * The default value is (10 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL
+ * The interval between queries in the startup phase.
+ *
+ * The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_NF_CALL_IPTABLES
+ * Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0)
+ * iptables hooks on the bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_IP6TABLES
+ * Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0)
+ * ip6tables hooks on the bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_ARPTABLES
+ * Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0)
+ * arptables hooks on the bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_DEFAULT_PVID
+ * VLAN ID applied to untagged and priority-tagged incoming packets.
+ *
+ * The default value is 1. Setting to the special value 0 makes all ports of
+ * this bridge not have a PVID by default, which means that they will
+ * not accept VLAN-untagged traffic.
+ *
+ * @IFLA_BR_PAD
+ * Bridge attribute padding type for netlink message.
+ *
+ * @IFLA_BR_VLAN_STATS_ENABLED
+ * Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable
+ * (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_STATS_ENABLED
+ * Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable
+ * (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats
+ * accounting.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_IGMP_VERSION
+ * Set the IGMP version.
+ *
+ * The valid values are 2 and 3. The default value is 2.
+ *
+ * @IFLA_BR_MCAST_MLD_VERSION
+ * Set the MLD version.
+ *
+ * The valid values are 1 and 2. The default value is 1.
+ *
+ * @IFLA_BR_VLAN_STATS_PER_PORT
+ * Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable
+ * (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting.
+ * Can be changed only when there are no port VLANs configured.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MULTI_BOOLOPT
+ * The multi_boolopt is used to control new boolean options to avoid adding
+ * new netlink attributes. You can look at ``enum br_boolopt_id`` for those
+ * options.
+ *
+ * @IFLA_BR_MCAST_QUERIER_STATE
+ * Bridge mcast querier states, read only.
+ *
+ * @IFLA_BR_FDB_N_LEARNED
+ * The number of dynamically learned FDB entries for the current bridge,
+ * read only.
+ *
+ * @IFLA_BR_FDB_MAX_LEARNED
+ * Set the number of max dynamically learned FDB entries for the current
+ * bridge.
+ */
+enum {
+ IFLA_BR_UNSPEC,
+ IFLA_BR_FORWARD_DELAY,
+ IFLA_BR_HELLO_TIME,
+ IFLA_BR_MAX_AGE,
+ IFLA_BR_AGEING_TIME,
+ IFLA_BR_STP_STATE,
+ IFLA_BR_PRIORITY,
+ IFLA_BR_VLAN_FILTERING,
+ IFLA_BR_VLAN_PROTOCOL,
+ IFLA_BR_GROUP_FWD_MASK,
+ IFLA_BR_ROOT_ID,
+ IFLA_BR_BRIDGE_ID,
+ IFLA_BR_ROOT_PORT,
+ IFLA_BR_ROOT_PATH_COST,
+ IFLA_BR_TOPOLOGY_CHANGE,
+ IFLA_BR_TOPOLOGY_CHANGE_DETECTED,
+ IFLA_BR_HELLO_TIMER,
+ IFLA_BR_TCN_TIMER,
+ IFLA_BR_TOPOLOGY_CHANGE_TIMER,
+ IFLA_BR_GC_TIMER,
+ IFLA_BR_GROUP_ADDR,
+ IFLA_BR_FDB_FLUSH,
+ IFLA_BR_MCAST_ROUTER,
+ IFLA_BR_MCAST_SNOOPING,
+ IFLA_BR_MCAST_QUERY_USE_IFADDR,
+ IFLA_BR_MCAST_QUERIER,
+ IFLA_BR_MCAST_HASH_ELASTICITY,
+ IFLA_BR_MCAST_HASH_MAX,
+ IFLA_BR_MCAST_LAST_MEMBER_CNT,
+ IFLA_BR_MCAST_STARTUP_QUERY_CNT,
+ IFLA_BR_MCAST_LAST_MEMBER_INTVL,
+ IFLA_BR_MCAST_MEMBERSHIP_INTVL,
+ IFLA_BR_MCAST_QUERIER_INTVL,
+ IFLA_BR_MCAST_QUERY_INTVL,
+ IFLA_BR_MCAST_QUERY_RESPONSE_INTVL,
+ IFLA_BR_MCAST_STARTUP_QUERY_INTVL,
+ IFLA_BR_NF_CALL_IPTABLES,
+ IFLA_BR_NF_CALL_IP6TABLES,
+ IFLA_BR_NF_CALL_ARPTABLES,
+ IFLA_BR_VLAN_DEFAULT_PVID,
+ IFLA_BR_PAD,
+ IFLA_BR_VLAN_STATS_ENABLED,
+ IFLA_BR_MCAST_STATS_ENABLED,
+ IFLA_BR_MCAST_IGMP_VERSION,
+ IFLA_BR_MCAST_MLD_VERSION,
+ IFLA_BR_VLAN_STATS_PER_PORT,
+ IFLA_BR_MULTI_BOOLOPT,
+ IFLA_BR_MCAST_QUERIER_STATE,
+ IFLA_BR_FDB_N_LEARNED,
+ IFLA_BR_FDB_MAX_LEARNED,
+ __IFLA_BR_MAX,
+};
+
+#define IFLA_BR_MAX (__IFLA_BR_MAX - 1)
+
+struct ifla_bridge_id {
+ __u8 prio[2];
+ __u8 addr[6]; /* ETH_ALEN */
+};
+
+/**
+ * DOC: Bridge mode enum definition
+ *
+ * @BRIDGE_MODE_HAIRPIN
+ * Controls whether traffic may be sent back out of the port on which it
+ * was received. This option is also called reflective relay mode, and is
+ * used to support basic VEPA (Virtual Ethernet Port Aggregator)
+ * capabilities. By default, this flag is turned off and the bridge will
+ * not forward traffic back out of the receiving port.
+ */
+enum {
+ BRIDGE_MODE_UNSPEC,
+ BRIDGE_MODE_HAIRPIN,
+};
+
+/**
+ * DOC: Bridge port enum definition
+ *
+ * @IFLA_BRPORT_STATE
+ * The operation state of the port. Here are the valid values.
+ *
+ * * 0 - port is in STP *DISABLED* state. Make this port completely
+ * inactive for STP. This is also called BPDU filter and could be used
+ * to disable STP on an untrusted port, like a leaf virtual device.
+ * The traffic forwarding is also stopped on this port.
+ * * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled
+ * on the bridge. In this state the port listens for STP BPDUs and
+ * drops all other traffic frames.
+ * * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on
+ * the bridge. In this state the port will accept traffic only for the
+ * purpose of updating MAC address tables.
+ * * 3 - port is in STP *FORWARDING* state. Port is fully active.
+ * * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on
+ * the bridge. This state is used during the STP election process.
+ * In this state, port will only process STP BPDUs.
+ *
+ * @IFLA_BRPORT_PRIORITY
+ * The STP port priority. The valid values are between 0 and 255.
+ *
+ * @IFLA_BRPORT_COST
+ * The STP path cost of the port. The valid values are between 1 and 65535.
+ *
+ * @IFLA_BRPORT_MODE
+ * Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details.
+ *
+ * @IFLA_BRPORT_GUARD
+ * Controls whether STP BPDUs will be processed by the bridge port. By
+ * default, the flag is turned off to allow BPDU processing. Turning this
+ * flag on will disable the bridge port if a STP BPDU packet is received.
+ *
+ * If the bridge has Spanning Tree enabled, hostile devices on the network
+ * may send BPDU on a port and cause network failure. Setting *guard on*
+ * will detect and stop this by disabling the port. The port will be
+ * restarted if the link is brought down, or removed and reattached.
+ *
+ * @IFLA_BRPORT_PROTECT
+ * Controls whether a given port is allowed to become a root port or not.
+ * Only used when STP is enabled on the bridge. By default the flag is off.
+ *
+ * This feature is also called root port guard. If BPDU is received from a
+ * leaf (edge) port, it should not be elected as root port. This could
+ * be used if using STP on a bridge and the downstream bridges are not fully
+ * trusted; this prevents a hostile guest from rerouting traffic.
+ *
+ * @IFLA_BRPORT_FAST_LEAVE
+ * This flag allows the bridge to immediately stop multicast traffic
+ * forwarding on a port that receives an IGMP Leave message. It is only used
+ * when IGMP snooping is enabled on the bridge. By default the flag is off.
+ *
+ * @IFLA_BRPORT_LEARNING
+ * Controls whether a given port will learn *source* MAC addresses from
+ * received traffic or not. Also controls whether dynamic FDB entries
+ * (which can also be added by software) will be refreshed by incoming
+ * traffic. By default this flag is on.
+ *
+ * @IFLA_BRPORT_UNICAST_FLOOD
+ * Controls whether unicast traffic for which there is no FDB entry will
+ * be flooded towards this port. By default this flag is on.
+ *
+ * @IFLA_BRPORT_PROXYARP
+ * Enable proxy ARP on this port.
+ *
+ * @IFLA_BRPORT_LEARNING_SYNC
+ * Controls whether a given port will sync MAC addresses learned on device
+ * port to bridge FDB.
+ *
+ * @IFLA_BRPORT_PROXYARP_WIFI
+ * Enable proxy ARP on this port which meets extended requirements by
+ * IEEE 802.11 and Hotspot 2.0 specifications.
+ *
+ * @IFLA_BRPORT_ROOT_ID
+ *
+ * @IFLA_BRPORT_BRIDGE_ID
+ *
+ * @IFLA_BRPORT_DESIGNATED_PORT
+ *
+ * @IFLA_BRPORT_DESIGNATED_COST
+ *
+ * @IFLA_BRPORT_ID
+ *
+ * @IFLA_BRPORT_NO
+ *
+ * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK
+ *
+ * @IFLA_BRPORT_CONFIG_PENDING
+ *
+ * @IFLA_BRPORT_MESSAGE_AGE_TIMER
+ *
+ * @IFLA_BRPORT_FORWARD_DELAY_TIMER
+ *
+ * @IFLA_BRPORT_HOLD_TIMER
+ *
+ * @IFLA_BRPORT_FLUSH
+ * Flush bridge ports' fdb dynamic entries.
+ *
+ * @IFLA_BRPORT_MULTICAST_ROUTER
+ * Configure the port's multicast router presence. A port with
+ * a multicast router will receive all multicast traffic.
+ * The valid values are:
+ *
+ * * 0 disable multicast routers on this port
+ * * 1 let the system detect the presence of routers (default)
+ * * 2 permanently enable multicast traffic forwarding on this port
+ * * 3 enable multicast routers temporarily on this port, not depending
+ * on incoming queries.
+ *
+ * @IFLA_BRPORT_PAD
+ *
+ * @IFLA_BRPORT_MCAST_FLOOD
+ * Controls whether a given port will flood multicast traffic for which
+ * there is no MDB entry. By default this flag is on.
+ *
+ * @IFLA_BRPORT_MCAST_TO_UCAST
+ * Controls whether a given port will replicate packets using unicast
+ * instead of multicast. By default this flag is off.
+ *
+ * This is done by copying the packet per host and changing the multicast
+ * destination MAC to a unicast one accordingly.
+ *
+ * *mcast_to_unicast* works on top of the multicast snooping feature of the
+ * bridge. Which means unicast copies are only delivered to hosts which
+ * are interested in unicast and signaled this via IGMP/MLD reports previously.
+ *
+ * This feature is intended for interface types which have a more reliable
+ * and/or efficient way to deliver unicast packets than broadcast ones
+ * (e.g. WiFi).
+ *
+ * However, it should only be enabled on interfaces where no IGMPv2/MLDv1
+ * report suppression takes place. IGMP/MLD report suppression issue is
+ * usually overcome by the network daemon (supplicant) enabling AP isolation
+ * and by that separating all STAs.
+ *
+ * Delivery of STA-to-STA IP multicast is made possible again by enabling
+ * and utilizing the bridge hairpin mode, which considers the incoming port
+ * as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option).
+ * Hairpin mode is performed after multicast snooping, therefore leading
+ * to only deliver reports to STAs running a multicast router.
+ *
+ * @IFLA_BRPORT_VLAN_TUNNEL
+ * Controls whether vlan to tunnel mapping is enabled on the port.
+ * By default this flag is off.
+ *
+ * @IFLA_BRPORT_BCAST_FLOOD
+ * Controls flooding of broadcast traffic on the given port. By default
+ * this flag is on.
+ *
+ * @IFLA_BRPORT_GROUP_FWD_MASK
+ * Set the group forward mask. This is a bitmask that is applied to
+ * decide whether to forward incoming frames destined to link-local
+ * addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults
+ * to 0, which means the bridge does not forward any link-local frames
+ * coming on this port).
+ *
+ * @IFLA_BRPORT_NEIGH_SUPPRESS
+ * Controls whether neighbor discovery (arp and nd) proxy and suppression
+ * is enabled on the port. By default this flag is off.
+ *
+ * @IFLA_BRPORT_ISOLATED
+ * Controls whether a given port will be isolated, which means it will be
+ * able to communicate with non-isolated ports only. By default this
+ * flag is off.
+ *
+ * @IFLA_BRPORT_BACKUP_PORT
+ * Set a backup port. If the port loses carrier all traffic will be
+ * redirected to the configured backup port. Set the value to 0 to disable
+ * it.
+ *
+ * @IFLA_BRPORT_MRP_RING_OPEN
+ *
+ * @IFLA_BRPORT_MRP_IN_OPEN
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT
+ * The number of per-port EHT hosts limit. The default value is 512.
+ * Setting to 0 is not allowed.
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT
+ * The current number of tracked hosts, read only.
+ *
+ * @IFLA_BRPORT_LOCKED
+ * Controls whether a port will be locked, meaning that hosts behind the
+ * port will not be able to communicate through the port unless an FDB
+ * entry with the unit's MAC address is in the FDB. The common use case is
+ * that hosts are allowed access through authentication with the IEEE 802.1X
+ * protocol or based on whitelists. By default this flag is off.
+ *
+ * Please note that secure 802.1X deployments should always use the
+ * *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its
+ * FDB based on link-local (EAPOL) traffic received on the port.
+ *
+ * @IFLA_BRPORT_MAB
+ * Controls whether a port will use MAC Authentication Bypass (MAB), a
+ * technique through which select MAC addresses may be allowed on a locked
+ * port, without using 802.1X authentication. Packets with an unknown source
+ * MAC address generates a "locked" FDB entry on the incoming bridge port.
+ * The common use case is for user space to react to these bridge FDB
+ * notifications and optionally replace the locked FDB entry with a normal
+ * one, allowing traffic to pass for whitelisted MAC addresses.
+ *
+ * Setting this flag also requires *IFLA_BRPORT_LOCKED* and
+ * *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized
+ * data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic
+ * FDB entries installed by user space (as replacements for the locked FDB
+ * entries) to be refreshed and/or aged out.
+ *
+ * @IFLA_BRPORT_MCAST_N_GROUPS
+ *
+ * @IFLA_BRPORT_MCAST_MAX_GROUPS
+ * Sets the maximum number of MDB entries that can be registered for a
+ * given port. Attempts to register more MDB entries at the port than this
+ * limit allows will be rejected, whether they are done through netlink
+ * (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a
+ * limit of 0 disables the limit. The default value is 0.
+ *
+ * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS
+ * Controls whether neighbor discovery (arp and nd) proxy and suppression is
+ * enabled for a given port. By default this flag is off.
+ *
+ * Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS*
+ * is enabled for a given port.
+ *
+ * @IFLA_BRPORT_BACKUP_NHID
+ * The FDB nexthop object ID to attach to packets being redirected to a
+ * backup port that has VLAN tunnel mapping enabled (via the
+ * *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has
+ * the effect of not attaching any ID.
+ */
+enum {
+ IFLA_BRPORT_UNSPEC,
+ IFLA_BRPORT_STATE, /* Spanning tree state */
+ IFLA_BRPORT_PRIORITY, /* " priority */
+ IFLA_BRPORT_COST, /* " cost */
+ IFLA_BRPORT_MODE, /* mode (hairpin) */
+ IFLA_BRPORT_GUARD, /* bpdu guard */
+ IFLA_BRPORT_PROTECT, /* root port protection */
+ IFLA_BRPORT_FAST_LEAVE, /* multicast fast leave */
+ IFLA_BRPORT_LEARNING, /* mac learning */
+ IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */
+ IFLA_BRPORT_PROXYARP, /* proxy ARP */
+ IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */
+ IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */
+ IFLA_BRPORT_ROOT_ID, /* designated root */
+ IFLA_BRPORT_BRIDGE_ID, /* designated bridge */
+ IFLA_BRPORT_DESIGNATED_PORT,
+ IFLA_BRPORT_DESIGNATED_COST,
+ IFLA_BRPORT_ID,
+ IFLA_BRPORT_NO,
+ IFLA_BRPORT_TOPOLOGY_CHANGE_ACK,
+ IFLA_BRPORT_CONFIG_PENDING,
+ IFLA_BRPORT_MESSAGE_AGE_TIMER,
+ IFLA_BRPORT_FORWARD_DELAY_TIMER,
+ IFLA_BRPORT_HOLD_TIMER,
+ IFLA_BRPORT_FLUSH,
+ IFLA_BRPORT_MULTICAST_ROUTER,
+ IFLA_BRPORT_PAD,
+ IFLA_BRPORT_MCAST_FLOOD,
+ IFLA_BRPORT_MCAST_TO_UCAST,
+ IFLA_BRPORT_VLAN_TUNNEL,
+ IFLA_BRPORT_BCAST_FLOOD,
+ IFLA_BRPORT_GROUP_FWD_MASK,
+ IFLA_BRPORT_NEIGH_SUPPRESS,
+ IFLA_BRPORT_ISOLATED,
+ IFLA_BRPORT_BACKUP_PORT,
+ IFLA_BRPORT_MRP_RING_OPEN,
+ IFLA_BRPORT_MRP_IN_OPEN,
+ IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
+ IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
+ IFLA_BRPORT_LOCKED,
+ IFLA_BRPORT_MAB,
+ IFLA_BRPORT_MCAST_N_GROUPS,
+ IFLA_BRPORT_MCAST_MAX_GROUPS,
+ IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
+ IFLA_BRPORT_BACKUP_NHID,
+ __IFLA_BRPORT_MAX
+};
+#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
+
+struct ifla_cacheinfo {
+ __u32 max_reasm_len;
+ __u32 tstamp; /* ipv6InterfaceTable updated timestamp */
+ __u32 reachable_time;
+ __u32 retrans_time;
+};
+
+enum {
+ IFLA_INFO_UNSPEC,
+ IFLA_INFO_KIND,
+ IFLA_INFO_DATA,
+ IFLA_INFO_XSTATS,
+ IFLA_INFO_SLAVE_KIND,
+ IFLA_INFO_SLAVE_DATA,
+ __IFLA_INFO_MAX,
+};
+
+#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1)
+
+/* VLAN section */
+
+enum {
+ IFLA_VLAN_UNSPEC,
+ IFLA_VLAN_ID,
+ IFLA_VLAN_FLAGS,
+ IFLA_VLAN_EGRESS_QOS,
+ IFLA_VLAN_INGRESS_QOS,
+ IFLA_VLAN_PROTOCOL,
+ __IFLA_VLAN_MAX,
+};
+
+#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1)
+
+struct ifla_vlan_flags {
+ __u32 flags;
+ __u32 mask;
+};
+
+enum {
+ IFLA_VLAN_QOS_UNSPEC,
+ IFLA_VLAN_QOS_MAPPING,
+ __IFLA_VLAN_QOS_MAX
+};
+
+#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1)
+
+struct ifla_vlan_qos_mapping {
+ __u32 from;
+ __u32 to;
+};
+
+/* MACVLAN section */
+enum {
+ IFLA_MACVLAN_UNSPEC,
+ IFLA_MACVLAN_MODE,
+ IFLA_MACVLAN_FLAGS,
+ IFLA_MACVLAN_MACADDR_MODE,
+ IFLA_MACVLAN_MACADDR,
+ IFLA_MACVLAN_MACADDR_DATA,
+ IFLA_MACVLAN_MACADDR_COUNT,
+ IFLA_MACVLAN_BC_QUEUE_LEN,
+ IFLA_MACVLAN_BC_QUEUE_LEN_USED,
+ IFLA_MACVLAN_BC_CUTOFF,
+ __IFLA_MACVLAN_MAX,
+};
+
+#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1)
+
+enum macvlan_mode {
+ MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */
+ MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */
+ MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */
+ MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */
+ MACVLAN_MODE_SOURCE = 16,/* use source MAC address list to assign */
+};
+
+enum macvlan_macaddr_mode {
+ MACVLAN_MACADDR_ADD,
+ MACVLAN_MACADDR_DEL,
+ MACVLAN_MACADDR_FLUSH,
+ MACVLAN_MACADDR_SET,
+};
+
+#define MACVLAN_FLAG_NOPROMISC 1
+#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */
+
+/* VRF section */
+enum {
+ IFLA_VRF_UNSPEC,
+ IFLA_VRF_TABLE,
+ __IFLA_VRF_MAX
+};
+
+#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1)
+
+enum {
+ IFLA_VRF_PORT_UNSPEC,
+ IFLA_VRF_PORT_TABLE,
+ __IFLA_VRF_PORT_MAX
+};
+
+#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1)
+
+/* MACSEC section */
+enum {
+ IFLA_MACSEC_UNSPEC,
+ IFLA_MACSEC_SCI,
+ IFLA_MACSEC_PORT,
+ IFLA_MACSEC_ICV_LEN,
+ IFLA_MACSEC_CIPHER_SUITE,
+ IFLA_MACSEC_WINDOW,
+ IFLA_MACSEC_ENCODING_SA,
+ IFLA_MACSEC_ENCRYPT,
+ IFLA_MACSEC_PROTECT,
+ IFLA_MACSEC_INC_SCI,
+ IFLA_MACSEC_ES,
+ IFLA_MACSEC_SCB,
+ IFLA_MACSEC_REPLAY_PROTECT,
+ IFLA_MACSEC_VALIDATION,
+ IFLA_MACSEC_PAD,
+ IFLA_MACSEC_OFFLOAD,
+ __IFLA_MACSEC_MAX,
+};
+
+#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
+
+/* XFRM section */
+enum {
+ IFLA_XFRM_UNSPEC,
+ IFLA_XFRM_LINK,
+ IFLA_XFRM_IF_ID,
+ IFLA_XFRM_COLLECT_METADATA,
+ __IFLA_XFRM_MAX
+};
+
+#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1)
+
+enum macsec_validation_type {
+ MACSEC_VALIDATE_DISABLED = 0,
+ MACSEC_VALIDATE_CHECK = 1,
+ MACSEC_VALIDATE_STRICT = 2,
+ __MACSEC_VALIDATE_END,
+ MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1,
+};
+
+enum macsec_offload {
+ MACSEC_OFFLOAD_OFF = 0,
+ MACSEC_OFFLOAD_PHY = 1,
+ MACSEC_OFFLOAD_MAC = 2,
+ __MACSEC_OFFLOAD_END,
+ MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1,
+};
+
+/* IPVLAN section */
+enum {
+ IFLA_IPVLAN_UNSPEC,
+ IFLA_IPVLAN_MODE,
+ IFLA_IPVLAN_FLAGS,
+ __IFLA_IPVLAN_MAX
+};
+
+#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1)
+
+enum ipvlan_mode {
+ IPVLAN_MODE_L2 = 0,
+ IPVLAN_MODE_L3,
+ IPVLAN_MODE_L3S,
+ IPVLAN_MODE_MAX
+};
+
+#define IPVLAN_F_PRIVATE 0x01
+#define IPVLAN_F_VEPA 0x02
+
+/* Tunnel RTM header */
+struct tunnel_msg {
+ __u8 family;
+ __u8 flags;
+ __u16 reserved2;
+ __u32 ifindex;
+};
+
+/* netkit section */
+enum netkit_action {
+ NETKIT_NEXT = -1,
+ NETKIT_PASS = 0,
+ NETKIT_DROP = 2,
+ NETKIT_REDIRECT = 7,
+};
+
+enum netkit_mode {
+ NETKIT_L2,
+ NETKIT_L3,
+};
+
+enum {
+ IFLA_NETKIT_UNSPEC,
+ IFLA_NETKIT_PEER_INFO,
+ IFLA_NETKIT_PRIMARY,
+ IFLA_NETKIT_POLICY,
+ IFLA_NETKIT_PEER_POLICY,
+ IFLA_NETKIT_MODE,
+ __IFLA_NETKIT_MAX,
+};
+#define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1)
+
+/* VXLAN section */
+
+/* include statistics in the dump */
+#define TUNNEL_MSG_FLAG_STATS 0x01
+
+#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS
+
+/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */
+enum {
+ VNIFILTER_ENTRY_STATS_UNSPEC,
+ VNIFILTER_ENTRY_STATS_RX_BYTES,
+ VNIFILTER_ENTRY_STATS_RX_PKTS,
+ VNIFILTER_ENTRY_STATS_RX_DROPS,
+ VNIFILTER_ENTRY_STATS_RX_ERRORS,
+ VNIFILTER_ENTRY_STATS_TX_BYTES,
+ VNIFILTER_ENTRY_STATS_TX_PKTS,
+ VNIFILTER_ENTRY_STATS_TX_DROPS,
+ VNIFILTER_ENTRY_STATS_TX_ERRORS,
+ VNIFILTER_ENTRY_STATS_PAD,
+ __VNIFILTER_ENTRY_STATS_MAX
+};
+#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1)
+
+enum {
+ VXLAN_VNIFILTER_ENTRY_UNSPEC,
+ VXLAN_VNIFILTER_ENTRY_START,
+ VXLAN_VNIFILTER_ENTRY_END,
+ VXLAN_VNIFILTER_ENTRY_GROUP,
+ VXLAN_VNIFILTER_ENTRY_GROUP6,
+ VXLAN_VNIFILTER_ENTRY_STATS,
+ __VXLAN_VNIFILTER_ENTRY_MAX
+};
+#define VXLAN_VNIFILTER_ENTRY_MAX (__VXLAN_VNIFILTER_ENTRY_MAX - 1)
+
+enum {
+ VXLAN_VNIFILTER_UNSPEC,
+ VXLAN_VNIFILTER_ENTRY,
+ __VXLAN_VNIFILTER_MAX
+};
+#define VXLAN_VNIFILTER_MAX (__VXLAN_VNIFILTER_MAX - 1)
+
+enum {
+ IFLA_VXLAN_UNSPEC,
+ IFLA_VXLAN_ID,
+ IFLA_VXLAN_GROUP, /* group or remote address */
+ IFLA_VXLAN_LINK,
+ IFLA_VXLAN_LOCAL,
+ IFLA_VXLAN_TTL,
+ IFLA_VXLAN_TOS,
+ IFLA_VXLAN_LEARNING,
+ IFLA_VXLAN_AGEING,
+ IFLA_VXLAN_LIMIT,
+ IFLA_VXLAN_PORT_RANGE, /* source port */
+ IFLA_VXLAN_PROXY,
+ IFLA_VXLAN_RSC,
+ IFLA_VXLAN_L2MISS,
+ IFLA_VXLAN_L3MISS,
+ IFLA_VXLAN_PORT, /* destination port */
+ IFLA_VXLAN_GROUP6,
+ IFLA_VXLAN_LOCAL6,
+ IFLA_VXLAN_UDP_CSUM,
+ IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
+ IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
+ IFLA_VXLAN_REMCSUM_TX,
+ IFLA_VXLAN_REMCSUM_RX,
+ IFLA_VXLAN_GBP,
+ IFLA_VXLAN_REMCSUM_NOPARTIAL,
+ IFLA_VXLAN_COLLECT_METADATA,
+ IFLA_VXLAN_LABEL,
+ IFLA_VXLAN_GPE,
+ IFLA_VXLAN_TTL_INHERIT,
+ IFLA_VXLAN_DF,
+ IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
+ IFLA_VXLAN_LOCALBYPASS,
+ IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
+ __IFLA_VXLAN_MAX
+};
+#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
+
+struct ifla_vxlan_port_range {
+ __be16 low;
+ __be16 high;
+};
+
+enum ifla_vxlan_df {
+ VXLAN_DF_UNSET = 0,
+ VXLAN_DF_SET,
+ VXLAN_DF_INHERIT,
+ __VXLAN_DF_END,
+ VXLAN_DF_MAX = __VXLAN_DF_END - 1,
+};
+
+enum ifla_vxlan_label_policy {
+ VXLAN_LABEL_FIXED = 0,
+ VXLAN_LABEL_INHERIT = 1,
+ __VXLAN_LABEL_END,
+ VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1,
+};
+
+/* GENEVE section */
+enum {
+ IFLA_GENEVE_UNSPEC,
+ IFLA_GENEVE_ID,
+ IFLA_GENEVE_REMOTE,
+ IFLA_GENEVE_TTL,
+ IFLA_GENEVE_TOS,
+ IFLA_GENEVE_PORT, /* destination port */
+ IFLA_GENEVE_COLLECT_METADATA,
+ IFLA_GENEVE_REMOTE6,
+ IFLA_GENEVE_UDP_CSUM,
+ IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
+ IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
+ IFLA_GENEVE_LABEL,
+ IFLA_GENEVE_TTL_INHERIT,
+ IFLA_GENEVE_DF,
+ IFLA_GENEVE_INNER_PROTO_INHERIT,
+ __IFLA_GENEVE_MAX
+};
+#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
+
+enum ifla_geneve_df {
+ GENEVE_DF_UNSET = 0,
+ GENEVE_DF_SET,
+ GENEVE_DF_INHERIT,
+ __GENEVE_DF_END,
+ GENEVE_DF_MAX = __GENEVE_DF_END - 1,
+};
+
+/* Bareudp section */
+enum {
+ IFLA_BAREUDP_UNSPEC,
+ IFLA_BAREUDP_PORT,
+ IFLA_BAREUDP_ETHERTYPE,
+ IFLA_BAREUDP_SRCPORT_MIN,
+ IFLA_BAREUDP_MULTIPROTO_MODE,
+ __IFLA_BAREUDP_MAX
+};
+
+#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1)
+
+/* PPP section */
+enum {
+ IFLA_PPP_UNSPEC,
+ IFLA_PPP_DEV_FD,
+ __IFLA_PPP_MAX
+};
+#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1)
+
+/* GTP section */
+
+enum ifla_gtp_role {
+ GTP_ROLE_GGSN = 0,
+ GTP_ROLE_SGSN,
+};
+
+enum {
+ IFLA_GTP_UNSPEC,
+ IFLA_GTP_FD0,
+ IFLA_GTP_FD1,
+ IFLA_GTP_PDP_HASHSIZE,
+ IFLA_GTP_ROLE,
+ IFLA_GTP_CREATE_SOCKETS,
+ IFLA_GTP_RESTART_COUNT,
+ __IFLA_GTP_MAX,
+};
+#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
+
+/* Bonding section */
+
+enum {
+ IFLA_BOND_UNSPEC,
+ IFLA_BOND_MODE,
+ IFLA_BOND_ACTIVE_SLAVE,
+ IFLA_BOND_MIIMON,
+ IFLA_BOND_UPDELAY,
+ IFLA_BOND_DOWNDELAY,
+ IFLA_BOND_USE_CARRIER,
+ IFLA_BOND_ARP_INTERVAL,
+ IFLA_BOND_ARP_IP_TARGET,
+ IFLA_BOND_ARP_VALIDATE,
+ IFLA_BOND_ARP_ALL_TARGETS,
+ IFLA_BOND_PRIMARY,
+ IFLA_BOND_PRIMARY_RESELECT,
+ IFLA_BOND_FAIL_OVER_MAC,
+ IFLA_BOND_XMIT_HASH_POLICY,
+ IFLA_BOND_RESEND_IGMP,
+ IFLA_BOND_NUM_PEER_NOTIF,
+ IFLA_BOND_ALL_SLAVES_ACTIVE,
+ IFLA_BOND_MIN_LINKS,
+ IFLA_BOND_LP_INTERVAL,
+ IFLA_BOND_PACKETS_PER_SLAVE,
+ IFLA_BOND_AD_LACP_RATE,
+ IFLA_BOND_AD_SELECT,
+ IFLA_BOND_AD_INFO,
+ IFLA_BOND_AD_ACTOR_SYS_PRIO,
+ IFLA_BOND_AD_USER_PORT_KEY,
+ IFLA_BOND_AD_ACTOR_SYSTEM,
+ IFLA_BOND_TLB_DYNAMIC_LB,
+ IFLA_BOND_PEER_NOTIF_DELAY,
+ IFLA_BOND_AD_LACP_ACTIVE,
+ IFLA_BOND_MISSED_MAX,
+ IFLA_BOND_NS_IP6_TARGET,
+ __IFLA_BOND_MAX,
+};
+
+#define IFLA_BOND_MAX (__IFLA_BOND_MAX - 1)
+
+enum {
+ IFLA_BOND_AD_INFO_UNSPEC,
+ IFLA_BOND_AD_INFO_AGGREGATOR,
+ IFLA_BOND_AD_INFO_NUM_PORTS,
+ IFLA_BOND_AD_INFO_ACTOR_KEY,
+ IFLA_BOND_AD_INFO_PARTNER_KEY,
+ IFLA_BOND_AD_INFO_PARTNER_MAC,
+ __IFLA_BOND_AD_INFO_MAX,
+};
+
+#define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1)
+
+enum {
+ IFLA_BOND_SLAVE_UNSPEC,
+ IFLA_BOND_SLAVE_STATE,
+ IFLA_BOND_SLAVE_MII_STATUS,
+ IFLA_BOND_SLAVE_LINK_FAILURE_COUNT,
+ IFLA_BOND_SLAVE_PERM_HWADDR,
+ IFLA_BOND_SLAVE_QUEUE_ID,
+ IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
+ IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
+ IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+ IFLA_BOND_SLAVE_PRIO,
+ __IFLA_BOND_SLAVE_MAX,
+};
+
+#define IFLA_BOND_SLAVE_MAX (__IFLA_BOND_SLAVE_MAX - 1)
+
+/* SR-IOV virtual function management section */
+
+enum {
+ IFLA_VF_INFO_UNSPEC,
+ IFLA_VF_INFO,
+ __IFLA_VF_INFO_MAX,
+};
+
+#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1)
+
+enum {
+ IFLA_VF_UNSPEC,
+ IFLA_VF_MAC, /* Hardware queue specific attributes */
+ IFLA_VF_VLAN, /* VLAN ID and QoS */
+ IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */
+ IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */
+ IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */
+ IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */
+ IFLA_VF_RSS_QUERY_EN, /* RSS Redirection Table and Hash Key query
+ * on/off switch
+ */
+ IFLA_VF_STATS, /* network device statistics */
+ IFLA_VF_TRUST, /* Trust VF */
+ IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */
+ IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */
+ IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */
+ IFLA_VF_BROADCAST, /* VF broadcast */
+ __IFLA_VF_MAX,
+};
+
+#define IFLA_VF_MAX (__IFLA_VF_MAX - 1)
+
+struct ifla_vf_mac {
+ __u32 vf;
+ __u8 mac[32]; /* MAX_ADDR_LEN */
+};
+
+struct ifla_vf_broadcast {
+ __u8 broadcast[32];
+};
+
+struct ifla_vf_vlan {
+ __u32 vf;
+ __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
+ __u32 qos;
+};
+
+enum {
+ IFLA_VF_VLAN_INFO_UNSPEC,
+ IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */
+ __IFLA_VF_VLAN_INFO_MAX,
+};
+
+#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1)
+#define MAX_VLAN_LIST_LEN 1
+
+struct ifla_vf_vlan_info {
+ __u32 vf;
+ __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
+ __u32 qos;
+ __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */
+};
+
+struct ifla_vf_tx_rate {
+ __u32 vf;
+ __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */
+};
+
+struct ifla_vf_rate {
+ __u32 vf;
+ __u32 min_tx_rate; /* Min Bandwidth in Mbps */
+ __u32 max_tx_rate; /* Max Bandwidth in Mbps */
+};
+
+struct ifla_vf_spoofchk {
+ __u32 vf;
+ __u32 setting;
+};
+
+struct ifla_vf_guid {
+ __u32 vf;
+ __u64 guid;
+};
+
+enum {
+ IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */
+ IFLA_VF_LINK_STATE_ENABLE, /* link always up */
+ IFLA_VF_LINK_STATE_DISABLE, /* link always down */
+ __IFLA_VF_LINK_STATE_MAX,
+};
+
+struct ifla_vf_link_state {
+ __u32 vf;
+ __u32 link_state;
+};
+
+struct ifla_vf_rss_query_en {
+ __u32 vf;
+ __u32 setting;
+};
+
+enum {
+ IFLA_VF_STATS_RX_PACKETS,
+ IFLA_VF_STATS_TX_PACKETS,
+ IFLA_VF_STATS_RX_BYTES,
+ IFLA_VF_STATS_TX_BYTES,
+ IFLA_VF_STATS_BROADCAST,
+ IFLA_VF_STATS_MULTICAST,
+ IFLA_VF_STATS_PAD,
+ IFLA_VF_STATS_RX_DROPPED,
+ IFLA_VF_STATS_TX_DROPPED,
+ __IFLA_VF_STATS_MAX,
+};
+
+#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1)
+
+struct ifla_vf_trust {
+ __u32 vf;
+ __u32 setting;
+};
+
+/* VF ports management section
+ *
+ * Nested layout of set/get msg is:
+ *
+ * [IFLA_NUM_VF]
+ * [IFLA_VF_PORTS]
+ * [IFLA_VF_PORT]
+ * [IFLA_PORT_*], ...
+ * [IFLA_VF_PORT]
+ * [IFLA_PORT_*], ...
+ * ...
+ * [IFLA_PORT_SELF]
+ * [IFLA_PORT_*], ...
+ */
+
+enum {
+ IFLA_VF_PORT_UNSPEC,
+ IFLA_VF_PORT, /* nest */
+ __IFLA_VF_PORT_MAX,
+};
+
+#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1)
+
+enum {
+ IFLA_PORT_UNSPEC,
+ IFLA_PORT_VF, /* __u32 */
+ IFLA_PORT_PROFILE, /* string */
+ IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */
+ IFLA_PORT_INSTANCE_UUID, /* binary UUID */
+ IFLA_PORT_HOST_UUID, /* binary UUID */
+ IFLA_PORT_REQUEST, /* __u8 */
+ IFLA_PORT_RESPONSE, /* __u16, output only */
+ __IFLA_PORT_MAX,
+};
+
+#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1)
+
+#define PORT_PROFILE_MAX 40
+#define PORT_UUID_MAX 16
+#define PORT_SELF_VF -1
+
+enum {
+ PORT_REQUEST_PREASSOCIATE = 0,
+ PORT_REQUEST_PREASSOCIATE_RR,
+ PORT_REQUEST_ASSOCIATE,
+ PORT_REQUEST_DISASSOCIATE,
+};
+
+enum {
+ PORT_VDP_RESPONSE_SUCCESS = 0,
+ PORT_VDP_RESPONSE_INVALID_FORMAT,
+ PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES,
+ PORT_VDP_RESPONSE_UNUSED_VTID,
+ PORT_VDP_RESPONSE_VTID_VIOLATION,
+ PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION,
+ PORT_VDP_RESPONSE_OUT_OF_SYNC,
+ /* 0x08-0xFF reserved for future VDP use */
+ PORT_PROFILE_RESPONSE_SUCCESS = 0x100,
+ PORT_PROFILE_RESPONSE_INPROGRESS,
+ PORT_PROFILE_RESPONSE_INVALID,
+ PORT_PROFILE_RESPONSE_BADSTATE,
+ PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES,
+ PORT_PROFILE_RESPONSE_ERROR,
+};
+
+struct ifla_port_vsi {
+ __u8 vsi_mgr_id;
+ __u8 vsi_type_id[3];
+ __u8 vsi_type_version;
+ __u8 pad[3];
+};
+
+
+/* IPoIB section */
+
+enum {
+ IFLA_IPOIB_UNSPEC,
+ IFLA_IPOIB_PKEY,
+ IFLA_IPOIB_MODE,
+ IFLA_IPOIB_UMCAST,
+ __IFLA_IPOIB_MAX
+};
+
+enum {
+ IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */
+ IPOIB_MODE_CONNECTED = 1, /* using connected QPs */
+};
+
+#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
+
+
+/* HSR/PRP section, both uses same interface */
+
+/* Different redundancy protocols for hsr device */
+enum {
+ HSR_PROTOCOL_HSR,
+ HSR_PROTOCOL_PRP,
+ HSR_PROTOCOL_MAX,
+};
+
+enum {
+ IFLA_HSR_UNSPEC,
+ IFLA_HSR_SLAVE1,
+ IFLA_HSR_SLAVE2,
+ IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */
+ IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */
+ IFLA_HSR_SEQ_NR,
+ IFLA_HSR_VERSION, /* HSR version */
+ IFLA_HSR_PROTOCOL, /* Indicate different protocol than
+ * HSR. For example PRP.
+ */
+ __IFLA_HSR_MAX,
+};
+
+#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1)
+
+/* STATS section */
+
+struct if_stats_msg {
+ __u8 family;
+ __u8 pad1;
+ __u16 pad2;
+ __u32 ifindex;
+ __u32 filter_mask;
+};
+
+/* A stats attribute can be netdev specific or a global stat.
+ * For netdev stats, lets use the prefix IFLA_STATS_LINK_*
+ */
+enum {
+ IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */
+ IFLA_STATS_LINK_64,
+ IFLA_STATS_LINK_XSTATS,
+ IFLA_STATS_LINK_XSTATS_SLAVE,
+ IFLA_STATS_LINK_OFFLOAD_XSTATS,
+ IFLA_STATS_AF_SPEC,
+ __IFLA_STATS_MAX,
+};
+
+#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1)
+
+#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1))
+
+enum {
+ IFLA_STATS_GETSET_UNSPEC,
+ IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with
+ * a filter mask for the corresponding group.
+ */
+ IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */
+ __IFLA_STATS_GETSET_MAX,
+};
+
+#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1)
+
+/* These are embedded into IFLA_STATS_LINK_XSTATS:
+ * [IFLA_STATS_LINK_XSTATS]
+ * -> [LINK_XSTATS_TYPE_xxx]
+ * -> [rtnl link type specific attributes]
+ */
+enum {
+ LINK_XSTATS_TYPE_UNSPEC,
+ LINK_XSTATS_TYPE_BRIDGE,
+ LINK_XSTATS_TYPE_BOND,
+ __LINK_XSTATS_TYPE_MAX
+};
+#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1)
+
+/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */
+enum {
+ IFLA_OFFLOAD_XSTATS_UNSPEC,
+ IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
+ IFLA_OFFLOAD_XSTATS_HW_S_INFO, /* HW stats info. A nest */
+ IFLA_OFFLOAD_XSTATS_L3_STATS, /* struct rtnl_hw_stats64 */
+ __IFLA_OFFLOAD_XSTATS_MAX
+};
+#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
+
+enum {
+ IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC,
+ IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST, /* u8 */
+ IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED, /* u8 */
+ __IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX,
+};
+#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \
+ (__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1)
+
+/* XDP section */
+
+#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0)
+#define XDP_FLAGS_SKB_MODE (1U << 1)
+#define XDP_FLAGS_DRV_MODE (1U << 2)
+#define XDP_FLAGS_HW_MODE (1U << 3)
+#define XDP_FLAGS_REPLACE (1U << 4)
+#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \
+ XDP_FLAGS_DRV_MODE | \
+ XDP_FLAGS_HW_MODE)
+#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \
+ XDP_FLAGS_MODES | XDP_FLAGS_REPLACE)
+
+/* These are stored into IFLA_XDP_ATTACHED on dump. */
+enum {
+ XDP_ATTACHED_NONE = 0,
+ XDP_ATTACHED_DRV,
+ XDP_ATTACHED_SKB,
+ XDP_ATTACHED_HW,
+ XDP_ATTACHED_MULTI,
+};
+
+enum {
+ IFLA_XDP_UNSPEC,
+ IFLA_XDP_FD,
+ IFLA_XDP_ATTACHED,
+ IFLA_XDP_FLAGS,
+ IFLA_XDP_PROG_ID,
+ IFLA_XDP_DRV_PROG_ID,
+ IFLA_XDP_SKB_PROG_ID,
+ IFLA_XDP_HW_PROG_ID,
+ IFLA_XDP_EXPECTED_FD,
+ __IFLA_XDP_MAX,
+};
+
+#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1)
+
+enum {
+ IFLA_EVENT_NONE,
+ IFLA_EVENT_REBOOT, /* internal reset / reboot */
+ IFLA_EVENT_FEATURES, /* change in offload features */
+ IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */
+ IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */
+ IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */
+ IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */
+};
+
+/* tun section */
+
+enum {
+ IFLA_TUN_UNSPEC,
+ IFLA_TUN_OWNER,
+ IFLA_TUN_GROUP,
+ IFLA_TUN_TYPE,
+ IFLA_TUN_PI,
+ IFLA_TUN_VNET_HDR,
+ IFLA_TUN_PERSIST,
+ IFLA_TUN_MULTI_QUEUE,
+ IFLA_TUN_NUM_QUEUES,
+ IFLA_TUN_NUM_DISABLED_QUEUES,
+ __IFLA_TUN_MAX,
+};
+
+#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1)
+
+/* rmnet section */
+
+#define RMNET_FLAGS_INGRESS_DEAGGREGATION (1U << 0)
+#define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5)
+
+enum {
+ IFLA_RMNET_UNSPEC,
+ IFLA_RMNET_MUX_ID,
+ IFLA_RMNET_FLAGS,
+ __IFLA_RMNET_MAX,
+};
+
+#define IFLA_RMNET_MAX (__IFLA_RMNET_MAX - 1)
+
+struct ifla_rmnet_flags {
+ __u32 flags;
+ __u32 mask;
+};
+
+/* MCTP section */
+
+enum {
+ IFLA_MCTP_UNSPEC,
+ IFLA_MCTP_NET,
+ __IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
+/* DSA section */
+
+enum {
+ IFLA_DSA_UNSPEC,
+ IFLA_DSA_CONDUIT,
+ /* Deprecated, use IFLA_DSA_CONDUIT instead */
+ IFLA_DSA_MASTER = IFLA_DSA_CONDUIT,
+ __IFLA_DSA_MAX,
+};
+
+#define IFLA_DSA_MAX (__IFLA_DSA_MAX - 1)
+
+#endif /* _LINUX_IF_LINK_H */
diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h
new file mode 100644
index 0000000..6edfea0
--- /dev/null
+++ b/include/uapi/linux/if_macsec.h
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * include/uapi/linux/if_macsec.h - MACsec device
+ *
+ * Copyright (c) 2015 Sabrina Dubroca <sd@queasysnail.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _MACSEC_H
+#define _MACSEC_H
+
+#include <linux/types.h>
+
+#define MACSEC_GENL_NAME "macsec"
+#define MACSEC_GENL_VERSION 1
+
+#define MACSEC_MAX_KEY_LEN 128
+
+#define MACSEC_KEYID_LEN 16
+
+#define MACSEC_SALT_LEN 12
+
+/* cipher IDs as per IEEE802.1AE-2018 (Table 14-1) */
+#define MACSEC_CIPHER_ID_GCM_AES_128 0x0080C20001000001ULL
+#define MACSEC_CIPHER_ID_GCM_AES_256 0x0080C20001000002ULL
+#define MACSEC_CIPHER_ID_GCM_AES_XPN_128 0x0080C20001000003ULL
+#define MACSEC_CIPHER_ID_GCM_AES_XPN_256 0x0080C20001000004ULL
+
+/* deprecated cipher ID for GCM-AES-128 */
+#define MACSEC_DEFAULT_CIPHER_ID 0x0080020001000001ULL
+#define MACSEC_DEFAULT_CIPHER_ALT MACSEC_CIPHER_ID_GCM_AES_128
+
+#define MACSEC_MIN_ICV_LEN 8
+#define MACSEC_MAX_ICV_LEN 32
+/* upper limit for ICV length as recommended by IEEE802.1AE-2006 */
+#define MACSEC_STD_ICV_LEN 16
+
+enum macsec_attrs {
+ MACSEC_ATTR_UNSPEC,
+ MACSEC_ATTR_IFINDEX, /* u32, ifindex of the MACsec netdevice */
+ MACSEC_ATTR_RXSC_CONFIG, /* config, nested macsec_rxsc_attrs */
+ MACSEC_ATTR_SA_CONFIG, /* config, nested macsec_sa_attrs */
+ MACSEC_ATTR_SECY, /* dump, nested macsec_secy_attrs */
+ MACSEC_ATTR_TXSA_LIST, /* dump, nested, macsec_sa_attrs for each TXSA */
+ MACSEC_ATTR_RXSC_LIST, /* dump, nested, macsec_rxsc_attrs for each RXSC */
+ MACSEC_ATTR_TXSC_STATS, /* dump, nested, macsec_txsc_stats_attr */
+ MACSEC_ATTR_SECY_STATS, /* dump, nested, macsec_secy_stats_attr */
+ MACSEC_ATTR_OFFLOAD, /* config, nested, macsec_offload_attrs */
+ __MACSEC_ATTR_END,
+ NUM_MACSEC_ATTR = __MACSEC_ATTR_END,
+ MACSEC_ATTR_MAX = __MACSEC_ATTR_END - 1,
+};
+
+enum macsec_secy_attrs {
+ MACSEC_SECY_ATTR_UNSPEC,
+ MACSEC_SECY_ATTR_SCI,
+ MACSEC_SECY_ATTR_ENCODING_SA,
+ MACSEC_SECY_ATTR_WINDOW,
+ MACSEC_SECY_ATTR_CIPHER_SUITE,
+ MACSEC_SECY_ATTR_ICV_LEN,
+ MACSEC_SECY_ATTR_PROTECT,
+ MACSEC_SECY_ATTR_REPLAY,
+ MACSEC_SECY_ATTR_OPER,
+ MACSEC_SECY_ATTR_VALIDATE,
+ MACSEC_SECY_ATTR_ENCRYPT,
+ MACSEC_SECY_ATTR_INC_SCI,
+ MACSEC_SECY_ATTR_ES,
+ MACSEC_SECY_ATTR_SCB,
+ MACSEC_SECY_ATTR_PAD,
+ __MACSEC_SECY_ATTR_END,
+ NUM_MACSEC_SECY_ATTR = __MACSEC_SECY_ATTR_END,
+ MACSEC_SECY_ATTR_MAX = __MACSEC_SECY_ATTR_END - 1,
+};
+
+enum macsec_rxsc_attrs {
+ MACSEC_RXSC_ATTR_UNSPEC,
+ MACSEC_RXSC_ATTR_SCI, /* config/dump, u64 */
+ MACSEC_RXSC_ATTR_ACTIVE, /* config/dump, u8 0..1 */
+ MACSEC_RXSC_ATTR_SA_LIST, /* dump, nested */
+ MACSEC_RXSC_ATTR_STATS, /* dump, nested, macsec_rxsc_stats_attr */
+ MACSEC_RXSC_ATTR_PAD,
+ __MACSEC_RXSC_ATTR_END,
+ NUM_MACSEC_RXSC_ATTR = __MACSEC_RXSC_ATTR_END,
+ MACSEC_RXSC_ATTR_MAX = __MACSEC_RXSC_ATTR_END - 1,
+};
+
+enum macsec_sa_attrs {
+ MACSEC_SA_ATTR_UNSPEC,
+ MACSEC_SA_ATTR_AN, /* config/dump, u8 0..3 */
+ MACSEC_SA_ATTR_ACTIVE, /* config/dump, u8 0..1 */
+ MACSEC_SA_ATTR_PN, /* config/dump, u32/u64 (u64 if XPN) */
+ MACSEC_SA_ATTR_KEY, /* config, data */
+ MACSEC_SA_ATTR_KEYID, /* config/dump, 128-bit */
+ MACSEC_SA_ATTR_STATS, /* dump, nested, macsec_sa_stats_attr */
+ MACSEC_SA_ATTR_PAD,
+ MACSEC_SA_ATTR_SSCI, /* config/dump, u32 - XPN only */
+ MACSEC_SA_ATTR_SALT, /* config, 96-bit - XPN only */
+ __MACSEC_SA_ATTR_END,
+ NUM_MACSEC_SA_ATTR = __MACSEC_SA_ATTR_END,
+ MACSEC_SA_ATTR_MAX = __MACSEC_SA_ATTR_END - 1,
+};
+
+enum macsec_offload_attrs {
+ MACSEC_OFFLOAD_ATTR_UNSPEC,
+ MACSEC_OFFLOAD_ATTR_TYPE, /* config/dump, u8 0..2 */
+ MACSEC_OFFLOAD_ATTR_PAD,
+ __MACSEC_OFFLOAD_ATTR_END,
+ NUM_MACSEC_OFFLOAD_ATTR = __MACSEC_OFFLOAD_ATTR_END,
+ MACSEC_OFFLOAD_ATTR_MAX = __MACSEC_OFFLOAD_ATTR_END - 1,
+};
+
+enum macsec_nl_commands {
+ MACSEC_CMD_GET_TXSC,
+ MACSEC_CMD_ADD_RXSC,
+ MACSEC_CMD_DEL_RXSC,
+ MACSEC_CMD_UPD_RXSC,
+ MACSEC_CMD_ADD_TXSA,
+ MACSEC_CMD_DEL_TXSA,
+ MACSEC_CMD_UPD_TXSA,
+ MACSEC_CMD_ADD_RXSA,
+ MACSEC_CMD_DEL_RXSA,
+ MACSEC_CMD_UPD_RXSA,
+ MACSEC_CMD_UPD_OFFLOAD,
+};
+
+/* u64 per-RXSC stats */
+enum macsec_rxsc_stats_attr {
+ MACSEC_RXSC_STATS_ATTR_UNSPEC,
+ MACSEC_RXSC_STATS_ATTR_IN_OCTETS_VALIDATED,
+ MACSEC_RXSC_STATS_ATTR_IN_OCTETS_DECRYPTED,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNCHECKED,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_DELAYED,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_OK,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_INVALID,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_LATE,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_VALID,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_USING_SA,
+ MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNUSED_SA,
+ MACSEC_RXSC_STATS_ATTR_PAD,
+ __MACSEC_RXSC_STATS_ATTR_END,
+ NUM_MACSEC_RXSC_STATS_ATTR = __MACSEC_RXSC_STATS_ATTR_END,
+ MACSEC_RXSC_STATS_ATTR_MAX = __MACSEC_RXSC_STATS_ATTR_END - 1,
+};
+
+/* u32 per-{RX,TX}SA stats */
+enum macsec_sa_stats_attr {
+ MACSEC_SA_STATS_ATTR_UNSPEC,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_OK,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_INVALID,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_VALID,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_USING_SA,
+ MACSEC_SA_STATS_ATTR_IN_PKTS_UNUSED_SA,
+ MACSEC_SA_STATS_ATTR_OUT_PKTS_PROTECTED,
+ MACSEC_SA_STATS_ATTR_OUT_PKTS_ENCRYPTED,
+ __MACSEC_SA_STATS_ATTR_END,
+ NUM_MACSEC_SA_STATS_ATTR = __MACSEC_SA_STATS_ATTR_END,
+ MACSEC_SA_STATS_ATTR_MAX = __MACSEC_SA_STATS_ATTR_END - 1,
+};
+
+/* u64 per-TXSC stats */
+enum macsec_txsc_stats_attr {
+ MACSEC_TXSC_STATS_ATTR_UNSPEC,
+ MACSEC_TXSC_STATS_ATTR_OUT_PKTS_PROTECTED,
+ MACSEC_TXSC_STATS_ATTR_OUT_PKTS_ENCRYPTED,
+ MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_PROTECTED,
+ MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_ENCRYPTED,
+ MACSEC_TXSC_STATS_ATTR_PAD,
+ __MACSEC_TXSC_STATS_ATTR_END,
+ NUM_MACSEC_TXSC_STATS_ATTR = __MACSEC_TXSC_STATS_ATTR_END,
+ MACSEC_TXSC_STATS_ATTR_MAX = __MACSEC_TXSC_STATS_ATTR_END - 1,
+};
+
+/* u64 per-SecY stats */
+enum macsec_secy_stats_attr {
+ MACSEC_SECY_STATS_ATTR_UNSPEC,
+ MACSEC_SECY_STATS_ATTR_OUT_PKTS_UNTAGGED,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_UNTAGGED,
+ MACSEC_SECY_STATS_ATTR_OUT_PKTS_TOO_LONG,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_TAG,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_BAD_TAG,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_UNKNOWN_SCI,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_SCI,
+ MACSEC_SECY_STATS_ATTR_IN_PKTS_OVERRUN,
+ MACSEC_SECY_STATS_ATTR_PAD,
+ __MACSEC_SECY_STATS_ATTR_END,
+ NUM_MACSEC_SECY_STATS_ATTR = __MACSEC_SECY_STATS_ATTR_END,
+ MACSEC_SECY_STATS_ATTR_MAX = __MACSEC_SECY_STATS_ATTR_END - 1,
+};
+
+#endif /* _MACSEC_H */
diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
new file mode 100644
index 0000000..9efc423
--- /dev/null
+++ b/include/uapi/linux/if_packet.h
@@ -0,0 +1,319 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_IF_PACKET_H
+#define __LINUX_IF_PACKET_H
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+
+struct sockaddr_pkt {
+ unsigned short spkt_family;
+ unsigned char spkt_device[14];
+ __be16 spkt_protocol;
+};
+
+struct sockaddr_ll {
+ unsigned short sll_family;
+ __be16 sll_protocol;
+ int sll_ifindex;
+ unsigned short sll_hatype;
+ unsigned char sll_pkttype;
+ unsigned char sll_halen;
+ unsigned char sll_addr[8];
+};
+
+/* Packet types */
+
+#define PACKET_HOST 0 /* To us */
+#define PACKET_BROADCAST 1 /* To all */
+#define PACKET_MULTICAST 2 /* To group */
+#define PACKET_OTHERHOST 3 /* To someone else */
+#define PACKET_OUTGOING 4 /* Outgoing of any type */
+#define PACKET_LOOPBACK 5 /* MC/BRD frame looped back */
+#define PACKET_USER 6 /* To user space */
+#define PACKET_KERNEL 7 /* To kernel space */
+/* Unused, PACKET_FASTROUTE and PACKET_LOOPBACK are invisible to user space */
+#define PACKET_FASTROUTE 6 /* Fastrouted frame */
+
+/* Packet socket options */
+
+#define PACKET_ADD_MEMBERSHIP 1
+#define PACKET_DROP_MEMBERSHIP 2
+#define PACKET_RECV_OUTPUT 3
+/* Value 4 is still used by obsolete turbo-packet. */
+#define PACKET_RX_RING 5
+#define PACKET_STATISTICS 6
+#define PACKET_COPY_THRESH 7
+#define PACKET_AUXDATA 8
+#define PACKET_ORIGDEV 9
+#define PACKET_VERSION 10
+#define PACKET_HDRLEN 11
+#define PACKET_RESERVE 12
+#define PACKET_TX_RING 13
+#define PACKET_LOSS 14
+#define PACKET_VNET_HDR 15
+#define PACKET_TX_TIMESTAMP 16
+#define PACKET_TIMESTAMP 17
+#define PACKET_FANOUT 18
+#define PACKET_TX_HAS_OFF 19
+#define PACKET_QDISC_BYPASS 20
+#define PACKET_ROLLOVER_STATS 21
+#define PACKET_FANOUT_DATA 22
+#define PACKET_IGNORE_OUTGOING 23
+#define PACKET_VNET_HDR_SZ 24
+
+#define PACKET_FANOUT_HASH 0
+#define PACKET_FANOUT_LB 1
+#define PACKET_FANOUT_CPU 2
+#define PACKET_FANOUT_ROLLOVER 3
+#define PACKET_FANOUT_RND 4
+#define PACKET_FANOUT_QM 5
+#define PACKET_FANOUT_CBPF 6
+#define PACKET_FANOUT_EBPF 7
+#define PACKET_FANOUT_FLAG_ROLLOVER 0x1000
+#define PACKET_FANOUT_FLAG_UNIQUEID 0x2000
+#define PACKET_FANOUT_FLAG_IGNORE_OUTGOING 0x4000
+#define PACKET_FANOUT_FLAG_DEFRAG 0x8000
+
+struct tpacket_stats {
+ unsigned int tp_packets;
+ unsigned int tp_drops;
+};
+
+struct tpacket_stats_v3 {
+ unsigned int tp_packets;
+ unsigned int tp_drops;
+ unsigned int tp_freeze_q_cnt;
+};
+
+struct tpacket_rollover_stats {
+ __aligned_u64 tp_all;
+ __aligned_u64 tp_huge;
+ __aligned_u64 tp_failed;
+};
+
+union tpacket_stats_u {
+ struct tpacket_stats stats1;
+ struct tpacket_stats_v3 stats3;
+};
+
+struct tpacket_auxdata {
+ __u32 tp_status;
+ __u32 tp_len;
+ __u32 tp_snaplen;
+ __u16 tp_mac;
+ __u16 tp_net;
+ __u16 tp_vlan_tci;
+ __u16 tp_vlan_tpid;
+};
+
+/* Rx ring - header status */
+#define TP_STATUS_KERNEL 0
+#define TP_STATUS_USER (1 << 0)
+#define TP_STATUS_COPY (1 << 1)
+#define TP_STATUS_LOSING (1 << 2)
+#define TP_STATUS_CSUMNOTREADY (1 << 3)
+#define TP_STATUS_VLAN_VALID (1 << 4) /* auxdata has valid tp_vlan_tci */
+#define TP_STATUS_BLK_TMO (1 << 5)
+#define TP_STATUS_VLAN_TPID_VALID (1 << 6) /* auxdata has valid tp_vlan_tpid */
+#define TP_STATUS_CSUM_VALID (1 << 7)
+#define TP_STATUS_GSO_TCP (1 << 8)
+
+/* Tx ring - header status */
+#define TP_STATUS_AVAILABLE 0
+#define TP_STATUS_SEND_REQUEST (1 << 0)
+#define TP_STATUS_SENDING (1 << 1)
+#define TP_STATUS_WRONG_FORMAT (1 << 2)
+
+/* Rx and Tx ring - header status */
+#define TP_STATUS_TS_SOFTWARE (1 << 29)
+#define TP_STATUS_TS_SYS_HARDWARE (1 << 30) /* deprecated, never set */
+#define TP_STATUS_TS_RAW_HARDWARE (1U << 31)
+
+/* Rx ring - feature request bits */
+#define TP_FT_REQ_FILL_RXHASH 0x1
+
+struct tpacket_hdr {
+ unsigned long tp_status;
+ unsigned int tp_len;
+ unsigned int tp_snaplen;
+ unsigned short tp_mac;
+ unsigned short tp_net;
+ unsigned int tp_sec;
+ unsigned int tp_usec;
+};
+
+#define TPACKET_ALIGNMENT 16
+#define TPACKET_ALIGN(x) (((x)+TPACKET_ALIGNMENT-1)&~(TPACKET_ALIGNMENT-1))
+#define TPACKET_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket_hdr)) + sizeof(struct sockaddr_ll))
+
+struct tpacket2_hdr {
+ __u32 tp_status;
+ __u32 tp_len;
+ __u32 tp_snaplen;
+ __u16 tp_mac;
+ __u16 tp_net;
+ __u32 tp_sec;
+ __u32 tp_nsec;
+ __u16 tp_vlan_tci;
+ __u16 tp_vlan_tpid;
+ __u8 tp_padding[4];
+};
+
+struct tpacket_hdr_variant1 {
+ __u32 tp_rxhash;
+ __u32 tp_vlan_tci;
+ __u16 tp_vlan_tpid;
+ __u16 tp_padding;
+};
+
+struct tpacket3_hdr {
+ __u32 tp_next_offset;
+ __u32 tp_sec;
+ __u32 tp_nsec;
+ __u32 tp_snaplen;
+ __u32 tp_len;
+ __u32 tp_status;
+ __u16 tp_mac;
+ __u16 tp_net;
+ /* pkt_hdr variants */
+ union {
+ struct tpacket_hdr_variant1 hv1;
+ };
+ __u8 tp_padding[8];
+};
+
+struct tpacket_bd_ts {
+ unsigned int ts_sec;
+ union {
+ unsigned int ts_usec;
+ unsigned int ts_nsec;
+ };
+};
+
+struct tpacket_hdr_v1 {
+ __u32 block_status;
+ __u32 num_pkts;
+ __u32 offset_to_first_pkt;
+
+ /* Number of valid bytes (including padding)
+ * blk_len <= tp_block_size
+ */
+ __u32 blk_len;
+
+ /*
+ * Quite a few uses of sequence number:
+ * 1. Make sure cache flush etc worked.
+ * Well, one can argue - why not use the increasing ts below?
+ * But look at 2. below first.
+ * 2. When you pass around blocks to other user space decoders,
+ * you can see which blk[s] is[are] outstanding etc.
+ * 3. Validate kernel code.
+ */
+ __aligned_u64 seq_num;
+
+ /*
+ * ts_last_pkt:
+ *
+ * Case 1. Block has 'N'(N >=1) packets and TMO'd(timed out)
+ * ts_last_pkt == 'time-stamp of last packet' and NOT the
+ * time when the timer fired and the block was closed.
+ * By providing the ts of the last packet we can absolutely
+ * guarantee that time-stamp wise, the first packet in the
+ * next block will never precede the last packet of the
+ * previous block.
+ * Case 2. Block has zero packets and TMO'd
+ * ts_last_pkt = time when the timer fired and the block
+ * was closed.
+ * Case 3. Block has 'N' packets and NO TMO.
+ * ts_last_pkt = time-stamp of the last pkt in the block.
+ *
+ * ts_first_pkt:
+ * Is always the time-stamp when the block was opened.
+ * Case a) ZERO packets
+ * No packets to deal with but atleast you know the
+ * time-interval of this block.
+ * Case b) Non-zero packets
+ * Use the ts of the first packet in the block.
+ *
+ */
+ struct tpacket_bd_ts ts_first_pkt, ts_last_pkt;
+};
+
+union tpacket_bd_header_u {
+ struct tpacket_hdr_v1 bh1;
+};
+
+struct tpacket_block_desc {
+ __u32 version;
+ __u32 offset_to_priv;
+ union tpacket_bd_header_u hdr;
+};
+
+#define TPACKET2_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket2_hdr)) + sizeof(struct sockaddr_ll))
+#define TPACKET3_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket3_hdr)) + sizeof(struct sockaddr_ll))
+
+enum tpacket_versions {
+ TPACKET_V1,
+ TPACKET_V2,
+ TPACKET_V3
+};
+
+/*
+ Frame structure:
+
+ - Start. Frame must be aligned to TPACKET_ALIGNMENT=16
+ - struct tpacket_hdr
+ - pad to TPACKET_ALIGNMENT=16
+ - struct sockaddr_ll
+ - Gap, chosen so that packet data (Start+tp_net) alignes to TPACKET_ALIGNMENT=16
+ - Start+tp_mac: [ Optional MAC header ]
+ - Start+tp_net: Packet data, aligned to TPACKET_ALIGNMENT=16.
+ - Pad to align to TPACKET_ALIGNMENT=16
+ */
+
+struct tpacket_req {
+ unsigned int tp_block_size; /* Minimal size of contiguous block */
+ unsigned int tp_block_nr; /* Number of blocks */
+ unsigned int tp_frame_size; /* Size of frame */
+ unsigned int tp_frame_nr; /* Total number of frames */
+};
+
+struct tpacket_req3 {
+ unsigned int tp_block_size; /* Minimal size of contiguous block */
+ unsigned int tp_block_nr; /* Number of blocks */
+ unsigned int tp_frame_size; /* Size of frame */
+ unsigned int tp_frame_nr; /* Total number of frames */
+ unsigned int tp_retire_blk_tov; /* timeout in msecs */
+ unsigned int tp_sizeof_priv; /* offset to private data area */
+ unsigned int tp_feature_req_word;
+};
+
+union tpacket_req_u {
+ struct tpacket_req req;
+ struct tpacket_req3 req3;
+};
+
+struct packet_mreq {
+ int mr_ifindex;
+ unsigned short mr_type;
+ unsigned short mr_alen;
+ unsigned char mr_address[8];
+};
+
+struct fanout_args {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u16 id;
+ __u16 type_flags;
+#else
+ __u16 type_flags;
+ __u16 id;
+#endif
+ __u32 max_num_members;
+};
+
+#define PACKET_MR_MULTICAST 0
+#define PACKET_MR_PROMISC 1
+#define PACKET_MR_ALLMULTI 2
+#define PACKET_MR_UNICAST 3
+
+#endif
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
new file mode 100644
index 0000000..8a6d5d4
--- /dev/null
+++ b/include/uapi/linux/if_tun.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Universal TUN/TAP device driver.
+ * Copyright (C) 1999-2000 Maxim Krasnyansky <max_mk@yahoo.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __IF_TUN_H
+#define __IF_TUN_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/filter.h>
+
+/* Read queue size */
+#define TUN_READQ_SIZE 500
+/* TUN device type flags: deprecated. Use IFF_TUN/IFF_TAP instead. */
+#define TUN_TUN_DEV IFF_TUN
+#define TUN_TAP_DEV IFF_TAP
+#define TUN_TYPE_MASK 0x000f
+
+/* Ioctl defines */
+#define TUNSETNOCSUM _IOW('T', 200, int)
+#define TUNSETDEBUG _IOW('T', 201, int)
+#define TUNSETIFF _IOW('T', 202, int)
+#define TUNSETPERSIST _IOW('T', 203, int)
+#define TUNSETOWNER _IOW('T', 204, int)
+#define TUNSETLINK _IOW('T', 205, int)
+#define TUNSETGROUP _IOW('T', 206, int)
+#define TUNGETFEATURES _IOR('T', 207, unsigned int)
+#define TUNSETOFFLOAD _IOW('T', 208, unsigned int)
+#define TUNSETTXFILTER _IOW('T', 209, unsigned int)
+#define TUNGETIFF _IOR('T', 210, unsigned int)
+#define TUNGETSNDBUF _IOR('T', 211, int)
+#define TUNSETSNDBUF _IOW('T', 212, int)
+#define TUNATTACHFILTER _IOW('T', 213, struct sock_fprog)
+#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog)
+#define TUNGETVNETHDRSZ _IOR('T', 215, int)
+#define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNSETQUEUE _IOW('T', 217, int)
+#define TUNSETIFINDEX _IOW('T', 218, unsigned int)
+#define TUNGETFILTER _IOR('T', 219, struct sock_fprog)
+#define TUNSETVNETLE _IOW('T', 220, int)
+#define TUNGETVNETLE _IOR('T', 221, int)
+/* The TUNSETVNETBE and TUNGETVNETBE ioctls are for cross-endian support on
+ * little-endian hosts. Not all kernel configurations support them, but all
+ * configurations that support SET also support GET.
+ */
+#define TUNSETVNETBE _IOW('T', 222, int)
+#define TUNGETVNETBE _IOR('T', 223, int)
+#define TUNSETSTEERINGEBPF _IOR('T', 224, int)
+#define TUNSETFILTEREBPF _IOR('T', 225, int)
+#define TUNSETCARRIER _IOW('T', 226, int)
+#define TUNGETDEVNETNS _IO('T', 227)
+
+/* TUNSETIFF ifr flags */
+#define IFF_TUN 0x0001
+#define IFF_TAP 0x0002
+#define IFF_NAPI 0x0010
+#define IFF_NAPI_FRAGS 0x0020
+/* Used in TUNSETIFF to bring up tun/tap without carrier */
+#define IFF_NO_CARRIER 0x0040
+#define IFF_NO_PI 0x1000
+/* This flag has no real effect */
+#define IFF_ONE_QUEUE 0x2000
+#define IFF_VNET_HDR 0x4000
+#define IFF_TUN_EXCL 0x8000
+#define IFF_MULTI_QUEUE 0x0100
+#define IFF_ATTACH_QUEUE 0x0200
+#define IFF_DETACH_QUEUE 0x0400
+/* read-only flag */
+#define IFF_PERSIST 0x0800
+#define IFF_NOFILTER 0x1000
+
+/* Socket options */
+#define TUN_TX_TIMESTAMP 1
+
+/* Features for GSO (TUNSETOFFLOAD). */
+#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */
+#define TUN_F_TSO4 0x02 /* I can handle TSO for IPv4 packets */
+#define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */
+#define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */
+#define TUN_F_UFO 0x10 /* I can handle UFO packets */
+#define TUN_F_USO4 0x20 /* I can handle USO for IPv4 packets */
+#define TUN_F_USO6 0x40 /* I can handle USO for IPv6 packets */
+
+/* Protocol info prepended to the packets (when IFF_NO_PI is not set) */
+#define TUN_PKT_STRIP 0x0001
+struct tun_pi {
+ __u16 flags;
+ __be16 proto;
+};
+
+/*
+ * Filter spec (used for SETXXFILTER ioctls)
+ * This stuff is applicable only to the TAP (Ethernet) devices.
+ * If the count is zero the filter is disabled and the driver accepts
+ * all packets (promisc mode).
+ * If the filter is enabled in order to accept broadcast packets
+ * broadcast addr must be explicitly included in the addr list.
+ */
+#define TUN_FLT_ALLMULTI 0x0001 /* Accept all multicast packets */
+struct tun_filter {
+ __u16 flags; /* TUN_FLT_ flags see above */
+ __u16 count; /* Number of addresses */
+ __u8 addr[][ETH_ALEN];
+};
+
+#endif /* __IF_TUN_H */
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
new file mode 100644
index 0000000..edaea41
--- /dev/null
+++ b/include/uapi/linux/if_tunnel.h
@@ -0,0 +1,185 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _IF_TUNNEL_H_
+#define _IF_TUNNEL_H_
+
+#include <linux/types.h>
+#include <linux/if.h>
+#include <linux/ip.h>
+#include <linux/in6.h>
+#include <asm/byteorder.h>
+
+
+#define SIOCGETTUNNEL (SIOCDEVPRIVATE + 0)
+#define SIOCADDTUNNEL (SIOCDEVPRIVATE + 1)
+#define SIOCDELTUNNEL (SIOCDEVPRIVATE + 2)
+#define SIOCCHGTUNNEL (SIOCDEVPRIVATE + 3)
+#define SIOCGETPRL (SIOCDEVPRIVATE + 4)
+#define SIOCADDPRL (SIOCDEVPRIVATE + 5)
+#define SIOCDELPRL (SIOCDEVPRIVATE + 6)
+#define SIOCCHGPRL (SIOCDEVPRIVATE + 7)
+#define SIOCGET6RD (SIOCDEVPRIVATE + 8)
+#define SIOCADD6RD (SIOCDEVPRIVATE + 9)
+#define SIOCDEL6RD (SIOCDEVPRIVATE + 10)
+#define SIOCCHG6RD (SIOCDEVPRIVATE + 11)
+
+#define GRE_CSUM __cpu_to_be16(0x8000)
+#define GRE_ROUTING __cpu_to_be16(0x4000)
+#define GRE_KEY __cpu_to_be16(0x2000)
+#define GRE_SEQ __cpu_to_be16(0x1000)
+#define GRE_STRICT __cpu_to_be16(0x0800)
+#define GRE_REC __cpu_to_be16(0x0700)
+#define GRE_ACK __cpu_to_be16(0x0080)
+#define GRE_FLAGS __cpu_to_be16(0x0078)
+#define GRE_VERSION __cpu_to_be16(0x0007)
+
+#define GRE_IS_CSUM(f) ((f) & GRE_CSUM)
+#define GRE_IS_ROUTING(f) ((f) & GRE_ROUTING)
+#define GRE_IS_KEY(f) ((f) & GRE_KEY)
+#define GRE_IS_SEQ(f) ((f) & GRE_SEQ)
+#define GRE_IS_STRICT(f) ((f) & GRE_STRICT)
+#define GRE_IS_REC(f) ((f) & GRE_REC)
+#define GRE_IS_ACK(f) ((f) & GRE_ACK)
+
+#define GRE_VERSION_0 __cpu_to_be16(0x0000)
+#define GRE_VERSION_1 __cpu_to_be16(0x0001)
+#define GRE_PROTO_PPP __cpu_to_be16(0x880b)
+#define GRE_PPTP_KEY_MASK __cpu_to_be32(0xffff)
+
+struct ip_tunnel_parm {
+ char name[IFNAMSIZ];
+ int link;
+ __be16 i_flags;
+ __be16 o_flags;
+ __be32 i_key;
+ __be32 o_key;
+ struct iphdr iph;
+};
+
+enum {
+ IFLA_IPTUN_UNSPEC,
+ IFLA_IPTUN_LINK,
+ IFLA_IPTUN_LOCAL,
+ IFLA_IPTUN_REMOTE,
+ IFLA_IPTUN_TTL,
+ IFLA_IPTUN_TOS,
+ IFLA_IPTUN_ENCAP_LIMIT,
+ IFLA_IPTUN_FLOWINFO,
+ IFLA_IPTUN_FLAGS,
+ IFLA_IPTUN_PROTO,
+ IFLA_IPTUN_PMTUDISC,
+ IFLA_IPTUN_6RD_PREFIX,
+ IFLA_IPTUN_6RD_RELAY_PREFIX,
+ IFLA_IPTUN_6RD_PREFIXLEN,
+ IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
+ IFLA_IPTUN_ENCAP_TYPE,
+ IFLA_IPTUN_ENCAP_FLAGS,
+ IFLA_IPTUN_ENCAP_SPORT,
+ IFLA_IPTUN_ENCAP_DPORT,
+ IFLA_IPTUN_COLLECT_METADATA,
+ IFLA_IPTUN_FWMARK,
+ __IFLA_IPTUN_MAX,
+};
+#define IFLA_IPTUN_MAX (__IFLA_IPTUN_MAX - 1)
+
+enum tunnel_encap_types {
+ TUNNEL_ENCAP_NONE,
+ TUNNEL_ENCAP_FOU,
+ TUNNEL_ENCAP_GUE,
+ TUNNEL_ENCAP_MPLS,
+};
+
+#define TUNNEL_ENCAP_FLAG_CSUM (1<<0)
+#define TUNNEL_ENCAP_FLAG_CSUM6 (1<<1)
+#define TUNNEL_ENCAP_FLAG_REMCSUM (1<<2)
+
+/* SIT-mode i_flags */
+#define SIT_ISATAP 0x0001
+
+struct ip_tunnel_prl {
+ __be32 addr;
+ __u16 flags;
+ __u16 __reserved;
+ __u32 datalen;
+ __u32 __reserved2;
+ /* data follows */
+};
+
+/* PRL flags */
+#define PRL_DEFAULT 0x0001
+
+struct ip_tunnel_6rd {
+ struct in6_addr prefix;
+ __be32 relay_prefix;
+ __u16 prefixlen;
+ __u16 relay_prefixlen;
+};
+
+enum {
+ IFLA_GRE_UNSPEC,
+ IFLA_GRE_LINK,
+ IFLA_GRE_IFLAGS,
+ IFLA_GRE_OFLAGS,
+ IFLA_GRE_IKEY,
+ IFLA_GRE_OKEY,
+ IFLA_GRE_LOCAL,
+ IFLA_GRE_REMOTE,
+ IFLA_GRE_TTL,
+ IFLA_GRE_TOS,
+ IFLA_GRE_PMTUDISC,
+ IFLA_GRE_ENCAP_LIMIT,
+ IFLA_GRE_FLOWINFO,
+ IFLA_GRE_FLAGS,
+ IFLA_GRE_ENCAP_TYPE,
+ IFLA_GRE_ENCAP_FLAGS,
+ IFLA_GRE_ENCAP_SPORT,
+ IFLA_GRE_ENCAP_DPORT,
+ IFLA_GRE_COLLECT_METADATA,
+ IFLA_GRE_IGNORE_DF,
+ IFLA_GRE_FWMARK,
+ IFLA_GRE_ERSPAN_INDEX,
+ IFLA_GRE_ERSPAN_VER,
+ IFLA_GRE_ERSPAN_DIR,
+ IFLA_GRE_ERSPAN_HWID,
+ __IFLA_GRE_MAX,
+};
+
+#define IFLA_GRE_MAX (__IFLA_GRE_MAX - 1)
+
+/* VTI-mode i_flags */
+#define VTI_ISVTI ((__be16)0x0001)
+
+enum {
+ IFLA_VTI_UNSPEC,
+ IFLA_VTI_LINK,
+ IFLA_VTI_IKEY,
+ IFLA_VTI_OKEY,
+ IFLA_VTI_LOCAL,
+ IFLA_VTI_REMOTE,
+ IFLA_VTI_FWMARK,
+ __IFLA_VTI_MAX,
+};
+
+#define IFLA_VTI_MAX (__IFLA_VTI_MAX - 1)
+
+#define TUNNEL_CSUM __cpu_to_be16(0x01)
+#define TUNNEL_ROUTING __cpu_to_be16(0x02)
+#define TUNNEL_KEY __cpu_to_be16(0x04)
+#define TUNNEL_SEQ __cpu_to_be16(0x08)
+#define TUNNEL_STRICT __cpu_to_be16(0x10)
+#define TUNNEL_REC __cpu_to_be16(0x20)
+#define TUNNEL_VERSION __cpu_to_be16(0x40)
+#define TUNNEL_NO_KEY __cpu_to_be16(0x80)
+#define TUNNEL_DONT_FRAGMENT __cpu_to_be16(0x0100)
+#define TUNNEL_OAM __cpu_to_be16(0x0200)
+#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400)
+#define TUNNEL_GENEVE_OPT __cpu_to_be16(0x0800)
+#define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000)
+#define TUNNEL_NOCACHE __cpu_to_be16(0x2000)
+#define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000)
+#define TUNNEL_GTP_OPT __cpu_to_be16(0x8000)
+
+#define TUNNEL_OPTIONS_PRESENT \
+ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT | \
+ TUNNEL_GTP_OPT)
+
+#endif /* _IF_TUNNEL_H_ */
diff --git a/include/uapi/linux/if_vlan.h b/include/uapi/linux/if_vlan.h
new file mode 100644
index 0000000..04bca79
--- /dev/null
+++ b/include/uapi/linux/if_vlan.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * VLAN An implementation of 802.1Q VLAN tagging.
+ *
+ * Authors: Ben Greear <greearb@candelatech.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#ifndef _LINUX_IF_VLAN_H_
+#define _LINUX_IF_VLAN_H_
+
+
+/* VLAN IOCTLs are found in sockios.h */
+
+/* Passed in vlan_ioctl_args structure to determine behaviour. */
+enum vlan_ioctl_cmds {
+ ADD_VLAN_CMD,
+ DEL_VLAN_CMD,
+ SET_VLAN_INGRESS_PRIORITY_CMD,
+ SET_VLAN_EGRESS_PRIORITY_CMD,
+ GET_VLAN_INGRESS_PRIORITY_CMD,
+ GET_VLAN_EGRESS_PRIORITY_CMD,
+ SET_VLAN_NAME_TYPE_CMD,
+ SET_VLAN_FLAG_CMD,
+ GET_VLAN_REALDEV_NAME_CMD, /* If this works, you know it's a VLAN device, btw */
+ GET_VLAN_VID_CMD /* Get the VID of this VLAN (specified by name) */
+};
+
+enum vlan_flags {
+ VLAN_FLAG_REORDER_HDR = 0x1,
+ VLAN_FLAG_GVRP = 0x2,
+ VLAN_FLAG_LOOSE_BINDING = 0x4,
+ VLAN_FLAG_MVRP = 0x8,
+ VLAN_FLAG_BRIDGE_BINDING = 0x10,
+};
+
+enum vlan_name_types {
+ VLAN_NAME_TYPE_PLUS_VID, /* Name will look like: vlan0005 */
+ VLAN_NAME_TYPE_RAW_PLUS_VID, /* name will look like: eth1.0005 */
+ VLAN_NAME_TYPE_PLUS_VID_NO_PAD, /* Name will look like: vlan5 */
+ VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD, /* Name will look like: eth0.5 */
+ VLAN_NAME_TYPE_HIGHEST
+};
+
+struct vlan_ioctl_args {
+ int cmd; /* Should be one of the vlan_ioctl_cmds enum above. */
+ char device1[24];
+
+ union {
+ char device2[24];
+ int VID;
+ unsigned int skb_priority;
+ unsigned int name_type;
+ unsigned int bind_type;
+ unsigned int flag; /* Matches vlan_dev_priv flags */
+ } u;
+
+ short vlan_qos;
+};
+
+#endif /* _LINUX_IF_VLAN_H_ */
diff --git a/include/uapi/linux/ife.h b/include/uapi/linux/ife.h
new file mode 100644
index 0000000..bdd953c
--- /dev/null
+++ b/include/uapi/linux/ife.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UAPI_IFE_H
+#define __UAPI_IFE_H
+
+#define IFE_METAHDRLEN 2
+
+enum {
+ IFE_META_SKBMARK = 1,
+ IFE_META_HASHID,
+ IFE_META_PRIO,
+ IFE_META_QMAP,
+ IFE_META_TCINDEX,
+ __IFE_META_MAX
+};
+
+/*Can be overridden at runtime by module option*/
+#define IFE_META_MAX (__IFE_META_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h
new file mode 100644
index 0000000..6a6c97c
--- /dev/null
+++ b/include/uapi/linux/ila.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* ila.h - ILA Interface */
+
+#ifndef _LINUX_ILA_H
+#define _LINUX_ILA_H
+
+/* NETLINK_GENERIC related info */
+#define ILA_GENL_NAME "ila"
+#define ILA_GENL_VERSION 0x1
+
+enum {
+ ILA_ATTR_UNSPEC,
+ ILA_ATTR_LOCATOR, /* u64 */
+ ILA_ATTR_IDENTIFIER, /* u64 */
+ ILA_ATTR_LOCATOR_MATCH, /* u64 */
+ ILA_ATTR_IFINDEX, /* s32 */
+ ILA_ATTR_DIR, /* u32 */
+ ILA_ATTR_PAD,
+ ILA_ATTR_CSUM_MODE, /* u8 */
+ ILA_ATTR_IDENT_TYPE, /* u8 */
+ ILA_ATTR_HOOK_TYPE, /* u8 */
+
+ __ILA_ATTR_MAX,
+};
+
+#define ILA_ATTR_MAX (__ILA_ATTR_MAX - 1)
+
+enum {
+ ILA_CMD_UNSPEC,
+ ILA_CMD_ADD,
+ ILA_CMD_DEL,
+ ILA_CMD_GET,
+ ILA_CMD_FLUSH,
+
+ __ILA_CMD_MAX,
+};
+
+#define ILA_CMD_MAX (__ILA_CMD_MAX - 1)
+
+#define ILA_DIR_IN (1 << 0)
+#define ILA_DIR_OUT (1 << 1)
+
+enum {
+ ILA_CSUM_ADJUST_TRANSPORT,
+ ILA_CSUM_NEUTRAL_MAP,
+ ILA_CSUM_NO_ACTION,
+ ILA_CSUM_NEUTRAL_MAP_AUTO,
+};
+
+enum {
+ ILA_ATYPE_IID = 0,
+ ILA_ATYPE_LUID,
+ ILA_ATYPE_VIRT_V4,
+ ILA_ATYPE_VIRT_UNI_V6,
+ ILA_ATYPE_VIRT_MULTI_V6,
+ ILA_ATYPE_NONLOCAL_ADDR,
+ ILA_ATYPE_RSVD_1,
+ ILA_ATYPE_RSVD_2,
+
+ ILA_ATYPE_USE_FORMAT = 32, /* Get type from type field in identifier */
+};
+
+enum {
+ ILA_HOOK_ROUTE_OUTPUT,
+ ILA_HOOK_ROUTE_INPUT,
+};
+
+#endif /* _LINUX_ILA_H */
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
new file mode 100644
index 0000000..7bdd684
--- /dev/null
+++ b/include/uapi/linux/in.h
@@ -0,0 +1,333 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions of the Internet Protocol.
+ *
+ * Version: @(#)in.h 1.0.1 04/21/93
+ *
+ * Authors: Original taken from the GNU Project <netinet/in.h> file.
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_IN_H
+#define _LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols. */
+enum {
+ IPPROTO_IP = 0, /* Dummy protocol for TCP */
+#define IPPROTO_IP IPPROTO_IP
+ IPPROTO_ICMP = 1, /* Internet Control Message Protocol */
+#define IPPROTO_ICMP IPPROTO_ICMP
+ IPPROTO_IGMP = 2, /* Internet Group Management Protocol */
+#define IPPROTO_IGMP IPPROTO_IGMP
+ IPPROTO_IPIP = 4, /* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP IPPROTO_IPIP
+ IPPROTO_TCP = 6, /* Transmission Control Protocol */
+#define IPPROTO_TCP IPPROTO_TCP
+ IPPROTO_EGP = 8, /* Exterior Gateway Protocol */
+#define IPPROTO_EGP IPPROTO_EGP
+ IPPROTO_PUP = 12, /* PUP protocol */
+#define IPPROTO_PUP IPPROTO_PUP
+ IPPROTO_UDP = 17, /* User Datagram Protocol */
+#define IPPROTO_UDP IPPROTO_UDP
+ IPPROTO_IDP = 22, /* XNS IDP protocol */
+#define IPPROTO_IDP IPPROTO_IDP
+ IPPROTO_TP = 29, /* SO Transport Protocol Class 4 */
+#define IPPROTO_TP IPPROTO_TP
+ IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP IPPROTO_DCCP
+ IPPROTO_IPV6 = 41, /* IPv6-in-IPv4 tunnelling */
+#define IPPROTO_IPV6 IPPROTO_IPV6
+ IPPROTO_RSVP = 46, /* RSVP Protocol */
+#define IPPROTO_RSVP IPPROTO_RSVP
+ IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */
+#define IPPROTO_GRE IPPROTO_GRE
+ IPPROTO_ESP = 50, /* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP IPPROTO_ESP
+ IPPROTO_AH = 51, /* Authentication Header protocol */
+#define IPPROTO_AH IPPROTO_AH
+ IPPROTO_MTP = 92, /* Multicast Transport Protocol */
+#define IPPROTO_MTP IPPROTO_MTP
+ IPPROTO_BEETPH = 94, /* IP option pseudo header for BEET */
+#define IPPROTO_BEETPH IPPROTO_BEETPH
+ IPPROTO_ENCAP = 98, /* Encapsulation Header */
+#define IPPROTO_ENCAP IPPROTO_ENCAP
+ IPPROTO_PIM = 103, /* Protocol Independent Multicast */
+#define IPPROTO_PIM IPPROTO_PIM
+ IPPROTO_COMP = 108, /* Compression Header Protocol */
+#define IPPROTO_COMP IPPROTO_COMP
+ IPPROTO_L2TP = 115, /* Layer 2 Tunnelling Protocol */
+#define IPPROTO_L2TP IPPROTO_L2TP
+ IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */
+#define IPPROTO_SCTP IPPROTO_SCTP
+ IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */
+#define IPPROTO_UDPLITE IPPROTO_UDPLITE
+ IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */
+#define IPPROTO_MPLS IPPROTO_MPLS
+ IPPROTO_ETHERNET = 143, /* Ethernet-within-IPv6 Encapsulation */
+#define IPPROTO_ETHERNET IPPROTO_ETHERNET
+ IPPROTO_RAW = 255, /* Raw IP packets */
+#define IPPROTO_RAW IPPROTO_RAW
+ IPPROTO_MPTCP = 262, /* Multipath TCP connection */
+#define IPPROTO_MPTCP IPPROTO_MPTCP
+ IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+ __be32 s_addr;
+};
+#endif
+
+#define IP_TOS 1
+#define IP_TTL 2
+#define IP_HDRINCL 3
+#define IP_OPTIONS 4
+#define IP_ROUTER_ALERT 5
+#define IP_RECVOPTS 6
+#define IP_RETOPTS 7
+#define IP_PKTINFO 8
+#define IP_PKTOPTIONS 9
+#define IP_MTU_DISCOVER 10
+#define IP_RECVERR 11
+#define IP_RECVTTL 12
+#define IP_RECVTOS 13
+#define IP_MTU 14
+#define IP_FREEBIND 15
+#define IP_IPSEC_POLICY 16
+#define IP_XFRM_POLICY 17
+#define IP_PASSSEC 18
+#define IP_TRANSPARENT 19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR 20
+#define IP_RECVORIGDSTADDR IP_ORIGDSTADDR
+
+#define IP_MINTTL 21
+#define IP_NODEFRAG 22
+#define IP_CHECKSUM 23
+#define IP_BIND_ADDRESS_NO_PORT 24
+#define IP_RECVFRAGSIZE 25
+#define IP_RECVERR_RFC4884 26
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT 0 /* Never send DF frames */
+#define IP_PMTUDISC_WANT 1 /* Use per route hints */
+#define IP_PMTUDISC_DO 2 /* Always DF */
+#define IP_PMTUDISC_PROBE 3 /* Ignore dst pmtu */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE 4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT 5
+
+#define IP_MULTICAST_IF 32
+#define IP_MULTICAST_TTL 33
+#define IP_MULTICAST_LOOP 34
+#define IP_ADD_MEMBERSHIP 35
+#define IP_DROP_MEMBERSHIP 36
+#define IP_UNBLOCK_SOURCE 37
+#define IP_BLOCK_SOURCE 38
+#define IP_ADD_SOURCE_MEMBERSHIP 39
+#define IP_DROP_SOURCE_MEMBERSHIP 40
+#define IP_MSFILTER 41
+#define MCAST_JOIN_GROUP 42
+#define MCAST_BLOCK_SOURCE 43
+#define MCAST_UNBLOCK_SOURCE 44
+#define MCAST_LEAVE_GROUP 45
+#define MCAST_JOIN_SOURCE_GROUP 46
+#define MCAST_LEAVE_SOURCE_GROUP 47
+#define MCAST_MSFILTER 48
+#define IP_MULTICAST_ALL 49
+#define IP_UNICAST_IF 50
+#define IP_LOCAL_PORT_RANGE 51
+#define IP_PROTOCOL 52
+
+#define MCAST_EXCLUDE 0
+#define MCAST_INCLUDE 1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL 1
+#define IP_DEFAULT_MULTICAST_LOOP 1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq {
+ struct in_addr imr_multiaddr; /* IP multicast address of group */
+ struct in_addr imr_interface; /* local IP address of interface */
+};
+
+struct ip_mreqn {
+ struct in_addr imr_multiaddr; /* IP multicast address of group */
+ struct in_addr imr_address; /* local IP address of interface */
+ int imr_ifindex; /* Interface index */
+};
+
+struct ip_mreq_source {
+ __be32 imr_multiaddr;
+ __be32 imr_interface;
+ __be32 imr_sourceaddr;
+};
+
+struct ip_msfilter {
+ __be32 imsf_multiaddr;
+ __be32 imsf_interface;
+ __u32 imsf_fmode;
+ __u32 imsf_numsrc;
+ union {
+ __be32 imsf_slist[1];
+ __DECLARE_FLEX_ARRAY(__be32, imsf_slist_flex);
+ };
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+ (sizeof(struct ip_msfilter) - sizeof(__u32) \
+ + (numsrc) * sizeof(__u32))
+
+struct group_req {
+ __u32 gr_interface; /* interface index */
+ struct __kernel_sockaddr_storage gr_group; /* group address */
+};
+
+struct group_source_req {
+ __u32 gsr_interface; /* interface index */
+ struct __kernel_sockaddr_storage gsr_group; /* group address */
+ struct __kernel_sockaddr_storage gsr_source; /* source address */
+};
+
+struct group_filter {
+ union {
+ struct {
+ __u32 gf_interface_aux; /* interface index */
+ struct __kernel_sockaddr_storage gf_group_aux; /* multicast address */
+ __u32 gf_fmode_aux; /* filter mode */
+ __u32 gf_numsrc_aux; /* number of sources */
+ struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */
+ };
+ struct {
+ __u32 gf_interface; /* interface index */
+ struct __kernel_sockaddr_storage gf_group; /* multicast address */
+ __u32 gf_fmode; /* filter mode */
+ __u32 gf_numsrc; /* number of sources */
+ struct __kernel_sockaddr_storage gf_slist_flex[]; /* interface index */
+ };
+ };
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+ (sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+ + (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+ int ipi_ifindex;
+ struct in_addr ipi_spec_dst;
+ struct in_addr ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */
+struct sockaddr_in {
+ __kernel_sa_family_t sin_family; /* Address family */
+ __be16 sin_port; /* Port number */
+ struct in_addr sin_addr; /* Internet address */
+
+ /* Pad to size of `struct sockaddr'. */
+ unsigned char __pad[__SOCK_SIZE__ - sizeof(short int) -
+ sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero __pad /* for BSD UNIX comp. -FvK */
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define IN_CLASSA(a) ((((long int) (a)) & 0x80000000) == 0)
+#define IN_CLASSA_NET 0xff000000
+#define IN_CLASSA_NSHIFT 24
+#define IN_CLASSA_HOST (0xffffffff & ~IN_CLASSA_NET)
+#define IN_CLASSA_MAX 128
+
+#define IN_CLASSB(a) ((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define IN_CLASSB_NET 0xffff0000
+#define IN_CLASSB_NSHIFT 16
+#define IN_CLASSB_HOST (0xffffffff & ~IN_CLASSB_NET)
+#define IN_CLASSB_MAX 65536
+
+#define IN_CLASSC(a) ((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define IN_CLASSC_NET 0xffffff00
+#define IN_CLASSC_NSHIFT 8
+#define IN_CLASSC_HOST (0xffffffff & ~IN_CLASSC_NET)
+
+#define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define IN_MULTICAST(a) IN_CLASSD(a)
+#define IN_MULTICAST_NET 0xe0000000
+
+#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff)
+#define IN_EXPERIMENTAL(a) IN_BADCLASS((a))
+
+#define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define IN_CLASSE_NET 0xffffffff
+#define IN_CLASSE_NSHIFT 0
+
+/* Address to accept any incoming messages. */
+#define INADDR_ANY ((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define INADDR_BROADCAST ((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define INADDR_NONE ((unsigned long int) 0xffffffff)
+
+/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */
+#define INADDR_DUMMY ((unsigned long int) 0xc0000008)
+
+/* Network number for local host loopback. */
+#define IN_LOOPBACKNET 127
+
+/* Address to loopback in software to local host. */
+#define INADDR_LOOPBACK 0x7f000001 /* 127.0.0.1 */
+#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */
+#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */
+#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */
+#define INADDR_ALLSNOOPERS_GROUP 0xe000006aU /* 224.0.0.106 */
+#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h>
+
+
+#endif /* _LINUX_IN_H */
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
new file mode 100644
index 0000000..776fb41
--- /dev/null
+++ b/include/uapi/linux/in6.h
@@ -0,0 +1,302 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Types and definitions for AF_INET6
+ * Linux INET6 implementation
+ *
+ * Authors:
+ * Pedro Roque <roque@di.fc.ul.pt>
+ *
+ * Sources:
+ * IPv6 Program Interfaces for BSD Systems
+ * <draft-ietf-ipngwg-bsd-api-05.txt>
+ *
+ * Advanced Sockets API for IPv6
+ * <draft-stevens-advanced-api-00.txt>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_IN6_H
+#define _LINUX_IN6_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+
+/*
+ * IPv6 address structure
+ */
+
+#if __UAPI_DEF_IN6_ADDR
+struct in6_addr {
+ union {
+ __u8 u6_addr8[16];
+#if __UAPI_DEF_IN6_ADDR_ALT
+ __be16 u6_addr16[8];
+ __be32 u6_addr32[4];
+#endif
+ } in6_u;
+#define s6_addr in6_u.u6_addr8
+#if __UAPI_DEF_IN6_ADDR_ALT
+#define s6_addr16 in6_u.u6_addr16
+#define s6_addr32 in6_u.u6_addr32
+#endif
+};
+#endif /* __UAPI_DEF_IN6_ADDR */
+
+#if __UAPI_DEF_SOCKADDR_IN6
+struct sockaddr_in6 {
+ unsigned short int sin6_family; /* AF_INET6 */
+ __be16 sin6_port; /* Transport layer port # */
+ __be32 sin6_flowinfo; /* IPv6 flow information */
+ struct in6_addr sin6_addr; /* IPv6 address */
+ __u32 sin6_scope_id; /* scope id (new in RFC2553) */
+};
+#endif /* __UAPI_DEF_SOCKADDR_IN6 */
+
+#if __UAPI_DEF_IPV6_MREQ
+struct ipv6_mreq {
+ /* IPv6 multicast address of group */
+ struct in6_addr ipv6mr_multiaddr;
+
+ /* local IPv6 address of interface */
+ int ipv6mr_ifindex;
+};
+#endif /* __UAPI_DEF_IVP6_MREQ */
+
+#define ipv6mr_acaddr ipv6mr_multiaddr
+
+struct in6_flowlabel_req {
+ struct in6_addr flr_dst;
+ __be32 flr_label;
+ __u8 flr_action;
+ __u8 flr_share;
+ __u16 flr_flags;
+ __u16 flr_expires;
+ __u16 flr_linger;
+ __u32 __flr_pad;
+ /* Options in format of IPV6_PKTOPTIONS */
+};
+
+#define IPV6_FL_A_GET 0
+#define IPV6_FL_A_PUT 1
+#define IPV6_FL_A_RENEW 2
+
+#define IPV6_FL_F_CREATE 1
+#define IPV6_FL_F_EXCL 2
+#define IPV6_FL_F_REFLECT 4
+#define IPV6_FL_F_REMOTE 8
+
+#define IPV6_FL_S_NONE 0
+#define IPV6_FL_S_EXCL 1
+#define IPV6_FL_S_PROCESS 2
+#define IPV6_FL_S_USER 3
+#define IPV6_FL_S_ANY 255
+
+
+/*
+ * Bitmask constant declarations to help applications select out the
+ * flow label and priority fields.
+ *
+ * Note that this are in host byte order while the flowinfo field of
+ * sockaddr_in6 is in network byte order.
+ */
+
+#define IPV6_FLOWINFO_FLOWLABEL 0x000fffff
+#define IPV6_FLOWINFO_PRIORITY 0x0ff00000
+
+/* These definitions are obsolete */
+#define IPV6_PRIORITY_UNCHARACTERIZED 0x0000
+#define IPV6_PRIORITY_FILLER 0x0100
+#define IPV6_PRIORITY_UNATTENDED 0x0200
+#define IPV6_PRIORITY_RESERVED1 0x0300
+#define IPV6_PRIORITY_BULK 0x0400
+#define IPV6_PRIORITY_RESERVED2 0x0500
+#define IPV6_PRIORITY_INTERACTIVE 0x0600
+#define IPV6_PRIORITY_CONTROL 0x0700
+#define IPV6_PRIORITY_8 0x0800
+#define IPV6_PRIORITY_9 0x0900
+#define IPV6_PRIORITY_10 0x0a00
+#define IPV6_PRIORITY_11 0x0b00
+#define IPV6_PRIORITY_12 0x0c00
+#define IPV6_PRIORITY_13 0x0d00
+#define IPV6_PRIORITY_14 0x0e00
+#define IPV6_PRIORITY_15 0x0f00
+
+/*
+ * IPV6 extension headers
+ */
+#if __UAPI_DEF_IPPROTO_V6
+#define IPPROTO_HOPOPTS 0 /* IPv6 hop-by-hop options */
+#define IPPROTO_ROUTING 43 /* IPv6 routing header */
+#define IPPROTO_FRAGMENT 44 /* IPv6 fragmentation header */
+#define IPPROTO_ICMPV6 58 /* ICMPv6 */
+#define IPPROTO_NONE 59 /* IPv6 no next header */
+#define IPPROTO_DSTOPTS 60 /* IPv6 destination options */
+#define IPPROTO_MH 135 /* IPv6 mobility header */
+#endif /* __UAPI_DEF_IPPROTO_V6 */
+
+/*
+ * IPv6 TLV options.
+ */
+#define IPV6_TLV_PAD1 0
+#define IPV6_TLV_PADN 1
+#define IPV6_TLV_ROUTERALERT 5
+#define IPV6_TLV_CALIPSO 7 /* RFC 5570 */
+#define IPV6_TLV_IOAM 49 /* RFC 9486 */
+#define IPV6_TLV_JUMBO 194
+#define IPV6_TLV_HAO 201 /* home address option */
+
+/*
+ * IPV6 socket options
+ */
+#if __UAPI_DEF_IPV6_OPTIONS
+#define IPV6_ADDRFORM 1
+#define IPV6_2292PKTINFO 2
+#define IPV6_2292HOPOPTS 3
+#define IPV6_2292DSTOPTS 4
+#define IPV6_2292RTHDR 5
+#define IPV6_2292PKTOPTIONS 6
+#define IPV6_CHECKSUM 7
+#define IPV6_2292HOPLIMIT 8
+#define IPV6_NEXTHOP 9
+#define IPV6_AUTHHDR 10 /* obsolete */
+#define IPV6_FLOWINFO 11
+
+#define IPV6_UNICAST_HOPS 16
+#define IPV6_MULTICAST_IF 17
+#define IPV6_MULTICAST_HOPS 18
+#define IPV6_MULTICAST_LOOP 19
+#define IPV6_ADD_MEMBERSHIP 20
+#define IPV6_DROP_MEMBERSHIP 21
+#define IPV6_ROUTER_ALERT 22
+#define IPV6_MTU_DISCOVER 23
+#define IPV6_MTU 24
+#define IPV6_RECVERR 25
+#define IPV6_V6ONLY 26
+#define IPV6_JOIN_ANYCAST 27
+#define IPV6_LEAVE_ANYCAST 28
+#define IPV6_MULTICAST_ALL 29
+#define IPV6_ROUTER_ALERT_ISOLATE 30
+#define IPV6_RECVERR_RFC4884 31
+
+/* IPV6_MTU_DISCOVER values */
+#define IPV6_PMTUDISC_DONT 0
+#define IPV6_PMTUDISC_WANT 1
+#define IPV6_PMTUDISC_DO 2
+#define IPV6_PMTUDISC_PROBE 3
+/* same as IPV6_PMTUDISC_PROBE, provided for symetry with IPv4
+ * also see comments on IP_PMTUDISC_INTERFACE
+ */
+#define IPV6_PMTUDISC_INTERFACE 4
+/* weaker version of IPV6_PMTUDISC_INTERFACE, which allows packets to
+ * get fragmented if they exceed the interface mtu
+ */
+#define IPV6_PMTUDISC_OMIT 5
+
+/* Flowlabel */
+#define IPV6_FLOWLABEL_MGR 32
+#define IPV6_FLOWINFO_SEND 33
+
+#define IPV6_IPSEC_POLICY 34
+#define IPV6_XFRM_POLICY 35
+#define IPV6_HDRINCL 36
+#endif
+
+/*
+ * Multicast:
+ * Following socket options are shared between IPv4 and IPv6.
+ *
+ * MCAST_JOIN_GROUP 42
+ * MCAST_BLOCK_SOURCE 43
+ * MCAST_UNBLOCK_SOURCE 44
+ * MCAST_LEAVE_GROUP 45
+ * MCAST_JOIN_SOURCE_GROUP 46
+ * MCAST_LEAVE_SOURCE_GROUP 47
+ * MCAST_MSFILTER 48
+ */
+
+/*
+ * Advanced API (RFC3542) (1)
+ *
+ * Note: IPV6_RECVRTHDRDSTOPTS does not exist. see net/ipv6/datagram.c.
+ */
+
+#define IPV6_RECVPKTINFO 49
+#define IPV6_PKTINFO 50
+#define IPV6_RECVHOPLIMIT 51
+#define IPV6_HOPLIMIT 52
+#define IPV6_RECVHOPOPTS 53
+#define IPV6_HOPOPTS 54
+#define IPV6_RTHDRDSTOPTS 55
+#define IPV6_RECVRTHDR 56
+#define IPV6_RTHDR 57
+#define IPV6_RECVDSTOPTS 58
+#define IPV6_DSTOPTS 59
+#define IPV6_RECVPATHMTU 60
+#define IPV6_PATHMTU 61
+#define IPV6_DONTFRAG 62
+#if 0 /* not yet */
+#define IPV6_USE_MIN_MTU 63
+#endif
+
+/*
+ * Netfilter (1)
+ *
+ * Following socket options are used in ip6_tables;
+ * see include/linux/netfilter_ipv6/ip6_tables.h.
+ *
+ * IP6T_SO_SET_REPLACE / IP6T_SO_GET_INFO 64
+ * IP6T_SO_SET_ADD_COUNTERS / IP6T_SO_GET_ENTRIES 65
+ */
+
+/*
+ * Advanced API (RFC3542) (2)
+ */
+#define IPV6_RECVTCLASS 66
+#define IPV6_TCLASS 67
+
+/*
+ * Netfilter (2)
+ *
+ * Following socket options are used in ip6_tables;
+ * see include/linux/netfilter_ipv6/ip6_tables.h.
+ *
+ * IP6T_SO_GET_REVISION_MATCH 68
+ * IP6T_SO_GET_REVISION_TARGET 69
+ * IP6T_SO_ORIGINAL_DST 80
+ */
+
+#define IPV6_AUTOFLOWLABEL 70
+/* RFC5014: Source address selection */
+#define IPV6_ADDR_PREFERENCES 72
+
+#define IPV6_PREFER_SRC_TMP 0x0001
+#define IPV6_PREFER_SRC_PUBLIC 0x0002
+#define IPV6_PREFER_SRC_PUBTMP_DEFAULT 0x0100
+#define IPV6_PREFER_SRC_COA 0x0004
+#define IPV6_PREFER_SRC_HOME 0x0400
+#define IPV6_PREFER_SRC_CGA 0x0008
+#define IPV6_PREFER_SRC_NONCGA 0x0800
+
+/* RFC5082: Generalized Ttl Security Mechanism */
+#define IPV6_MINHOPCOUNT 73
+
+#define IPV6_ORIGDSTADDR 74
+#define IPV6_RECVORIGDSTADDR IPV6_ORIGDSTADDR
+#define IPV6_TRANSPARENT 75
+#define IPV6_UNICAST_IF 76
+#define IPV6_RECVFRAGSIZE 77
+#define IPV6_FREEBIND 78
+
+/*
+ * Multicast Routing:
+ * see include/uapi/linux/mroute6.h.
+ *
+ * MRT6_BASE 200
+ * ...
+ * MRT6_MAX
+ */
+#endif /* _LINUX_IN6_H */
diff --git a/include/uapi/linux/in_route.h b/include/uapi/linux/in_route.h
new file mode 100644
index 0000000..0cc2c23
--- /dev/null
+++ b/include/uapi/linux/in_route.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_IN_ROUTE_H
+#define _LINUX_IN_ROUTE_H
+
+/* IPv4 routing cache flags */
+
+#define RTCF_DEAD RTNH_F_DEAD
+#define RTCF_ONLINK RTNH_F_ONLINK
+
+/* Obsolete flag. About to be deleted */
+#define RTCF_NOPMTUDISC RTM_F_NOPMTUDISC
+
+#define RTCF_NOTIFY 0x00010000
+#define RTCF_DIRECTDST 0x00020000 /* unused */
+#define RTCF_REDIRECTED 0x00040000
+#define RTCF_TPROXY 0x00080000 /* unused */
+
+#define RTCF_FAST 0x00200000 /* unused */
+#define RTCF_MASQ 0x00400000 /* unused */
+#define RTCF_SNAT 0x00800000 /* unused */
+#define RTCF_DOREDIRECT 0x01000000
+#define RTCF_DIRECTSRC 0x04000000
+#define RTCF_DNAT 0x08000000
+#define RTCF_BROADCAST 0x10000000
+#define RTCF_MULTICAST 0x20000000
+#define RTCF_REJECT 0x40000000 /* unused */
+#define RTCF_LOCAL 0x80000000
+
+#define RTCF_NAT (RTCF_DNAT|RTCF_SNAT)
+
+#define RT_TOS(tos) ((tos)&IPTOS_TOS_MASK)
+
+#endif /* _LINUX_IN_ROUTE_H */
diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
new file mode 100644
index 0000000..d81cb69
--- /dev/null
+++ b/include/uapi/linux/inet_diag.h
@@ -0,0 +1,239 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _INET_DIAG_H_
+#define _INET_DIAG_H_
+
+#include <linux/types.h>
+
+/* Just some random number */
+#define TCPDIAG_GETSOCK 18
+#define DCCPDIAG_GETSOCK 19
+
+#define INET_DIAG_GETSOCK_MAX 24
+
+/* Socket identity */
+struct inet_diag_sockid {
+ __be16 idiag_sport;
+ __be16 idiag_dport;
+ __be32 idiag_src[4];
+ __be32 idiag_dst[4];
+ __u32 idiag_if;
+ __u32 idiag_cookie[2];
+#define INET_DIAG_NOCOOKIE (~0U)
+};
+
+/* Request structure */
+
+struct inet_diag_req {
+ __u8 idiag_family; /* Family of addresses. */
+ __u8 idiag_src_len;
+ __u8 idiag_dst_len;
+ __u8 idiag_ext; /* Query extended information */
+
+ struct inet_diag_sockid id;
+
+ __u32 idiag_states; /* States to dump */
+ __u32 idiag_dbs; /* Tables to dump (NI) */
+};
+
+struct inet_diag_req_v2 {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u8 idiag_ext;
+ __u8 pad;
+ __u32 idiag_states;
+ struct inet_diag_sockid id;
+};
+
+/*
+ * SOCK_RAW sockets require the underlied protocol to be
+ * additionally specified so we can use @pad member for
+ * this, but we can't rename it because userspace programs
+ * still may depend on this name. Instead lets use another
+ * structure definition as an alias for struct
+ * @inet_diag_req_v2.
+ */
+struct inet_diag_req_raw {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u8 idiag_ext;
+ __u8 sdiag_raw_protocol;
+ __u32 idiag_states;
+ struct inet_diag_sockid id;
+};
+
+enum {
+ INET_DIAG_REQ_NONE,
+ INET_DIAG_REQ_BYTECODE,
+ INET_DIAG_REQ_SK_BPF_STORAGES,
+ INET_DIAG_REQ_PROTOCOL,
+ __INET_DIAG_REQ_MAX,
+};
+
+#define INET_DIAG_REQ_MAX (__INET_DIAG_REQ_MAX - 1)
+
+/* Bytecode is sequence of 4 byte commands followed by variable arguments.
+ * All the commands identified by "code" are conditional jumps forward:
+ * to offset cc+"yes" or to offset cc+"no". "yes" is supposed to be
+ * length of the command and its arguments.
+ */
+
+struct inet_diag_bc_op {
+ unsigned char code;
+ unsigned char yes;
+ unsigned short no;
+};
+
+enum {
+ INET_DIAG_BC_NOP,
+ INET_DIAG_BC_JMP,
+ INET_DIAG_BC_S_GE,
+ INET_DIAG_BC_S_LE,
+ INET_DIAG_BC_D_GE,
+ INET_DIAG_BC_D_LE,
+ INET_DIAG_BC_AUTO,
+ INET_DIAG_BC_S_COND,
+ INET_DIAG_BC_D_COND,
+ INET_DIAG_BC_DEV_COND, /* u32 ifindex */
+ INET_DIAG_BC_MARK_COND,
+ INET_DIAG_BC_S_EQ,
+ INET_DIAG_BC_D_EQ,
+ INET_DIAG_BC_CGROUP_COND, /* u64 cgroup v2 ID */
+};
+
+struct inet_diag_hostcond {
+ __u8 family;
+ __u8 prefix_len;
+ int port;
+ __be32 addr[];
+};
+
+struct inet_diag_markcond {
+ __u32 mark;
+ __u32 mask;
+};
+
+/* Base info structure. It contains socket identity (addrs/ports/cookie)
+ * and, alas, the information shown by netstat. */
+struct inet_diag_msg {
+ __u8 idiag_family;
+ __u8 idiag_state;
+ __u8 idiag_timer;
+ __u8 idiag_retrans;
+
+ struct inet_diag_sockid id;
+
+ __u32 idiag_expires;
+ __u32 idiag_rqueue;
+ __u32 idiag_wqueue;
+ __u32 idiag_uid;
+ __u32 idiag_inode;
+};
+
+/* Extensions */
+
+enum {
+ INET_DIAG_NONE,
+ INET_DIAG_MEMINFO,
+ INET_DIAG_INFO,
+ INET_DIAG_VEGASINFO,
+ INET_DIAG_CONG,
+ INET_DIAG_TOS,
+ INET_DIAG_TCLASS,
+ INET_DIAG_SKMEMINFO,
+ INET_DIAG_SHUTDOWN,
+
+ /*
+ * Next extenstions cannot be requested in struct inet_diag_req_v2:
+ * its field idiag_ext has only 8 bits.
+ */
+
+ INET_DIAG_DCTCPINFO, /* request as INET_DIAG_VEGASINFO */
+ INET_DIAG_PROTOCOL, /* response attribute only */
+ INET_DIAG_SKV6ONLY,
+ INET_DIAG_LOCALS,
+ INET_DIAG_PEERS,
+ INET_DIAG_PAD,
+ INET_DIAG_MARK, /* only with CAP_NET_ADMIN */
+ INET_DIAG_BBRINFO, /* request as INET_DIAG_VEGASINFO */
+ INET_DIAG_CLASS_ID, /* request as INET_DIAG_TCLASS */
+ INET_DIAG_MD5SIG,
+ INET_DIAG_ULP_INFO,
+ INET_DIAG_SK_BPF_STORAGES,
+ INET_DIAG_CGROUP_ID,
+ INET_DIAG_SOCKOPT,
+ __INET_DIAG_MAX,
+};
+
+#define INET_DIAG_MAX (__INET_DIAG_MAX - 1)
+
+enum {
+ INET_ULP_INFO_UNSPEC,
+ INET_ULP_INFO_NAME,
+ INET_ULP_INFO_TLS,
+ INET_ULP_INFO_MPTCP,
+ __INET_ULP_INFO_MAX,
+};
+#define INET_ULP_INFO_MAX (__INET_ULP_INFO_MAX - 1)
+
+/* INET_DIAG_MEM */
+
+struct inet_diag_meminfo {
+ __u32 idiag_rmem;
+ __u32 idiag_wmem;
+ __u32 idiag_fmem;
+ __u32 idiag_tmem;
+};
+
+/* INET_DIAG_SOCKOPT */
+
+struct inet_diag_sockopt {
+ __u8 recverr:1,
+ is_icsk:1,
+ freebind:1,
+ hdrincl:1,
+ mc_loop:1,
+ transparent:1,
+ mc_all:1,
+ nodefrag:1;
+ __u8 bind_address_no_port:1,
+ recverr_rfc4884:1,
+ defer_connect:1,
+ unused:5;
+};
+
+/* INET_DIAG_VEGASINFO */
+
+struct tcpvegas_info {
+ __u32 tcpv_enabled;
+ __u32 tcpv_rttcnt;
+ __u32 tcpv_rtt;
+ __u32 tcpv_minrtt;
+};
+
+/* INET_DIAG_DCTCPINFO */
+
+struct tcp_dctcp_info {
+ __u16 dctcp_enabled;
+ __u16 dctcp_ce_state;
+ __u32 dctcp_alpha;
+ __u32 dctcp_ab_ecn;
+ __u32 dctcp_ab_tot;
+};
+
+/* INET_DIAG_BBRINFO */
+
+struct tcp_bbr_info {
+ /* u64 bw: max-filtered BW (app throughput) estimate in Byte per sec: */
+ __u32 bbr_bw_lo; /* lower 32 bits of bw */
+ __u32 bbr_bw_hi; /* upper 32 bits of bw */
+ __u32 bbr_min_rtt; /* min-filtered RTT in uSec */
+ __u32 bbr_pacing_gain; /* pacing gain shifted left 8 bits */
+ __u32 bbr_cwnd_gain; /* cwnd gain shifted left 8 bits */
+};
+
+union tcp_cc_info {
+ struct tcpvegas_info vegas;
+ struct tcp_dctcp_info dctcp;
+ struct tcp_bbr_info bbr;
+};
+#endif /* _INET_DIAG_H_ */
diff --git a/include/uapi/linux/ioam6.h b/include/uapi/linux/ioam6.h
new file mode 100644
index 0000000..e646011
--- /dev/null
+++ b/include/uapi/linux/ioam6.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * IPv6 IOAM implementation
+ *
+ * Author:
+ * Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _LINUX_IOAM6_H
+#define _LINUX_IOAM6_H
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+
+#define IOAM6_U16_UNAVAILABLE U16_MAX
+#define IOAM6_U32_UNAVAILABLE U32_MAX
+#define IOAM6_U64_UNAVAILABLE U64_MAX
+
+#define IOAM6_DEFAULT_ID (IOAM6_U32_UNAVAILABLE >> 8)
+#define IOAM6_DEFAULT_ID_WIDE (IOAM6_U64_UNAVAILABLE >> 8)
+#define IOAM6_DEFAULT_IF_ID IOAM6_U16_UNAVAILABLE
+#define IOAM6_DEFAULT_IF_ID_WIDE IOAM6_U32_UNAVAILABLE
+
+/*
+ * IPv6 IOAM Option Header
+ */
+struct ioam6_hdr {
+ __u8 opt_type;
+ __u8 opt_len;
+ __u8 :8; /* reserved */
+#define IOAM6_TYPE_PREALLOC 0
+ __u8 type;
+} __attribute__((packed));
+
+/*
+ * IOAM Trace Header
+ */
+struct ioam6_trace_hdr {
+ __be16 namespace_id;
+
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+
+ __u8 :1, /* unused */
+ :1, /* unused */
+ overflow:1,
+ nodelen:5;
+
+ __u8 remlen:7,
+ :1; /* unused */
+
+ union {
+ __be32 type_be32;
+
+ struct {
+ __u32 bit7:1,
+ bit6:1,
+ bit5:1,
+ bit4:1,
+ bit3:1,
+ bit2:1,
+ bit1:1,
+ bit0:1,
+ bit15:1, /* unused */
+ bit14:1, /* unused */
+ bit13:1, /* unused */
+ bit12:1, /* unused */
+ bit11:1,
+ bit10:1,
+ bit9:1,
+ bit8:1,
+ bit23:1, /* reserved */
+ bit22:1,
+ bit21:1, /* unused */
+ bit20:1, /* unused */
+ bit19:1, /* unused */
+ bit18:1, /* unused */
+ bit17:1, /* unused */
+ bit16:1, /* unused */
+ :8; /* reserved */
+ } type;
+ };
+
+#elif defined(__BIG_ENDIAN_BITFIELD)
+
+ __u8 nodelen:5,
+ overflow:1,
+ :1, /* unused */
+ :1; /* unused */
+
+ __u8 :1, /* unused */
+ remlen:7;
+
+ union {
+ __be32 type_be32;
+
+ struct {
+ __u32 bit0:1,
+ bit1:1,
+ bit2:1,
+ bit3:1,
+ bit4:1,
+ bit5:1,
+ bit6:1,
+ bit7:1,
+ bit8:1,
+ bit9:1,
+ bit10:1,
+ bit11:1,
+ bit12:1, /* unused */
+ bit13:1, /* unused */
+ bit14:1, /* unused */
+ bit15:1, /* unused */
+ bit16:1, /* unused */
+ bit17:1, /* unused */
+ bit18:1, /* unused */
+ bit19:1, /* unused */
+ bit20:1, /* unused */
+ bit21:1, /* unused */
+ bit22:1,
+ bit23:1, /* reserved */
+ :8; /* reserved */
+ } type;
+ };
+
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+
+#define IOAM6_TRACE_DATA_SIZE_MAX 244
+ __u8 data[];
+} __attribute__((packed));
+
+#endif /* _LINUX_IOAM6_H */
diff --git a/include/uapi/linux/ioam6_genl.h b/include/uapi/linux/ioam6_genl.h
new file mode 100644
index 0000000..6043d9f
--- /dev/null
+++ b/include/uapi/linux/ioam6_genl.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * IPv6 IOAM Generic Netlink API
+ *
+ * Author:
+ * Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _LINUX_IOAM6_GENL_H
+#define _LINUX_IOAM6_GENL_H
+
+#define IOAM6_GENL_NAME "IOAM6"
+#define IOAM6_GENL_VERSION 0x1
+
+enum {
+ IOAM6_ATTR_UNSPEC,
+
+ IOAM6_ATTR_NS_ID, /* u16 */
+ IOAM6_ATTR_NS_DATA, /* u32 */
+ IOAM6_ATTR_NS_DATA_WIDE,/* u64 */
+
+#define IOAM6_MAX_SCHEMA_DATA_LEN (255 * 4)
+ IOAM6_ATTR_SC_ID, /* u32 */
+ IOAM6_ATTR_SC_DATA, /* Binary */
+ IOAM6_ATTR_SC_NONE, /* Flag */
+
+ IOAM6_ATTR_PAD,
+
+ __IOAM6_ATTR_MAX,
+};
+
+#define IOAM6_ATTR_MAX (__IOAM6_ATTR_MAX - 1)
+
+enum {
+ IOAM6_CMD_UNSPEC,
+
+ IOAM6_CMD_ADD_NAMESPACE,
+ IOAM6_CMD_DEL_NAMESPACE,
+ IOAM6_CMD_DUMP_NAMESPACES,
+
+ IOAM6_CMD_ADD_SCHEMA,
+ IOAM6_CMD_DEL_SCHEMA,
+ IOAM6_CMD_DUMP_SCHEMAS,
+
+ IOAM6_CMD_NS_SET_SCHEMA,
+
+ __IOAM6_CMD_MAX,
+};
+
+#define IOAM6_CMD_MAX (__IOAM6_CMD_MAX - 1)
+
+#endif /* _LINUX_IOAM6_GENL_H */
diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h
new file mode 100644
index 0000000..750357b
--- /dev/null
+++ b/include/uapi/linux/ioam6_iptunnel.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * IPv6 IOAM Lightweight Tunnel API
+ *
+ * Author:
+ * Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _LINUX_IOAM6_IPTUNNEL_H
+#define _LINUX_IOAM6_IPTUNNEL_H
+
+/* Encap modes:
+ * - inline: direct insertion
+ * - encap: ip6ip6 encapsulation
+ * - auto: __inline__ for local packets, encap for in-transit packets
+ */
+enum {
+ __IOAM6_IPTUNNEL_MODE_MIN,
+
+ IOAM6_IPTUNNEL_MODE_INLINE,
+ IOAM6_IPTUNNEL_MODE_ENCAP,
+ IOAM6_IPTUNNEL_MODE_AUTO,
+
+ __IOAM6_IPTUNNEL_MODE_MAX,
+};
+
+#define IOAM6_IPTUNNEL_MODE_MIN (__IOAM6_IPTUNNEL_MODE_MIN + 1)
+#define IOAM6_IPTUNNEL_MODE_MAX (__IOAM6_IPTUNNEL_MODE_MAX - 1)
+
+enum {
+ IOAM6_IPTUNNEL_UNSPEC,
+
+ /* Encap mode */
+ IOAM6_IPTUNNEL_MODE, /* u8 */
+
+ /* Tunnel dst address.
+ * For encap,auto modes.
+ */
+ IOAM6_IPTUNNEL_DST, /* struct in6_addr */
+
+ /* IOAM Trace Header */
+ IOAM6_IPTUNNEL_TRACE, /* struct ioam6_trace_hdr */
+
+ /* Insertion frequency:
+ * "k over n" packets (0 < k <= n)
+ * [0.0001% ... 100%]
+ */
+#define IOAM6_IPTUNNEL_FREQ_MIN 1
+#define IOAM6_IPTUNNEL_FREQ_MAX 1000000
+ IOAM6_IPTUNNEL_FREQ_K, /* u32 */
+ IOAM6_IPTUNNEL_FREQ_N, /* u32 */
+
+ __IOAM6_IPTUNNEL_MAX,
+};
+
+#define IOAM6_IPTUNNEL_MAX (__IOAM6_IPTUNNEL_MAX - 1)
+
+#endif /* _LINUX_IOAM6_IPTUNNEL_H */
diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h
new file mode 100644
index 0000000..9b4dd89
--- /dev/null
+++ b/include/uapi/linux/ip.h
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions for the IP protocol.
+ *
+ * Version: @(#)ip.h 1.0.2 04/28/93
+ *
+ * Authors: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_IP_H
+#define _LINUX_IP_H
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <asm/byteorder.h>
+
+#define IPTOS_TOS_MASK 0x1E
+#define IPTOS_TOS(tos) ((tos)&IPTOS_TOS_MASK)
+#define IPTOS_LOWDELAY 0x10
+#define IPTOS_THROUGHPUT 0x08
+#define IPTOS_RELIABILITY 0x04
+#define IPTOS_MINCOST 0x02
+
+#define IPTOS_PREC_MASK 0xE0
+#define IPTOS_PREC(tos) ((tos)&IPTOS_PREC_MASK)
+#define IPTOS_PREC_NETCONTROL 0xe0
+#define IPTOS_PREC_INTERNETCONTROL 0xc0
+#define IPTOS_PREC_CRITIC_ECP 0xa0
+#define IPTOS_PREC_FLASHOVERRIDE 0x80
+#define IPTOS_PREC_FLASH 0x60
+#define IPTOS_PREC_IMMEDIATE 0x40
+#define IPTOS_PREC_PRIORITY 0x20
+#define IPTOS_PREC_ROUTINE 0x00
+
+
+/* IP options */
+#define IPOPT_COPY 0x80
+#define IPOPT_CLASS_MASK 0x60
+#define IPOPT_NUMBER_MASK 0x1f
+
+#define IPOPT_COPIED(o) ((o)&IPOPT_COPY)
+#define IPOPT_CLASS(o) ((o)&IPOPT_CLASS_MASK)
+#define IPOPT_NUMBER(o) ((o)&IPOPT_NUMBER_MASK)
+
+#define IPOPT_CONTROL 0x00
+#define IPOPT_RESERVED1 0x20
+#define IPOPT_MEASUREMENT 0x40
+#define IPOPT_RESERVED2 0x60
+
+#define IPOPT_END (0 |IPOPT_CONTROL)
+#define IPOPT_NOOP (1 |IPOPT_CONTROL)
+#define IPOPT_SEC (2 |IPOPT_CONTROL|IPOPT_COPY)
+#define IPOPT_LSRR (3 |IPOPT_CONTROL|IPOPT_COPY)
+#define IPOPT_TIMESTAMP (4 |IPOPT_MEASUREMENT)
+#define IPOPT_CIPSO (6 |IPOPT_CONTROL|IPOPT_COPY)
+#define IPOPT_RR (7 |IPOPT_CONTROL)
+#define IPOPT_SID (8 |IPOPT_CONTROL|IPOPT_COPY)
+#define IPOPT_SSRR (9 |IPOPT_CONTROL|IPOPT_COPY)
+#define IPOPT_RA (20|IPOPT_CONTROL|IPOPT_COPY)
+
+#define IPVERSION 4
+#define MAXTTL 255
+#define IPDEFTTL 64
+
+#define IPOPT_OPTVAL 0
+#define IPOPT_OLEN 1
+#define IPOPT_OFFSET 2
+#define IPOPT_MINOFF 4
+#define MAX_IPOPTLEN 40
+#define IPOPT_NOP IPOPT_NOOP
+#define IPOPT_EOL IPOPT_END
+#define IPOPT_TS IPOPT_TIMESTAMP
+
+#define IPOPT_TS_TSONLY 0 /* timestamps only */
+#define IPOPT_TS_TSANDADDR 1 /* timestamps and addresses */
+#define IPOPT_TS_PRESPEC 3 /* specified modules only */
+
+#define IPV4_BEET_PHMAXLEN 8
+
+struct iphdr {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u8 ihl:4,
+ version:4;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+ __u8 version:4,
+ ihl:4;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+ __u8 tos;
+ __be16 tot_len;
+ __be16 id;
+ __be16 frag_off;
+ __u8 ttl;
+ __u8 protocol;
+ __sum16 check;
+ __struct_group(/* no tag */, addrs, /* no attrs */,
+ __be32 saddr;
+ __be32 daddr;
+ );
+ /*The options start here. */
+};
+
+
+struct ip_auth_hdr {
+ __u8 nexthdr;
+ __u8 hdrlen; /* This one is measured in 32 bit units! */
+ __be16 reserved;
+ __be32 spi;
+ __be32 seq_no; /* Sequence number */
+ __u8 auth_data[]; /* Variable len but >=4. Mind the 64 bit alignment! */
+};
+
+struct ip_esp_hdr {
+ __be32 spi;
+ __be32 seq_no; /* Sequence number */
+ __u8 enc_data[]; /* Variable len but >=8. Mind the 64 bit alignment! */
+};
+
+struct ip_comp_hdr {
+ __u8 nexthdr;
+ __u8 flags;
+ __be16 cpi;
+};
+
+struct ip_beet_phdr {
+ __u8 nexthdr;
+ __u8 hdrlen;
+ __u8 padlen;
+ __u8 reserved;
+};
+
+/* index values for the variables in ipv4_devconf */
+enum
+{
+ IPV4_DEVCONF_FORWARDING=1,
+ IPV4_DEVCONF_MC_FORWARDING,
+ IPV4_DEVCONF_PROXY_ARP,
+ IPV4_DEVCONF_ACCEPT_REDIRECTS,
+ IPV4_DEVCONF_SECURE_REDIRECTS,
+ IPV4_DEVCONF_SEND_REDIRECTS,
+ IPV4_DEVCONF_SHARED_MEDIA,
+ IPV4_DEVCONF_RP_FILTER,
+ IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE,
+ IPV4_DEVCONF_BOOTP_RELAY,
+ IPV4_DEVCONF_LOG_MARTIANS,
+ IPV4_DEVCONF_TAG,
+ IPV4_DEVCONF_ARPFILTER,
+ IPV4_DEVCONF_MEDIUM_ID,
+ IPV4_DEVCONF_NOXFRM,
+ IPV4_DEVCONF_NOPOLICY,
+ IPV4_DEVCONF_FORCE_IGMP_VERSION,
+ IPV4_DEVCONF_ARP_ANNOUNCE,
+ IPV4_DEVCONF_ARP_IGNORE,
+ IPV4_DEVCONF_PROMOTE_SECONDARIES,
+ IPV4_DEVCONF_ARP_ACCEPT,
+ IPV4_DEVCONF_ARP_NOTIFY,
+ IPV4_DEVCONF_ACCEPT_LOCAL,
+ IPV4_DEVCONF_SRC_VMARK,
+ IPV4_DEVCONF_PROXY_ARP_PVLAN,
+ IPV4_DEVCONF_ROUTE_LOCALNET,
+ IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL,
+ IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL,
+ IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN,
+ IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST,
+ IPV4_DEVCONF_DROP_GRATUITOUS_ARP,
+ IPV4_DEVCONF_BC_FORWARDING,
+ IPV4_DEVCONF_ARP_EVICT_NOCARRIER,
+ __IPV4_DEVCONF_MAX
+};
+
+#define IPV4_DEVCONF_MAX (__IPV4_DEVCONF_MAX - 1)
+
+#endif /* _LINUX_IP_H */
diff --git a/include/uapi/linux/ip6_tunnel.h b/include/uapi/linux/ip6_tunnel.h
new file mode 100644
index 0000000..0245269
--- /dev/null
+++ b/include/uapi/linux/ip6_tunnel.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _IP6_TUNNEL_H
+#define _IP6_TUNNEL_H
+
+#include <linux/types.h>
+#include <linux/if.h> /* For IFNAMSIZ. */
+#include <linux/in6.h> /* For struct in6_addr. */
+
+#define IPV6_TLV_TNL_ENCAP_LIMIT 4
+#define IPV6_DEFAULT_TNL_ENCAP_LIMIT 4
+
+/* don't add encapsulation limit if one isn't present in inner packet */
+#define IP6_TNL_F_IGN_ENCAP_LIMIT 0x1
+/* copy the traffic class field from the inner packet */
+#define IP6_TNL_F_USE_ORIG_TCLASS 0x2
+/* copy the flowlabel from the inner packet */
+#define IP6_TNL_F_USE_ORIG_FLOWLABEL 0x4
+/* being used for Mobile IPv6 */
+#define IP6_TNL_F_MIP6_DEV 0x8
+/* copy DSCP from the outer packet */
+#define IP6_TNL_F_RCV_DSCP_COPY 0x10
+/* copy fwmark from inner packet */
+#define IP6_TNL_F_USE_ORIG_FWMARK 0x20
+/* allow remote endpoint on the local node */
+#define IP6_TNL_F_ALLOW_LOCAL_REMOTE 0x40
+
+struct ip6_tnl_parm {
+ char name[IFNAMSIZ]; /* name of tunnel device */
+ int link; /* ifindex of underlying L2 interface */
+ __u8 proto; /* tunnel protocol */
+ __u8 encap_limit; /* encapsulation limit for tunnel */
+ __u8 hop_limit; /* hop limit for tunnel */
+ __be32 flowinfo; /* traffic class and flowlabel for tunnel */
+ __u32 flags; /* tunnel flags */
+ struct in6_addr laddr; /* local tunnel end-point address */
+ struct in6_addr raddr; /* remote tunnel end-point address */
+};
+
+struct ip6_tnl_parm2 {
+ char name[IFNAMSIZ]; /* name of tunnel device */
+ int link; /* ifindex of underlying L2 interface */
+ __u8 proto; /* tunnel protocol */
+ __u8 encap_limit; /* encapsulation limit for tunnel */
+ __u8 hop_limit; /* hop limit for tunnel */
+ __be32 flowinfo; /* traffic class and flowlabel for tunnel */
+ __u32 flags; /* tunnel flags */
+ struct in6_addr laddr; /* local tunnel end-point address */
+ struct in6_addr raddr; /* remote tunnel end-point address */
+
+ __be16 i_flags;
+ __be16 o_flags;
+ __be32 i_key;
+ __be32 o_key;
+};
+
+#endif
diff --git a/include/uapi/linux/ipsec.h b/include/uapi/linux/ipsec.h
new file mode 100644
index 0000000..50d8ee1
--- /dev/null
+++ b/include/uapi/linux/ipsec.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_IPSEC_H
+#define _LINUX_IPSEC_H
+
+/* The definitions, required to talk to KAME racoon IKE. */
+
+#include <linux/pfkeyv2.h>
+
+#define IPSEC_PORT_ANY 0
+#define IPSEC_ULPROTO_ANY 255
+#define IPSEC_PROTO_ANY 255
+
+enum {
+ IPSEC_MODE_ANY = 0, /* We do not support this for SA */
+ IPSEC_MODE_TRANSPORT = 1,
+ IPSEC_MODE_TUNNEL = 2,
+ IPSEC_MODE_BEET = 3
+};
+
+enum {
+ IPSEC_DIR_ANY = 0,
+ IPSEC_DIR_INBOUND = 1,
+ IPSEC_DIR_OUTBOUND = 2,
+ IPSEC_DIR_FWD = 3, /* It is our own */
+ IPSEC_DIR_MAX = 4,
+ IPSEC_DIR_INVALID = 5
+};
+
+enum {
+ IPSEC_POLICY_DISCARD = 0,
+ IPSEC_POLICY_NONE = 1,
+ IPSEC_POLICY_IPSEC = 2,
+ IPSEC_POLICY_ENTRUST = 3,
+ IPSEC_POLICY_BYPASS = 4
+};
+
+enum {
+ IPSEC_LEVEL_DEFAULT = 0,
+ IPSEC_LEVEL_USE = 1,
+ IPSEC_LEVEL_REQUIRE = 2,
+ IPSEC_LEVEL_UNIQUE = 3
+};
+
+#define IPSEC_MANUAL_REQID_MAX 0x3fff
+
+#define IPSEC_REPLAYWSIZE 32
+
+#endif /* _LINUX_IPSEC_H */
diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h
new file mode 100644
index 0000000..5413a8c
--- /dev/null
+++ b/include/uapi/linux/kernel.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_KERNEL_H
+#define _LINUX_KERNEL_H
+
+#include <linux/sysinfo.h>
+#include <linux/const.h>
+
+#endif /* _LINUX_KERNEL_H */
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
new file mode 100644
index 0000000..e7705e8
--- /dev/null
+++ b/include/uapi/linux/l2tp.h
@@ -0,0 +1,203 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * L2TP-over-IP socket for L2TPv3.
+ *
+ * Author: James Chapman <jchapman@katalix.com>
+ */
+
+#ifndef _LINUX_L2TP_H_
+#define _LINUX_L2TP_H_
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+
+/**
+ * struct sockaddr_l2tpip - the sockaddr structure for L2TP-over-IP sockets
+ * @l2tp_family: address family number AF_L2TPIP.
+ * @l2tp_addr: protocol specific address information
+ * @l2tp_conn_id: connection id of tunnel
+ */
+#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */
+struct sockaddr_l2tpip {
+ /* The first fields must match struct sockaddr_in */
+ __kernel_sa_family_t l2tp_family; /* AF_INET */
+ __be16 l2tp_unused; /* INET port number (unused) */
+ struct in_addr l2tp_addr; /* Internet address */
+
+ __u32 l2tp_conn_id; /* Connection ID of tunnel */
+
+ /* Pad to size of `struct sockaddr'. */
+ unsigned char __pad[__SOCK_SIZE__ -
+ sizeof(__kernel_sa_family_t) -
+ sizeof(__be16) - sizeof(struct in_addr) -
+ sizeof(__u32)];
+};
+
+/**
+ * struct sockaddr_l2tpip6 - the sockaddr structure for L2TP-over-IPv6 sockets
+ * @l2tp_family: address family number AF_L2TPIP.
+ * @l2tp_addr: protocol specific address information
+ * @l2tp_conn_id: connection id of tunnel
+ */
+struct sockaddr_l2tpip6 {
+ /* The first fields must match struct sockaddr_in6 */
+ __kernel_sa_family_t l2tp_family; /* AF_INET6 */
+ __be16 l2tp_unused; /* INET port number (unused) */
+ __be32 l2tp_flowinfo; /* IPv6 flow information */
+ struct in6_addr l2tp_addr; /* IPv6 address */
+ __u32 l2tp_scope_id; /* scope id (new in RFC2553) */
+ __u32 l2tp_conn_id; /* Connection ID of tunnel */
+};
+
+/*****************************************************************************
+ * NETLINK_GENERIC netlink family.
+ *****************************************************************************/
+
+/*
+ * Commands.
+ * Valid TLVs of each command are:-
+ * TUNNEL_CREATE - CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum
+ * TUNNEL_DELETE - CONN_ID
+ * TUNNEL_MODIFY - CONN_ID, udpcsum
+ * TUNNEL_GETSTATS - CONN_ID, (stats)
+ * TUNNEL_GET - CONN_ID, (...)
+ * SESSION_CREATE - SESSION_ID, PW_TYPE, cookie, peer_cookie, l2spec
+ * SESSION_DELETE - SESSION_ID
+ * SESSION_MODIFY - SESSION_ID
+ * SESSION_GET - SESSION_ID, (...)
+ * SESSION_GETSTATS - SESSION_ID, (stats)
+ *
+ */
+enum {
+ L2TP_CMD_NOOP,
+ L2TP_CMD_TUNNEL_CREATE,
+ L2TP_CMD_TUNNEL_DELETE,
+ L2TP_CMD_TUNNEL_MODIFY,
+ L2TP_CMD_TUNNEL_GET,
+ L2TP_CMD_SESSION_CREATE,
+ L2TP_CMD_SESSION_DELETE,
+ L2TP_CMD_SESSION_MODIFY,
+ L2TP_CMD_SESSION_GET,
+ __L2TP_CMD_MAX,
+};
+
+#define L2TP_CMD_MAX (__L2TP_CMD_MAX - 1)
+
+/*
+ * ATTR types defined for L2TP
+ */
+enum {
+ L2TP_ATTR_NONE, /* no data */
+ L2TP_ATTR_PW_TYPE, /* u16, enum l2tp_pwtype */
+ L2TP_ATTR_ENCAP_TYPE, /* u16, enum l2tp_encap_type */
+ L2TP_ATTR_OFFSET, /* u16 (not used) */
+ L2TP_ATTR_DATA_SEQ, /* u16 (not used) */
+ L2TP_ATTR_L2SPEC_TYPE, /* u8, enum l2tp_l2spec_type */
+ L2TP_ATTR_L2SPEC_LEN, /* u8 (not used) */
+ L2TP_ATTR_PROTO_VERSION, /* u8 */
+ L2TP_ATTR_IFNAME, /* string */
+ L2TP_ATTR_CONN_ID, /* u32 */
+ L2TP_ATTR_PEER_CONN_ID, /* u32 */
+ L2TP_ATTR_SESSION_ID, /* u32 */
+ L2TP_ATTR_PEER_SESSION_ID, /* u32 */
+ L2TP_ATTR_UDP_CSUM, /* u8 */
+ L2TP_ATTR_VLAN_ID, /* u16 (not used) */
+ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */
+ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */
+ L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags (not used) */
+ L2TP_ATTR_RECV_SEQ, /* u8 */
+ L2TP_ATTR_SEND_SEQ, /* u8 */
+ L2TP_ATTR_LNS_MODE, /* u8 */
+ L2TP_ATTR_USING_IPSEC, /* u8 */
+ L2TP_ATTR_RECV_TIMEOUT, /* msec */
+ L2TP_ATTR_FD, /* int */
+ L2TP_ATTR_IP_SADDR, /* u32 */
+ L2TP_ATTR_IP_DADDR, /* u32 */
+ L2TP_ATTR_UDP_SPORT, /* u16 */
+ L2TP_ATTR_UDP_DPORT, /* u16 */
+ L2TP_ATTR_MTU, /* u16 (not used) */
+ L2TP_ATTR_MRU, /* u16 (not used) */
+ L2TP_ATTR_STATS, /* nested */
+ L2TP_ATTR_IP6_SADDR, /* struct in6_addr */
+ L2TP_ATTR_IP6_DADDR, /* struct in6_addr */
+ L2TP_ATTR_UDP_ZERO_CSUM6_TX, /* flag */
+ L2TP_ATTR_UDP_ZERO_CSUM6_RX, /* flag */
+ L2TP_ATTR_PAD,
+ __L2TP_ATTR_MAX,
+};
+
+#define L2TP_ATTR_MAX (__L2TP_ATTR_MAX - 1)
+
+/* Nested in L2TP_ATTR_STATS */
+enum {
+ L2TP_ATTR_STATS_NONE, /* no data */
+ L2TP_ATTR_TX_PACKETS, /* u64 */
+ L2TP_ATTR_TX_BYTES, /* u64 */
+ L2TP_ATTR_TX_ERRORS, /* u64 */
+ L2TP_ATTR_RX_PACKETS, /* u64 */
+ L2TP_ATTR_RX_BYTES, /* u64 */
+ L2TP_ATTR_RX_SEQ_DISCARDS, /* u64 */
+ L2TP_ATTR_RX_OOS_PACKETS, /* u64 */
+ L2TP_ATTR_RX_ERRORS, /* u64 */
+ L2TP_ATTR_STATS_PAD,
+ L2TP_ATTR_RX_COOKIE_DISCARDS, /* u64 */
+ L2TP_ATTR_RX_INVALID, /* u64 */
+ __L2TP_ATTR_STATS_MAX,
+};
+
+#define L2TP_ATTR_STATS_MAX (__L2TP_ATTR_STATS_MAX - 1)
+
+enum l2tp_pwtype {
+ L2TP_PWTYPE_NONE = 0x0000,
+ L2TP_PWTYPE_ETH_VLAN = 0x0004,
+ L2TP_PWTYPE_ETH = 0x0005,
+ L2TP_PWTYPE_PPP = 0x0007,
+ L2TP_PWTYPE_PPP_AC = 0x0008,
+ L2TP_PWTYPE_IP = 0x000b,
+ __L2TP_PWTYPE_MAX
+};
+
+enum l2tp_l2spec_type {
+ L2TP_L2SPECTYPE_NONE,
+ L2TP_L2SPECTYPE_DEFAULT,
+};
+
+enum l2tp_encap_type {
+ L2TP_ENCAPTYPE_UDP,
+ L2TP_ENCAPTYPE_IP,
+};
+
+/* For L2TP_ATTR_DATA_SEQ. Unused. */
+enum l2tp_seqmode {
+ L2TP_SEQ_NONE = 0,
+ L2TP_SEQ_IP = 1,
+ L2TP_SEQ_ALL = 2,
+};
+
+/**
+ * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions.
+ *
+ * Unused.
+ *
+ * @L2TP_MSG_DEBUG: verbose debug (if compiled in)
+ * @L2TP_MSG_CONTROL: userspace - kernel interface
+ * @L2TP_MSG_SEQ: sequence numbers
+ * @L2TP_MSG_DATA: data packets
+ */
+enum l2tp_debug_flags {
+ L2TP_MSG_DEBUG = (1 << 0),
+ L2TP_MSG_CONTROL = (1 << 1),
+ L2TP_MSG_SEQ = (1 << 2),
+ L2TP_MSG_DATA = (1 << 3),
+};
+
+/*
+ * NETLINK_GENERIC related info
+ */
+#define L2TP_GENL_NAME "l2tp"
+#define L2TP_GENL_VERSION 0x1
+#define L2TP_GENL_MCGROUP "l2tp"
+
+#endif /* _LINUX_L2TP_H_ */
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
new file mode 100644
index 0000000..a159991
--- /dev/null
+++ b/include/uapi/linux/libc-compat.h
@@ -0,0 +1,267 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Compatibility interface for userspace libc header coordination:
+ *
+ * Define compatibility macros that are used to control the inclusion or
+ * exclusion of UAPI structures and definitions in coordination with another
+ * userspace C library.
+ *
+ * This header is intended to solve the problem of UAPI definitions that
+ * conflict with userspace definitions. If a UAPI header has such conflicting
+ * definitions then the solution is as follows:
+ *
+ * * Synchronize the UAPI header and the libc headers so either one can be
+ * used and such that the ABI is preserved. If this is not possible then
+ * no simple compatibility interface exists (you need to write translating
+ * wrappers and rename things) and you can't use this interface.
+ *
+ * Then follow this process:
+ *
+ * (a) Include libc-compat.h in the UAPI header.
+ * e.g. #include <linux/libc-compat.h>
+ * This include must be as early as possible.
+ *
+ * (b) In libc-compat.h add enough code to detect that the comflicting
+ * userspace libc header has been included first.
+ *
+ * (c) If the userspace libc header has been included first define a set of
+ * guard macros of the form __UAPI_DEF_FOO and set their values to 1, else
+ * set their values to 0.
+ *
+ * (d) Back in the UAPI header with the conflicting definitions, guard the
+ * definitions with:
+ * #if __UAPI_DEF_FOO
+ * ...
+ * #endif
+ *
+ * This fixes the situation where the linux headers are included *after* the
+ * libc headers. To fix the problem with the inclusion in the other order the
+ * userspace libc headers must be fixed like this:
+ *
+ * * For all definitions that conflict with kernel definitions wrap those
+ * defines in the following:
+ * #if !__UAPI_DEF_FOO
+ * ...
+ * #endif
+ *
+ * This prevents the redefinition of a construct already defined by the kernel.
+ */
+#ifndef _LIBC_COMPAT_H
+#define _LIBC_COMPAT_H
+
+/* We have included glibc headers... */
+#if defined(__GLIBC__)
+
+/* Coordinate with glibc net/if.h header. */
+#if defined(_NET_IF_H) && defined(__USE_MISC)
+
+/* GLIBC headers included first so don't define anything
+ * that would already be defined. */
+
+#define __UAPI_DEF_IF_IFCONF 0
+#define __UAPI_DEF_IF_IFMAP 0
+#define __UAPI_DEF_IF_IFNAMSIZ 0
+#define __UAPI_DEF_IF_IFREQ 0
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 0
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
+
+#else /* _NET_IF_H */
+
+/* Linux headers included first, and we must define everything
+ * we need. The expectation is that glibc will check the
+ * __UAPI_DEF_* defines and adjust appropriately. */
+
+#define __UAPI_DEF_IF_IFCONF 1
+#define __UAPI_DEF_IF_IFMAP 1
+#define __UAPI_DEF_IF_IFNAMSIZ 1
+#define __UAPI_DEF_IF_IFREQ 1
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+
+#endif /* _NET_IF_H */
+
+/* Coordinate with glibc netinet/in.h header. */
+#if defined(_NETINET_IN_H)
+
+/* GLIBC headers included first so don't define anything
+ * that would already be defined. */
+#define __UAPI_DEF_IN_ADDR 0
+#define __UAPI_DEF_IN_IPPROTO 0
+#define __UAPI_DEF_IN_PKTINFO 0
+#define __UAPI_DEF_IP_MREQ 0
+#define __UAPI_DEF_SOCKADDR_IN 0
+#define __UAPI_DEF_IN_CLASS 0
+
+#define __UAPI_DEF_IN6_ADDR 0
+/* The exception is the in6_addr macros which must be defined
+ * if the glibc code didn't define them. This guard matches
+ * the guard in glibc/inet/netinet/in.h which defines the
+ * additional in6_addr macros e.g. s6_addr16, and s6_addr32. */
+#if defined(__USE_MISC) || defined (__USE_GNU)
+#define __UAPI_DEF_IN6_ADDR_ALT 0
+#else
+#define __UAPI_DEF_IN6_ADDR_ALT 1
+#endif
+#define __UAPI_DEF_SOCKADDR_IN6 0
+#define __UAPI_DEF_IPV6_MREQ 0
+#define __UAPI_DEF_IPPROTO_V6 0
+#define __UAPI_DEF_IPV6_OPTIONS 0
+#define __UAPI_DEF_IN6_PKTINFO 0
+#define __UAPI_DEF_IP6_MTUINFO 0
+
+#else
+
+/* Linux headers included first, and we must define everything
+ * we need. The expectation is that glibc will check the
+ * __UAPI_DEF_* defines and adjust appropriately. */
+#define __UAPI_DEF_IN_ADDR 1
+#define __UAPI_DEF_IN_IPPROTO 1
+#define __UAPI_DEF_IN_PKTINFO 1
+#define __UAPI_DEF_IP_MREQ 1
+#define __UAPI_DEF_SOCKADDR_IN 1
+#define __UAPI_DEF_IN_CLASS 1
+
+#define __UAPI_DEF_IN6_ADDR 1
+/* We unconditionally define the in6_addr macros and glibc must
+ * coordinate. */
+#define __UAPI_DEF_IN6_ADDR_ALT 1
+#define __UAPI_DEF_SOCKADDR_IN6 1
+#define __UAPI_DEF_IPV6_MREQ 1
+#define __UAPI_DEF_IPPROTO_V6 1
+#define __UAPI_DEF_IPV6_OPTIONS 1
+#define __UAPI_DEF_IN6_PKTINFO 1
+#define __UAPI_DEF_IP6_MTUINFO 1
+
+#endif /* _NETINET_IN_H */
+
+/* Coordinate with glibc netipx/ipx.h header. */
+#if defined(__NETIPX_IPX_H)
+
+#define __UAPI_DEF_SOCKADDR_IPX 0
+#define __UAPI_DEF_IPX_ROUTE_DEFINITION 0
+#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 0
+#define __UAPI_DEF_IPX_CONFIG_DATA 0
+#define __UAPI_DEF_IPX_ROUTE_DEF 0
+
+#else /* defined(__NETIPX_IPX_H) */
+
+#define __UAPI_DEF_SOCKADDR_IPX 1
+#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1
+#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1
+#define __UAPI_DEF_IPX_CONFIG_DATA 1
+#define __UAPI_DEF_IPX_ROUTE_DEF 1
+
+#endif /* defined(__NETIPX_IPX_H) */
+
+/* Definitions for xattr.h */
+#if defined(_SYS_XATTR_H)
+#define __UAPI_DEF_XATTR 0
+#else
+#define __UAPI_DEF_XATTR 1
+#endif
+
+/* If we did not see any headers from any supported C libraries,
+ * or we are being included in the kernel, then define everything
+ * that we need. Check for previous __UAPI_* definitions to give
+ * unsupported C libraries a way to opt out of any kernel definition. */
+#else /* !defined(__GLIBC__) */
+
+/* Definitions for if.h */
+#ifndef __UAPI_DEF_IF_IFCONF
+#define __UAPI_DEF_IF_IFCONF 1
+#endif
+#ifndef __UAPI_DEF_IF_IFMAP
+#define __UAPI_DEF_IF_IFMAP 1
+#endif
+#ifndef __UAPI_DEF_IF_IFNAMSIZ
+#define __UAPI_DEF_IF_IFNAMSIZ 1
+#endif
+#ifndef __UAPI_DEF_IF_IFREQ
+#define __UAPI_DEF_IF_IFREQ 1
+#endif
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1
+#endif
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+#endif
+
+/* Definitions for in.h */
+#ifndef __UAPI_DEF_IN_ADDR
+#define __UAPI_DEF_IN_ADDR 1
+#endif
+#ifndef __UAPI_DEF_IN_IPPROTO
+#define __UAPI_DEF_IN_IPPROTO 1
+#endif
+#ifndef __UAPI_DEF_IN_PKTINFO
+#define __UAPI_DEF_IN_PKTINFO 1
+#endif
+#ifndef __UAPI_DEF_IP_MREQ
+#define __UAPI_DEF_IP_MREQ 1
+#endif
+#ifndef __UAPI_DEF_SOCKADDR_IN
+#define __UAPI_DEF_SOCKADDR_IN 1
+#endif
+#ifndef __UAPI_DEF_IN_CLASS
+#define __UAPI_DEF_IN_CLASS 1
+#endif
+
+/* Definitions for in6.h */
+#ifndef __UAPI_DEF_IN6_ADDR
+#define __UAPI_DEF_IN6_ADDR 1
+#endif
+#ifndef __UAPI_DEF_IN6_ADDR_ALT
+#define __UAPI_DEF_IN6_ADDR_ALT 1
+#endif
+#ifndef __UAPI_DEF_SOCKADDR_IN6
+#define __UAPI_DEF_SOCKADDR_IN6 1
+#endif
+#ifndef __UAPI_DEF_IPV6_MREQ
+#define __UAPI_DEF_IPV6_MREQ 1
+#endif
+#ifndef __UAPI_DEF_IPPROTO_V6
+#define __UAPI_DEF_IPPROTO_V6 1
+#endif
+#ifndef __UAPI_DEF_IPV6_OPTIONS
+#define __UAPI_DEF_IPV6_OPTIONS 1
+#endif
+#ifndef __UAPI_DEF_IN6_PKTINFO
+#define __UAPI_DEF_IN6_PKTINFO 1
+#endif
+#ifndef __UAPI_DEF_IP6_MTUINFO
+#define __UAPI_DEF_IP6_MTUINFO 1
+#endif
+
+/* Definitions for ipx.h */
+#ifndef __UAPI_DEF_SOCKADDR_IPX
+#define __UAPI_DEF_SOCKADDR_IPX 1
+#endif
+#ifndef __UAPI_DEF_IPX_ROUTE_DEFINITION
+#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1
+#endif
+#ifndef __UAPI_DEF_IPX_INTERFACE_DEFINITION
+#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1
+#endif
+#ifndef __UAPI_DEF_IPX_CONFIG_DATA
+#define __UAPI_DEF_IPX_CONFIG_DATA 1
+#endif
+#ifndef __UAPI_DEF_IPX_ROUTE_DEF
+#define __UAPI_DEF_IPX_ROUTE_DEF 1
+#endif
+
+/* Definitions for xattr.h */
+#ifndef __UAPI_DEF_XATTR
+#define __UAPI_DEF_XATTR 1
+#endif
+
+#endif /* __GLIBC__ */
+
+#endif /* _LIBC_COMPAT_H */
diff --git a/include/uapi/linux/limits.h b/include/uapi/linux/limits.h
new file mode 100644
index 0000000..c3547f0
--- /dev/null
+++ b/include/uapi/linux/limits.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_LIMITS_H
+#define _LINUX_LIMITS_H
+
+#define NR_OPEN 1024
+
+#define NGROUPS_MAX 65536 /* supplemental group IDs are available */
+#define ARG_MAX 131072 /* # bytes of args + environ for exec() */
+#define LINK_MAX 127 /* # links a file may have */
+#define MAX_CANON 255 /* size of the canonical input queue */
+#define MAX_INPUT 255 /* size of the type-ahead buffer */
+#define NAME_MAX 255 /* # chars in a file name */
+#define PATH_MAX 4096 /* # chars in a path name including nul */
+#define PIPE_BUF 4096 /* # bytes in atomic write to a pipe */
+#define XATTR_NAME_MAX 255 /* # chars in an extended attribute name */
+#define XATTR_SIZE_MAX 65536 /* size of an extended attribute value (64k) */
+#define XATTR_LIST_MAX 65536 /* size of extended attribute namelist (64k) */
+
+#define RTSIG_MAX 32
+
+#endif
diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h
new file mode 100644
index 0000000..9d22961
--- /dev/null
+++ b/include/uapi/linux/lwtunnel.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LWTUNNEL_H_
+#define _LWTUNNEL_H_
+
+#include <linux/types.h>
+
+enum lwtunnel_encap_types {
+ LWTUNNEL_ENCAP_NONE,
+ LWTUNNEL_ENCAP_MPLS,
+ LWTUNNEL_ENCAP_IP,
+ LWTUNNEL_ENCAP_ILA,
+ LWTUNNEL_ENCAP_IP6,
+ LWTUNNEL_ENCAP_SEG6,
+ LWTUNNEL_ENCAP_BPF,
+ LWTUNNEL_ENCAP_SEG6_LOCAL,
+ LWTUNNEL_ENCAP_RPL,
+ LWTUNNEL_ENCAP_IOAM6,
+ LWTUNNEL_ENCAP_XFRM,
+ __LWTUNNEL_ENCAP_MAX,
+};
+
+#define LWTUNNEL_ENCAP_MAX (__LWTUNNEL_ENCAP_MAX - 1)
+
+enum lwtunnel_ip_t {
+ LWTUNNEL_IP_UNSPEC,
+ LWTUNNEL_IP_ID,
+ LWTUNNEL_IP_DST,
+ LWTUNNEL_IP_SRC,
+ LWTUNNEL_IP_TTL,
+ LWTUNNEL_IP_TOS,
+ LWTUNNEL_IP_FLAGS,
+ LWTUNNEL_IP_PAD,
+ LWTUNNEL_IP_OPTS,
+ __LWTUNNEL_IP_MAX,
+};
+
+#define LWTUNNEL_IP_MAX (__LWTUNNEL_IP_MAX - 1)
+
+enum lwtunnel_ip6_t {
+ LWTUNNEL_IP6_UNSPEC,
+ LWTUNNEL_IP6_ID,
+ LWTUNNEL_IP6_DST,
+ LWTUNNEL_IP6_SRC,
+ LWTUNNEL_IP6_HOPLIMIT,
+ LWTUNNEL_IP6_TC,
+ LWTUNNEL_IP6_FLAGS,
+ LWTUNNEL_IP6_PAD,
+ LWTUNNEL_IP6_OPTS,
+ __LWTUNNEL_IP6_MAX,
+};
+
+#define LWTUNNEL_IP6_MAX (__LWTUNNEL_IP6_MAX - 1)
+
+enum {
+ LWTUNNEL_IP_OPTS_UNSPEC,
+ LWTUNNEL_IP_OPTS_GENEVE,
+ LWTUNNEL_IP_OPTS_VXLAN,
+ LWTUNNEL_IP_OPTS_ERSPAN,
+ __LWTUNNEL_IP_OPTS_MAX,
+};
+
+#define LWTUNNEL_IP_OPTS_MAX (__LWTUNNEL_IP_OPTS_MAX - 1)
+
+enum {
+ LWTUNNEL_IP_OPT_GENEVE_UNSPEC,
+ LWTUNNEL_IP_OPT_GENEVE_CLASS,
+ LWTUNNEL_IP_OPT_GENEVE_TYPE,
+ LWTUNNEL_IP_OPT_GENEVE_DATA,
+ __LWTUNNEL_IP_OPT_GENEVE_MAX,
+};
+
+#define LWTUNNEL_IP_OPT_GENEVE_MAX (__LWTUNNEL_IP_OPT_GENEVE_MAX - 1)
+
+enum {
+ LWTUNNEL_IP_OPT_VXLAN_UNSPEC,
+ LWTUNNEL_IP_OPT_VXLAN_GBP,
+ __LWTUNNEL_IP_OPT_VXLAN_MAX,
+};
+
+#define LWTUNNEL_IP_OPT_VXLAN_MAX (__LWTUNNEL_IP_OPT_VXLAN_MAX - 1)
+
+enum {
+ LWTUNNEL_IP_OPT_ERSPAN_UNSPEC,
+ LWTUNNEL_IP_OPT_ERSPAN_VER,
+ LWTUNNEL_IP_OPT_ERSPAN_INDEX,
+ LWTUNNEL_IP_OPT_ERSPAN_DIR,
+ LWTUNNEL_IP_OPT_ERSPAN_HWID,
+ __LWTUNNEL_IP_OPT_ERSPAN_MAX,
+};
+
+#define LWTUNNEL_IP_OPT_ERSPAN_MAX (__LWTUNNEL_IP_OPT_ERSPAN_MAX - 1)
+
+enum {
+ LWT_BPF_PROG_UNSPEC,
+ LWT_BPF_PROG_FD,
+ LWT_BPF_PROG_NAME,
+ __LWT_BPF_PROG_MAX,
+};
+
+#define LWT_BPF_PROG_MAX (__LWT_BPF_PROG_MAX - 1)
+
+enum {
+ LWT_BPF_UNSPEC,
+ LWT_BPF_IN,
+ LWT_BPF_OUT,
+ LWT_BPF_XMIT,
+ LWT_BPF_XMIT_HEADROOM,
+ __LWT_BPF_MAX,
+};
+
+#define LWT_BPF_MAX (__LWT_BPF_MAX - 1)
+
+#define LWT_BPF_MAX_HEADROOM 256
+
+enum {
+ LWT_XFRM_UNSPEC,
+ LWT_XFRM_IF_ID,
+ LWT_XFRM_LINK,
+ __LWT_XFRM_MAX,
+};
+
+#define LWT_XFRM_MAX (__LWT_XFRM_MAX - 1)
+
+#endif /* _LWTUNNEL_H_ */
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
new file mode 100644
index 0000000..6325d1d
--- /dev/null
+++ b/include/uapi/linux/magic.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_MAGIC_H__
+#define __LINUX_MAGIC_H__
+
+#define ADFS_SUPER_MAGIC 0xadf5
+#define AFFS_SUPER_MAGIC 0xadff
+#define AFS_SUPER_MAGIC 0x5346414F
+#define AUTOFS_SUPER_MAGIC 0x0187
+#define CEPH_SUPER_MAGIC 0x00c36400
+#define CODA_SUPER_MAGIC 0x73757245
+#define CRAMFS_MAGIC 0x28cd3d45 /* some random number */
+#define CRAMFS_MAGIC_WEND 0x453dcd28 /* magic number with the wrong endianess */
+#define DEBUGFS_MAGIC 0x64626720
+#define SECURITYFS_MAGIC 0x73636673
+#define SELINUX_MAGIC 0xf97cff8c
+#define SMACK_MAGIC 0x43415d53 /* "SMAC" */
+#define RAMFS_MAGIC 0x858458f6 /* some random number */
+#define TMPFS_MAGIC 0x01021994
+#define HUGETLBFS_MAGIC 0x958458f6 /* some random number */
+#define SQUASHFS_MAGIC 0x73717368
+#define ECRYPTFS_SUPER_MAGIC 0xf15f
+#define EFS_SUPER_MAGIC 0x414A53
+#define EROFS_SUPER_MAGIC_V1 0xE0F5E1E2
+#define EXT2_SUPER_MAGIC 0xEF53
+#define EXT3_SUPER_MAGIC 0xEF53
+#define XENFS_SUPER_MAGIC 0xabba1974
+#define EXT4_SUPER_MAGIC 0xEF53
+#define BTRFS_SUPER_MAGIC 0x9123683E
+#define NILFS_SUPER_MAGIC 0x3434
+#define F2FS_SUPER_MAGIC 0xF2F52010
+#define HPFS_SUPER_MAGIC 0xf995e849
+#define ISOFS_SUPER_MAGIC 0x9660
+#define JFFS2_SUPER_MAGIC 0x72b6
+#define XFS_SUPER_MAGIC 0x58465342 /* "XFSB" */
+#define PSTOREFS_MAGIC 0x6165676C
+#define EFIVARFS_MAGIC 0xde5e81e4
+#define HOSTFS_SUPER_MAGIC 0x00c0ffee
+#define OVERLAYFS_SUPER_MAGIC 0x794c7630
+#define FUSE_SUPER_MAGIC 0x65735546
+
+#define MINIX_SUPER_MAGIC 0x137F /* minix v1 fs, 14 char names */
+#define MINIX_SUPER_MAGIC2 0x138F /* minix v1 fs, 30 char names */
+#define MINIX2_SUPER_MAGIC 0x2468 /* minix v2 fs, 14 char names */
+#define MINIX2_SUPER_MAGIC2 0x2478 /* minix v2 fs, 30 char names */
+#define MINIX3_SUPER_MAGIC 0x4d5a /* minix v3 fs, 60 char names */
+
+#define MSDOS_SUPER_MAGIC 0x4d44 /* MD */
+#define EXFAT_SUPER_MAGIC 0x2011BAB0
+#define NCP_SUPER_MAGIC 0x564c /* Guess, what 0x564c is :-) */
+#define NFS_SUPER_MAGIC 0x6969
+#define OCFS2_SUPER_MAGIC 0x7461636f
+#define OPENPROM_SUPER_MAGIC 0x9fa1
+#define QNX4_SUPER_MAGIC 0x002f /* qnx4 fs detection */
+#define QNX6_SUPER_MAGIC 0x68191122 /* qnx6 fs detection */
+#define AFS_FS_MAGIC 0x6B414653
+
+
+#define REISERFS_SUPER_MAGIC 0x52654973 /* used by gcc */
+ /* used by file system utilities that
+ look at the superblock, etc. */
+#define REISERFS_SUPER_MAGIC_STRING "ReIsErFs"
+#define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs"
+#define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs"
+
+#define SMB_SUPER_MAGIC 0x517B
+#define CIFS_SUPER_MAGIC 0xFF534D42 /* the first four bytes of SMB PDUs */
+#define SMB2_SUPER_MAGIC 0xFE534D42
+
+#define CGROUP_SUPER_MAGIC 0x27e0eb
+#define CGROUP2_SUPER_MAGIC 0x63677270
+
+#define RDTGROUP_SUPER_MAGIC 0x7655821
+
+#define STACK_END_MAGIC 0x57AC6E9D
+
+#define TRACEFS_MAGIC 0x74726163
+
+#define V9FS_MAGIC 0x01021997
+
+#define BDEVFS_MAGIC 0x62646576
+#define DAXFS_MAGIC 0x64646178
+#define BINFMTFS_MAGIC 0x42494e4d
+#define DEVPTS_SUPER_MAGIC 0x1cd1
+#define BINDERFS_SUPER_MAGIC 0x6c6f6f70
+#define FUTEXFS_SUPER_MAGIC 0xBAD1DEA
+#define PIPEFS_MAGIC 0x50495045
+#define PROC_SUPER_MAGIC 0x9fa0
+#define SOCKFS_MAGIC 0x534F434B
+#define SYSFS_MAGIC 0x62656572
+#define USBDEVICE_SUPER_MAGIC 0x9fa2
+#define MTD_INODE_FS_MAGIC 0x11307854
+#define ANON_INODE_FS_MAGIC 0x09041934
+#define BTRFS_TEST_MAGIC 0x73727279
+#define NSFS_MAGIC 0x6e736673
+#define BPF_FS_MAGIC 0xcafe4a11
+#define AAFS_MAGIC 0x5a3c69f0
+#define ZONEFS_MAGIC 0x5a4f4653
+
+/* Since UDF 2.01 is ISO 13346 based... */
+#define UDF_SUPER_MAGIC 0x15013346
+#define DMA_BUF_MAGIC 0x444d4142 /* "DMAB" */
+#define DEVMEM_MAGIC 0x454d444d /* "DMEM" */
+#define SECRETMEM_MAGIC 0x5345434d /* "SECM" */
+
+#endif /* __LINUX_MAGIC_H__ */
diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h
new file mode 100644
index 0000000..9effbf9
--- /dev/null
+++ b/include/uapi/linux/mpls.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _MPLS_H
+#define _MPLS_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/* Reference: RFC 5462, RFC 3032
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Label | TC |S| TTL |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * Label: Label Value, 20 bits
+ * TC: Traffic Class field, 3 bits
+ * S: Bottom of Stack, 1 bit
+ * TTL: Time to Live, 8 bits
+ */
+
+struct mpls_label {
+ __be32 entry;
+};
+
+#define MPLS_LS_LABEL_MASK 0xFFFFF000
+#define MPLS_LS_LABEL_SHIFT 12
+#define MPLS_LS_TC_MASK 0x00000E00
+#define MPLS_LS_TC_SHIFT 9
+#define MPLS_LS_S_MASK 0x00000100
+#define MPLS_LS_S_SHIFT 8
+#define MPLS_LS_TTL_MASK 0x000000FF
+#define MPLS_LS_TTL_SHIFT 0
+
+/* Reserved labels */
+#define MPLS_LABEL_IPV4NULL 0 /* RFC3032 */
+#define MPLS_LABEL_RTALERT 1 /* RFC3032 */
+#define MPLS_LABEL_IPV6NULL 2 /* RFC3032 */
+#define MPLS_LABEL_IMPLNULL 3 /* RFC3032 */
+#define MPLS_LABEL_ENTROPY 7 /* RFC6790 */
+#define MPLS_LABEL_GAL 13 /* RFC5586 */
+#define MPLS_LABEL_OAMALERT 14 /* RFC3429 */
+#define MPLS_LABEL_EXTENSION 15 /* RFC7274 */
+
+#define MPLS_LABEL_FIRST_UNRESERVED 16 /* RFC3032 */
+
+/* These are embedded into IFLA_STATS_AF_SPEC:
+ * [IFLA_STATS_AF_SPEC]
+ * -> [AF_MPLS]
+ * -> [MPLS_STATS_xxx]
+ *
+ * Attributes:
+ * [MPLS_STATS_LINK] = {
+ * struct mpls_link_stats
+ * }
+ */
+enum {
+ MPLS_STATS_UNSPEC, /* also used as 64bit pad attribute */
+ MPLS_STATS_LINK,
+ __MPLS_STATS_MAX,
+};
+
+#define MPLS_STATS_MAX (__MPLS_STATS_MAX - 1)
+
+struct mpls_link_stats {
+ __u64 rx_packets; /* total packets received */
+ __u64 tx_packets; /* total packets transmitted */
+ __u64 rx_bytes; /* total bytes received */
+ __u64 tx_bytes; /* total bytes transmitted */
+ __u64 rx_errors; /* bad packets received */
+ __u64 tx_errors; /* packet transmit problems */
+ __u64 rx_dropped; /* packet dropped on receive */
+ __u64 tx_dropped; /* packet dropped on transmit */
+ __u64 rx_noroute; /* no route for packet dest */
+};
+
+#endif /* _MPLS_H */
diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h
new file mode 100644
index 0000000..2c69b7d
--- /dev/null
+++ b/include/uapi/linux/mpls_iptunnel.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * mpls tunnel api
+ *
+ * Authors:
+ * Roopa Prabhu <roopa@cumulusnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_MPLS_IPTUNNEL_H
+#define _LINUX_MPLS_IPTUNNEL_H
+
+/* MPLS tunnel attributes
+ * [RTA_ENCAP] = {
+ * [MPLS_IPTUNNEL_DST]
+ * [MPLS_IPTUNNEL_TTL]
+ * }
+ */
+enum {
+ MPLS_IPTUNNEL_UNSPEC,
+ MPLS_IPTUNNEL_DST,
+ MPLS_IPTUNNEL_TTL,
+ __MPLS_IPTUNNEL_MAX,
+};
+#define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1)
+
+#endif /* _LINUX_MPLS_IPTUNNEL_H */
diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h
new file mode 100644
index 0000000..c2e6f3b
--- /dev/null
+++ b/include/uapi/linux/mptcp.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _MPTCP_H
+#define _MPTCP_H
+
+#include <netinet/in.h> /* for sockaddr_in and sockaddr_in6 */
+#include <sys/socket.h> /* for struct sockaddr */
+
+#include <linux/const.h>
+#include <linux/types.h>
+#include <linux/in.h> /* for sockaddr_in */
+#include <linux/in6.h> /* for sockaddr_in6 */
+#include <linux/socket.h> /* for sockaddr_storage and sa_family */
+
+#define MPTCP_SUBFLOW_FLAG_MCAP_REM _BITUL(0)
+#define MPTCP_SUBFLOW_FLAG_MCAP_LOC _BITUL(1)
+#define MPTCP_SUBFLOW_FLAG_JOIN_REM _BITUL(2)
+#define MPTCP_SUBFLOW_FLAG_JOIN_LOC _BITUL(3)
+#define MPTCP_SUBFLOW_FLAG_BKUP_REM _BITUL(4)
+#define MPTCP_SUBFLOW_FLAG_BKUP_LOC _BITUL(5)
+#define MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED _BITUL(6)
+#define MPTCP_SUBFLOW_FLAG_CONNECTED _BITUL(7)
+#define MPTCP_SUBFLOW_FLAG_MAPVALID _BITUL(8)
+
+#define MPTCP_PM_CMD_GRP_NAME "mptcp_pm_cmds"
+#define MPTCP_PM_EV_GRP_NAME "mptcp_pm_events"
+
+#include <linux/mptcp_pm.h>
+
+#define MPTCP_INFO_FLAG_FALLBACK _BITUL(0)
+#define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1)
+
+#define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0)
+#define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1)
+#define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2)
+#define MPTCP_PM_ADDR_FLAG_FULLMESH (1 << 3)
+#define MPTCP_PM_ADDR_FLAG_IMPLICIT (1 << 4)
+
+struct mptcp_info {
+ __u8 mptcpi_subflows;
+ __u8 mptcpi_add_addr_signal;
+ __u8 mptcpi_add_addr_accepted;
+ __u8 mptcpi_subflows_max;
+ __u8 mptcpi_add_addr_signal_max;
+ __u8 mptcpi_add_addr_accepted_max;
+ __u32 mptcpi_flags;
+ __u32 mptcpi_token;
+ __u64 mptcpi_write_seq;
+ __u64 mptcpi_snd_una;
+ __u64 mptcpi_rcv_nxt;
+ __u8 mptcpi_local_addr_used;
+ __u8 mptcpi_local_addr_max;
+ __u8 mptcpi_csum_enabled;
+ __u32 mptcpi_retransmits;
+ __u64 mptcpi_bytes_retrans;
+ __u64 mptcpi_bytes_sent;
+ __u64 mptcpi_bytes_received;
+ __u64 mptcpi_bytes_acked;
+ __u8 mptcpi_subflows_total;
+};
+
+/* MPTCP Reset reason codes, rfc8684 */
+#define MPTCP_RST_EUNSPEC 0
+#define MPTCP_RST_EMPTCP 1
+#define MPTCP_RST_ERESOURCE 2
+#define MPTCP_RST_EPROHIBIT 3
+#define MPTCP_RST_EWQ2BIG 4
+#define MPTCP_RST_EBADPERF 5
+#define MPTCP_RST_EMIDDLEBOX 6
+
+struct mptcp_subflow_data {
+ __u32 size_subflow_data; /* size of this structure in userspace */
+ __u32 num_subflows; /* must be 0, set by kernel */
+ __u32 size_kernel; /* must be 0, set by kernel */
+ __u32 size_user; /* size of one element in data[] */
+} __attribute__((aligned(8)));
+
+struct mptcp_subflow_addrs {
+ union {
+ __kernel_sa_family_t sa_family;
+ struct sockaddr sa_local;
+ struct sockaddr_in sin_local;
+ struct sockaddr_in6 sin6_local;
+ struct __kernel_sockaddr_storage ss_local;
+ };
+ union {
+ struct sockaddr sa_remote;
+ struct sockaddr_in sin_remote;
+ struct sockaddr_in6 sin6_remote;
+ struct __kernel_sockaddr_storage ss_remote;
+ };
+};
+
+struct mptcp_subflow_info {
+ __u32 id;
+ struct mptcp_subflow_addrs addrs;
+};
+
+struct mptcp_full_info {
+ __u32 size_tcpinfo_kernel; /* must be 0, set by kernel */
+ __u32 size_tcpinfo_user;
+ __u32 size_sfinfo_kernel; /* must be 0, set by kernel */
+ __u32 size_sfinfo_user;
+ __u32 num_subflows; /* must be 0, set by kernel (real subflow count) */
+ __u32 size_arrays_user; /* max subflows that userspace is interested in;
+ * the buffers at subflow_info/tcp_info
+ * are respectively at least:
+ * size_arrays * size_sfinfo_user
+ * size_arrays * size_tcpinfo_user
+ * bytes wide
+ */
+ __aligned_u64 subflow_info;
+ __aligned_u64 tcp_info;
+ struct mptcp_info mptcp_info;
+};
+
+/* MPTCP socket options */
+#define MPTCP_INFO 1
+#define MPTCP_TCPINFO 2
+#define MPTCP_SUBFLOW_ADDRS 3
+#define MPTCP_FULL_INFO 4
+
+#endif /* _MPTCP_H */
diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h
new file mode 100644
index 0000000..a66f18a
--- /dev/null
+++ b/include/uapi/linux/mptcp_pm.h
@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/mptcp_pm.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _LINUX_MPTCP_PM_H
+#define _LINUX_MPTCP_PM_H
+
+#define MPTCP_PM_NAME "mptcp_pm"
+#define MPTCP_PM_VER 1
+
+/**
+ * enum mptcp_event_type
+ * @MPTCP_EVENT_UNSPEC: unused event
+ * @MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ * sport, dport A new MPTCP connection has been created. It is the good time
+ * to allocate memory and send ADD_ADDR if needed. Depending on the
+ * traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED
+ * is sent.
+ * @MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6,
+ * sport, dport A MPTCP connection is established (can start new subflows).
+ * @MPTCP_EVENT_CLOSED: token A MPTCP connection has stopped.
+ * @MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] A
+ * new address has been announced by the peer.
+ * @MPTCP_EVENT_REMOVED: token, rem_id An address has been lost by the peer.
+ * @MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, saddr4 |
+ * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error] A new
+ * subflow has been established. 'error' should not be set.
+ * @MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6,
+ * daddr4 | daddr6, sport, dport, backup, if_idx [, error] A subflow has been
+ * closed. An error (copy of sk_err) could be set if an error has been
+ * detected for this subflow.
+ * @MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6,
+ * daddr4 | daddr6, sport, dport, backup, if_idx [, error] The priority of a
+ * subflow has changed. 'error' should not be set.
+ * @MPTCP_EVENT_LISTENER_CREATED: family, sport, saddr4 | saddr6 A new PM
+ * listener is created.
+ * @MPTCP_EVENT_LISTENER_CLOSED: family, sport, saddr4 | saddr6 A PM listener
+ * is closed.
+ */
+enum mptcp_event_type {
+ MPTCP_EVENT_UNSPEC,
+ MPTCP_EVENT_CREATED,
+ MPTCP_EVENT_ESTABLISHED,
+ MPTCP_EVENT_CLOSED,
+ MPTCP_EVENT_ANNOUNCED = 6,
+ MPTCP_EVENT_REMOVED,
+ MPTCP_EVENT_SUB_ESTABLISHED = 10,
+ MPTCP_EVENT_SUB_CLOSED,
+ MPTCP_EVENT_SUB_PRIORITY = 13,
+ MPTCP_EVENT_LISTENER_CREATED = 15,
+ MPTCP_EVENT_LISTENER_CLOSED,
+};
+
+enum {
+ MPTCP_PM_ADDR_ATTR_UNSPEC,
+ MPTCP_PM_ADDR_ATTR_FAMILY,
+ MPTCP_PM_ADDR_ATTR_ID,
+ MPTCP_PM_ADDR_ATTR_ADDR4,
+ MPTCP_PM_ADDR_ATTR_ADDR6,
+ MPTCP_PM_ADDR_ATTR_PORT,
+ MPTCP_PM_ADDR_ATTR_FLAGS,
+ MPTCP_PM_ADDR_ATTR_IF_IDX,
+
+ __MPTCP_PM_ADDR_ATTR_MAX
+};
+#define MPTCP_PM_ADDR_ATTR_MAX (__MPTCP_PM_ADDR_ATTR_MAX - 1)
+
+enum {
+ MPTCP_SUBFLOW_ATTR_UNSPEC,
+ MPTCP_SUBFLOW_ATTR_TOKEN_REM,
+ MPTCP_SUBFLOW_ATTR_TOKEN_LOC,
+ MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
+ MPTCP_SUBFLOW_ATTR_MAP_SEQ,
+ MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
+ MPTCP_SUBFLOW_ATTR_SSN_OFFSET,
+ MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
+ MPTCP_SUBFLOW_ATTR_FLAGS,
+ MPTCP_SUBFLOW_ATTR_ID_REM,
+ MPTCP_SUBFLOW_ATTR_ID_LOC,
+ MPTCP_SUBFLOW_ATTR_PAD,
+
+ __MPTCP_SUBFLOW_ATTR_MAX
+};
+#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1)
+
+enum {
+ MPTCP_PM_ENDPOINT_ADDR = 1,
+
+ __MPTCP_PM_ENDPOINT_MAX
+};
+#define MPTCP_PM_ENDPOINT_MAX (__MPTCP_PM_ENDPOINT_MAX - 1)
+
+enum {
+ MPTCP_PM_ATTR_UNSPEC,
+ MPTCP_PM_ATTR_ADDR,
+ MPTCP_PM_ATTR_RCV_ADD_ADDRS,
+ MPTCP_PM_ATTR_SUBFLOWS,
+ MPTCP_PM_ATTR_TOKEN,
+ MPTCP_PM_ATTR_LOC_ID,
+ MPTCP_PM_ATTR_ADDR_REMOTE,
+
+ __MPTCP_ATTR_AFTER_LAST
+};
+#define MPTCP_PM_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1)
+
+enum mptcp_event_attr {
+ MPTCP_ATTR_UNSPEC,
+ MPTCP_ATTR_TOKEN,
+ MPTCP_ATTR_FAMILY,
+ MPTCP_ATTR_LOC_ID,
+ MPTCP_ATTR_REM_ID,
+ MPTCP_ATTR_SADDR4,
+ MPTCP_ATTR_SADDR6,
+ MPTCP_ATTR_DADDR4,
+ MPTCP_ATTR_DADDR6,
+ MPTCP_ATTR_SPORT,
+ MPTCP_ATTR_DPORT,
+ MPTCP_ATTR_BACKUP,
+ MPTCP_ATTR_ERROR,
+ MPTCP_ATTR_FLAGS,
+ MPTCP_ATTR_TIMEOUT,
+ MPTCP_ATTR_IF_IDX,
+ MPTCP_ATTR_RESET_REASON,
+ MPTCP_ATTR_RESET_FLAGS,
+ MPTCP_ATTR_SERVER_SIDE,
+
+ __MPTCP_ATTR_MAX
+};
+#define MPTCP_ATTR_MAX (__MPTCP_ATTR_MAX - 1)
+
+enum {
+ MPTCP_PM_CMD_UNSPEC,
+ MPTCP_PM_CMD_ADD_ADDR,
+ MPTCP_PM_CMD_DEL_ADDR,
+ MPTCP_PM_CMD_GET_ADDR,
+ MPTCP_PM_CMD_FLUSH_ADDRS,
+ MPTCP_PM_CMD_SET_LIMITS,
+ MPTCP_PM_CMD_GET_LIMITS,
+ MPTCP_PM_CMD_SET_FLAGS,
+ MPTCP_PM_CMD_ANNOUNCE,
+ MPTCP_PM_CMD_REMOVE,
+ MPTCP_PM_CMD_SUBFLOW_CREATE,
+ MPTCP_PM_CMD_SUBFLOW_DESTROY,
+
+ __MPTCP_PM_CMD_AFTER_LAST
+};
+#define MPTCP_PM_CMD_MAX (__MPTCP_PM_CMD_AFTER_LAST - 1)
+
+#endif /* _LINUX_MPTCP_PM_H */
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
new file mode 100644
index 0000000..5e67a7e
--- /dev/null
+++ b/include/uapi/linux/neighbour.h
@@ -0,0 +1,224 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_NEIGHBOUR_H
+#define __LINUX_NEIGHBOUR_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+struct ndmsg {
+ __u8 ndm_family;
+ __u8 ndm_pad1;
+ __u16 ndm_pad2;
+ __s32 ndm_ifindex;
+ __u16 ndm_state;
+ __u8 ndm_flags;
+ __u8 ndm_type;
+};
+
+enum {
+ NDA_UNSPEC,
+ NDA_DST,
+ NDA_LLADDR,
+ NDA_CACHEINFO,
+ NDA_PROBES,
+ NDA_VLAN,
+ NDA_PORT,
+ NDA_VNI,
+ NDA_IFINDEX,
+ NDA_MASTER,
+ NDA_LINK_NETNSID,
+ NDA_SRC_VNI,
+ NDA_PROTOCOL, /* Originator of entry */
+ NDA_NH_ID,
+ NDA_FDB_EXT_ATTRS,
+ NDA_FLAGS_EXT,
+ NDA_NDM_STATE_MASK,
+ NDA_NDM_FLAGS_MASK,
+ __NDA_MAX
+};
+
+#define NDA_MAX (__NDA_MAX - 1)
+
+/*
+ * Neighbor Cache Entry Flags
+ */
+
+#define NTF_USE (1 << 0)
+#define NTF_SELF (1 << 1)
+#define NTF_MASTER (1 << 2)
+#define NTF_PROXY (1 << 3) /* == ATF_PUBL */
+#define NTF_EXT_LEARNED (1 << 4)
+#define NTF_OFFLOADED (1 << 5)
+#define NTF_STICKY (1 << 6)
+#define NTF_ROUTER (1 << 7)
+/* Extended flags under NDA_FLAGS_EXT: */
+#define NTF_EXT_MANAGED (1 << 0)
+#define NTF_EXT_LOCKED (1 << 1)
+
+/*
+ * Neighbor Cache Entry States.
+ */
+
+#define NUD_INCOMPLETE 0x01
+#define NUD_REACHABLE 0x02
+#define NUD_STALE 0x04
+#define NUD_DELAY 0x08
+#define NUD_PROBE 0x10
+#define NUD_FAILED 0x20
+
+/* Dummy states */
+#define NUD_NOARP 0x40
+#define NUD_PERMANENT 0x80
+#define NUD_NONE 0x00
+
+/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change and make no
+ * address resolution or NUD.
+ *
+ * NUD_PERMANENT also cannot be deleted by garbage collectors. This holds true
+ * for dynamic entries with NTF_EXT_LEARNED flag as well. However, upon carrier
+ * down event, NUD_PERMANENT entries are not flushed whereas NTF_EXT_LEARNED
+ * flagged entries explicitly are (which is also consistent with the routing
+ * subsystem).
+ *
+ * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry
+ * states don't make sense and thus are ignored. Such entries don't age and
+ * can roam.
+ *
+ * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf
+ * of a user space control plane, and automatically refreshed so that (if
+ * possible) they remain in NUD_REACHABLE state.
+ *
+ * NTF_EXT_LOCKED flagged bridge FDB entries are entries generated by the
+ * bridge in response to a host trying to communicate via a locked bridge port
+ * with MAB enabled. Their purpose is to notify user space that a host requires
+ * authentication.
+ */
+
+struct nda_cacheinfo {
+ __u32 ndm_confirmed;
+ __u32 ndm_used;
+ __u32 ndm_updated;
+ __u32 ndm_refcnt;
+};
+
+/*****************************************************************
+ * Neighbour tables specific messages.
+ *
+ * To retrieve the neighbour tables send RTM_GETNEIGHTBL with the
+ * NLM_F_DUMP flag set. Every neighbour table configuration is
+ * spread over multiple messages to avoid running into message
+ * size limits on systems with many interfaces. The first message
+ * in the sequence transports all not device specific data such as
+ * statistics, configuration, and the default parameter set.
+ * This message is followed by 0..n messages carrying device
+ * specific parameter sets.
+ * Although the ordering should be sufficient, NDTA_NAME can be
+ * used to identify sequences. The initial message can be identified
+ * by checking for NDTA_CONFIG. The device specific messages do
+ * not contain this TLV but have NDTPA_IFINDEX set to the
+ * corresponding interface index.
+ *
+ * To change neighbour table attributes, send RTM_SETNEIGHTBL
+ * with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3],
+ * NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked
+ * otherwise. Device specific parameter sets can be changed by
+ * setting NDTPA_IFINDEX to the interface index of the corresponding
+ * device.
+ ****/
+
+struct ndt_stats {
+ __u64 ndts_allocs;
+ __u64 ndts_destroys;
+ __u64 ndts_hash_grows;
+ __u64 ndts_res_failed;
+ __u64 ndts_lookups;
+ __u64 ndts_hits;
+ __u64 ndts_rcv_probes_mcast;
+ __u64 ndts_rcv_probes_ucast;
+ __u64 ndts_periodic_gc_runs;
+ __u64 ndts_forced_gc_runs;
+ __u64 ndts_table_fulls;
+};
+
+enum {
+ NDTPA_UNSPEC,
+ NDTPA_IFINDEX, /* u32, unchangeable */
+ NDTPA_REFCNT, /* u32, read-only */
+ NDTPA_REACHABLE_TIME, /* u64, read-only, msecs */
+ NDTPA_BASE_REACHABLE_TIME, /* u64, msecs */
+ NDTPA_RETRANS_TIME, /* u64, msecs */
+ NDTPA_GC_STALETIME, /* u64, msecs */
+ NDTPA_DELAY_PROBE_TIME, /* u64, msecs */
+ NDTPA_QUEUE_LEN, /* u32 */
+ NDTPA_APP_PROBES, /* u32 */
+ NDTPA_UCAST_PROBES, /* u32 */
+ NDTPA_MCAST_PROBES, /* u32 */
+ NDTPA_ANYCAST_DELAY, /* u64, msecs */
+ NDTPA_PROXY_DELAY, /* u64, msecs */
+ NDTPA_PROXY_QLEN, /* u32 */
+ NDTPA_LOCKTIME, /* u64, msecs */
+ NDTPA_QUEUE_LENBYTES, /* u32 */
+ NDTPA_MCAST_REPROBES, /* u32 */
+ NDTPA_PAD,
+ NDTPA_INTERVAL_PROBE_TIME_MS, /* u64, msecs */
+ __NDTPA_MAX
+};
+#define NDTPA_MAX (__NDTPA_MAX - 1)
+
+struct ndtmsg {
+ __u8 ndtm_family;
+ __u8 ndtm_pad1;
+ __u16 ndtm_pad2;
+};
+
+struct ndt_config {
+ __u16 ndtc_key_len;
+ __u16 ndtc_entry_size;
+ __u32 ndtc_entries;
+ __u32 ndtc_last_flush; /* delta to now in msecs */
+ __u32 ndtc_last_rand; /* delta to now in msecs */
+ __u32 ndtc_hash_rnd;
+ __u32 ndtc_hash_mask;
+ __u32 ndtc_hash_chain_gc;
+ __u32 ndtc_proxy_qlen;
+};
+
+enum {
+ NDTA_UNSPEC,
+ NDTA_NAME, /* char *, unchangeable */
+ NDTA_THRESH1, /* u32 */
+ NDTA_THRESH2, /* u32 */
+ NDTA_THRESH3, /* u32 */
+ NDTA_CONFIG, /* struct ndt_config, read-only */
+ NDTA_PARMS, /* nested TLV NDTPA_* */
+ NDTA_STATS, /* struct ndt_stats, read-only */
+ NDTA_GC_INTERVAL, /* u64, msecs */
+ NDTA_PAD,
+ __NDTA_MAX
+};
+#define NDTA_MAX (__NDTA_MAX - 1)
+
+ /* FDB activity notification bits used in NFEA_ACTIVITY_NOTIFY:
+ * - FDB_NOTIFY_BIT - notify on activity/expire for any entry
+ * - FDB_NOTIFY_INACTIVE_BIT - mark as inactive to avoid multiple notifications
+ */
+enum {
+ FDB_NOTIFY_BIT = (1 << 0),
+ FDB_NOTIFY_INACTIVE_BIT = (1 << 1)
+};
+
+/* embedded into NDA_FDB_EXT_ATTRS:
+ * [NDA_FDB_EXT_ATTRS] = {
+ * [NFEA_ACTIVITY_NOTIFY]
+ * ...
+ * }
+ */
+enum {
+ NFEA_UNSPEC,
+ NFEA_ACTIVITY_NOTIFY,
+ NFEA_DONT_REFRESH,
+ __NFEA_MAX
+};
+#define NFEA_MAX (__NFEA_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/net.h b/include/uapi/linux/net.h
new file mode 100644
index 0000000..4754f70
--- /dev/null
+++ b/include/uapi/linux/net.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * NET An implementation of the SOCKET network access protocol.
+ * This is the master header file for the Linux NET layer,
+ * or, in plain English: the networking handling part of the
+ * kernel.
+ *
+ * Version: @(#)net.h 1.0.3 05/25/93
+ *
+ * Authors: Orest Zborowski, <obz@Kodak.COM>
+ * Ross Biro
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_NET_H
+#define _LINUX_NET_H
+
+#include <linux/socket.h>
+#include <asm/socket.h>
+
+#define NPROTO AF_MAX
+
+#define SYS_SOCKET 1 /* sys_socket(2) */
+#define SYS_BIND 2 /* sys_bind(2) */
+#define SYS_CONNECT 3 /* sys_connect(2) */
+#define SYS_LISTEN 4 /* sys_listen(2) */
+#define SYS_ACCEPT 5 /* sys_accept(2) */
+#define SYS_GETSOCKNAME 6 /* sys_getsockname(2) */
+#define SYS_GETPEERNAME 7 /* sys_getpeername(2) */
+#define SYS_SOCKETPAIR 8 /* sys_socketpair(2) */
+#define SYS_SEND 9 /* sys_send(2) */
+#define SYS_RECV 10 /* sys_recv(2) */
+#define SYS_SENDTO 11 /* sys_sendto(2) */
+#define SYS_RECVFROM 12 /* sys_recvfrom(2) */
+#define SYS_SHUTDOWN 13 /* sys_shutdown(2) */
+#define SYS_SETSOCKOPT 14 /* sys_setsockopt(2) */
+#define SYS_GETSOCKOPT 15 /* sys_getsockopt(2) */
+#define SYS_SENDMSG 16 /* sys_sendmsg(2) */
+#define SYS_RECVMSG 17 /* sys_recvmsg(2) */
+#define SYS_ACCEPT4 18 /* sys_accept4(2) */
+#define SYS_RECVMMSG 19 /* sys_recvmmsg(2) */
+#define SYS_SENDMMSG 20 /* sys_sendmmsg(2) */
+
+typedef enum {
+ SS_FREE = 0, /* not allocated */
+ SS_UNCONNECTED, /* unconnected to any socket */
+ SS_CONNECTING, /* in process of connecting */
+ SS_CONNECTED, /* connected to socket */
+ SS_DISCONNECTING /* in process of disconnecting */
+} socket_state;
+
+#define __SO_ACCEPTCON (1 << 16) /* performed a listen */
+
+#endif /* _LINUX_NET_H */
diff --git a/include/uapi/linux/net_namespace.h b/include/uapi/linux/net_namespace.h
new file mode 100644
index 0000000..fa81f1e
--- /dev/null
+++ b/include/uapi/linux/net_namespace.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2015 6WIND S.A.
+ * Author: Nicolas Dichtel <nicolas.dichtel@6wind.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+#ifndef _LINUX_NET_NAMESPACE_H_
+#define _LINUX_NET_NAMESPACE_H_
+
+/* Attributes of RTM_NEWNSID/RTM_GETNSID messages */
+enum {
+ NETNSA_NONE,
+#define NETNSA_NSID_NOT_ASSIGNED -1
+ NETNSA_NSID,
+ NETNSA_PID,
+ NETNSA_FD,
+ NETNSA_TARGET_NSID,
+ NETNSA_CURRENT_NSID,
+ __NETNSA_MAX,
+};
+
+#define NETNSA_MAX (__NETNSA_MAX - 1)
+
+#endif /* _LINUX_NET_NAMESPACE_H_ */
diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
new file mode 100644
index 0000000..229e885
--- /dev/null
+++ b/include/uapi/linux/netconf.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_NETCONF_H_
+#define _LINUX_NETCONF_H_
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+struct netconfmsg {
+ __u8 ncm_family;
+};
+
+enum {
+ NETCONFA_UNSPEC,
+ NETCONFA_IFINDEX,
+ NETCONFA_FORWARDING,
+ NETCONFA_RP_FILTER,
+ NETCONFA_MC_FORWARDING,
+ NETCONFA_PROXY_NEIGH,
+ NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+ NETCONFA_INPUT,
+ NETCONFA_BC_FORWARDING,
+ __NETCONFA_MAX
+};
+#define NETCONFA_MAX (__NETCONFA_MAX - 1)
+#define NETCONFA_ALL -1
+
+#define NETCONFA_IFINDEX_ALL -1
+#define NETCONFA_IFINDEX_DEFAULT -2
+
+#endif /* _LINUX_NETCONF_H_ */
diff --git a/include/uapi/linux/netdevice.h b/include/uapi/linux/netdevice.h
new file mode 100644
index 0000000..86d961c
--- /dev/null
+++ b/include/uapi/linux/netdevice.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions for the Interfaces handler.
+ *
+ * Version: @(#)dev.h 1.0.10 08/12/93
+ *
+ * Authors: Ross Biro
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ * Corey Minyard <wf-rch!minyard@relay.EU.net>
+ * Donald J. Becker, <becker@cesdis.gsfc.nasa.gov>
+ * Alan Cox, <alan@lxorguk.ukuu.org.uk>
+ * Bjorn Ekwall. <bj0rn@blox.se>
+ * Pekka Riikonen <priikone@poseidon.pspt.fi>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Moved to /usr/include/linux for NET3
+ */
+#ifndef _LINUX_NETDEVICE_H
+#define _LINUX_NETDEVICE_H
+
+#include <linux/if.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_link.h>
+
+
+#define MAX_ADDR_LEN 32 /* Largest hardware address length */
+
+/* Initial net device group. All devices belong to group 0 by default. */
+#define INIT_NETDEV_GROUP 0
+
+
+/* interface name assignment types (sysfs name_assign_type attribute) */
+#define NET_NAME_UNKNOWN 0 /* unknown origin (not exposed to userspace) */
+#define NET_NAME_ENUM 1 /* enumerated by kernel */
+#define NET_NAME_PREDICTABLE 2 /* predictably named by the kernel */
+#define NET_NAME_USER 3 /* provided by user-space */
+#define NET_NAME_RENAMED 4 /* renamed by user-space */
+
+/* Media selection options. */
+enum {
+ IF_PORT_UNKNOWN = 0,
+ IF_PORT_10BASE2,
+ IF_PORT_10BASET,
+ IF_PORT_AUI,
+ IF_PORT_100BASET,
+ IF_PORT_100BASETX,
+ IF_PORT_100BASEFX
+};
+
+/* hardware address assignment types */
+#define NET_ADDR_PERM 0 /* address is permanent (default) */
+#define NET_ADDR_RANDOM 1 /* address is generated randomly */
+#define NET_ADDR_STOLEN 2 /* address is stolen from other device */
+#define NET_ADDR_SET 3 /* address is set using
+ * dev_set_mac_address() */
+
+#endif /* _LINUX_NETDEVICE_H */
diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h
new file mode 100644
index 0000000..30c045b
--- /dev/null
+++ b/include/uapi/linux/netfilter.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_NETFILTER_H
+#define __LINUX_NETFILTER_H
+
+#include <linux/types.h>
+
+#include <linux/in.h>
+#include <linux/in6.h>
+
+/* Responses from hook functions. */
+#define NF_DROP 0
+#define NF_ACCEPT 1
+#define NF_STOLEN 2
+#define NF_QUEUE 3
+#define NF_REPEAT 4
+#define NF_STOP 5 /* Deprecated, for userspace nf_queue compatibility. */
+#define NF_MAX_VERDICT NF_STOP
+
+/* we overload the higher bits for encoding auxiliary data such as the queue
+ * number or errno values. Not nice, but better than additional function
+ * arguments. */
+#define NF_VERDICT_MASK 0x000000ff
+
+/* extra verdict flags have mask 0x0000ff00 */
+#define NF_VERDICT_FLAG_QUEUE_BYPASS 0x00008000
+
+/* queue number (NF_QUEUE) or errno (NF_DROP) */
+#define NF_VERDICT_QMASK 0xffff0000
+#define NF_VERDICT_QBITS 16
+
+#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE)
+
+#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP)
+
+/* only for userspace compatibility */
+
+/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */
+#define NF_VERDICT_BITS 16
+
+enum nf_inet_hooks {
+ NF_INET_PRE_ROUTING,
+ NF_INET_LOCAL_IN,
+ NF_INET_FORWARD,
+ NF_INET_LOCAL_OUT,
+ NF_INET_POST_ROUTING,
+ NF_INET_NUMHOOKS,
+ NF_INET_INGRESS = NF_INET_NUMHOOKS,
+};
+
+enum nf_dev_hooks {
+ NF_NETDEV_INGRESS,
+ NF_NETDEV_EGRESS,
+ NF_NETDEV_NUMHOOKS
+};
+
+enum {
+ NFPROTO_UNSPEC = 0,
+ NFPROTO_INET = 1,
+ NFPROTO_IPV4 = 2,
+ NFPROTO_ARP = 3,
+ NFPROTO_NETDEV = 5,
+ NFPROTO_BRIDGE = 7,
+ NFPROTO_IPV6 = 10,
+ NFPROTO_DECNET = 12,
+ NFPROTO_NUMPROTO,
+};
+
+union nf_inet_addr {
+ __u32 all[4];
+ __be32 ip;
+ __be32 ip6[4];
+ struct in_addr in;
+ struct in6_addr in6;
+};
+
+#endif /* __LINUX_NETFILTER_H */
diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
new file mode 100644
index 0000000..f9725c3
--- /dev/null
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -0,0 +1,312 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
+ * Patrick Schaaf <bof@bof.de>
+ * Martin Josefsson <gandalf@wlug.westbo.se>
+ * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@netfilter.org>
+ */
+#ifndef _IP_SET_H
+#define _IP_SET_H
+
+#include <linux/types.h>
+
+/* The protocol versions */
+#define IPSET_PROTOCOL 7
+#define IPSET_PROTOCOL_MIN 6
+
+/* The max length of strings including NUL: set and type identifiers */
+#define IPSET_MAXNAMELEN 32
+
+/* The maximum permissible comment length we will accept over netlink */
+#define IPSET_MAX_COMMENT_SIZE 255
+
+/* Message types and commands */
+enum ipset_cmd {
+ IPSET_CMD_NONE,
+ IPSET_CMD_PROTOCOL, /* 1: Return protocol version */
+ IPSET_CMD_CREATE, /* 2: Create a new (empty) set */
+ IPSET_CMD_DESTROY, /* 3: Destroy a (empty) set */
+ IPSET_CMD_FLUSH, /* 4: Remove all elements from a set */
+ IPSET_CMD_RENAME, /* 5: Rename a set */
+ IPSET_CMD_SWAP, /* 6: Swap two sets */
+ IPSET_CMD_LIST, /* 7: List sets */
+ IPSET_CMD_SAVE, /* 8: Save sets */
+ IPSET_CMD_ADD, /* 9: Add an element to a set */
+ IPSET_CMD_DEL, /* 10: Delete an element from a set */
+ IPSET_CMD_TEST, /* 11: Test an element in a set */
+ IPSET_CMD_HEADER, /* 12: Get set header data only */
+ IPSET_CMD_TYPE, /* 13: Get set type */
+ IPSET_CMD_GET_BYNAME, /* 14: Get set index by name */
+ IPSET_CMD_GET_BYINDEX, /* 15: Get set name by index */
+ IPSET_MSG_MAX, /* Netlink message commands */
+
+ /* Commands in userspace: */
+ IPSET_CMD_RESTORE = IPSET_MSG_MAX, /* 16: Enter restore mode */
+ IPSET_CMD_HELP, /* 17: Get help */
+ IPSET_CMD_VERSION, /* 18: Get program version */
+ IPSET_CMD_QUIT, /* 19: Quit from interactive mode */
+
+ IPSET_CMD_MAX,
+
+ IPSET_CMD_COMMIT = IPSET_CMD_MAX, /* 20: Commit buffered commands */
+};
+
+/* Attributes at command level */
+enum {
+ IPSET_ATTR_UNSPEC,
+ IPSET_ATTR_PROTOCOL, /* 1: Protocol version */
+ IPSET_ATTR_SETNAME, /* 2: Name of the set */
+ IPSET_ATTR_TYPENAME, /* 3: Typename */
+ IPSET_ATTR_SETNAME2 = IPSET_ATTR_TYPENAME, /* Setname at rename/swap */
+ IPSET_ATTR_REVISION, /* 4: Settype revision */
+ IPSET_ATTR_FAMILY, /* 5: Settype family */
+ IPSET_ATTR_FLAGS, /* 6: Flags at command level */
+ IPSET_ATTR_DATA, /* 7: Nested attributes */
+ IPSET_ATTR_ADT, /* 8: Multiple data containers */
+ IPSET_ATTR_LINENO, /* 9: Restore lineno */
+ IPSET_ATTR_PROTOCOL_MIN, /* 10: Minimal supported version number */
+ IPSET_ATTR_REVISION_MIN = IPSET_ATTR_PROTOCOL_MIN, /* type rev min */
+ IPSET_ATTR_INDEX, /* 11: Kernel index of set */
+ __IPSET_ATTR_CMD_MAX,
+};
+#define IPSET_ATTR_CMD_MAX (__IPSET_ATTR_CMD_MAX - 1)
+
+/* CADT specific attributes */
+enum {
+ IPSET_ATTR_IP = IPSET_ATTR_UNSPEC + 1,
+ IPSET_ATTR_IP_FROM = IPSET_ATTR_IP,
+ IPSET_ATTR_IP_TO, /* 2 */
+ IPSET_ATTR_CIDR, /* 3 */
+ IPSET_ATTR_PORT, /* 4 */
+ IPSET_ATTR_PORT_FROM = IPSET_ATTR_PORT,
+ IPSET_ATTR_PORT_TO, /* 5 */
+ IPSET_ATTR_TIMEOUT, /* 6 */
+ IPSET_ATTR_PROTO, /* 7 */
+ IPSET_ATTR_CADT_FLAGS, /* 8 */
+ IPSET_ATTR_CADT_LINENO = IPSET_ATTR_LINENO, /* 9 */
+ IPSET_ATTR_MARK, /* 10 */
+ IPSET_ATTR_MARKMASK, /* 11 */
+ IPSET_ATTR_BITMASK, /* 12 */
+ /* Reserve empty slots */
+ IPSET_ATTR_CADT_MAX = 16,
+ /* Create-only specific attributes */
+ IPSET_ATTR_INITVAL, /* was unused IPSET_ATTR_GC */
+ IPSET_ATTR_HASHSIZE,
+ IPSET_ATTR_MAXELEM,
+ IPSET_ATTR_NETMASK,
+ IPSET_ATTR_BUCKETSIZE, /* was unused IPSET_ATTR_PROBES */
+ IPSET_ATTR_RESIZE,
+ IPSET_ATTR_SIZE,
+ /* Kernel-only */
+ IPSET_ATTR_ELEMENTS,
+ IPSET_ATTR_REFERENCES,
+ IPSET_ATTR_MEMSIZE,
+
+ __IPSET_ATTR_CREATE_MAX,
+};
+#define IPSET_ATTR_CREATE_MAX (__IPSET_ATTR_CREATE_MAX - 1)
+
+/* ADT specific attributes */
+enum {
+ IPSET_ATTR_ETHER = IPSET_ATTR_CADT_MAX + 1,
+ IPSET_ATTR_NAME,
+ IPSET_ATTR_NAMEREF,
+ IPSET_ATTR_IP2,
+ IPSET_ATTR_CIDR2,
+ IPSET_ATTR_IP2_TO,
+ IPSET_ATTR_IFACE,
+ IPSET_ATTR_BYTES,
+ IPSET_ATTR_PACKETS,
+ IPSET_ATTR_COMMENT,
+ IPSET_ATTR_SKBMARK,
+ IPSET_ATTR_SKBPRIO,
+ IPSET_ATTR_SKBQUEUE,
+ IPSET_ATTR_PAD,
+ __IPSET_ATTR_ADT_MAX,
+};
+#define IPSET_ATTR_ADT_MAX (__IPSET_ATTR_ADT_MAX - 1)
+
+/* IP specific attributes */
+enum {
+ IPSET_ATTR_IPADDR_IPV4 = IPSET_ATTR_UNSPEC + 1,
+ IPSET_ATTR_IPADDR_IPV6,
+ __IPSET_ATTR_IPADDR_MAX,
+};
+#define IPSET_ATTR_IPADDR_MAX (__IPSET_ATTR_IPADDR_MAX - 1)
+
+/* Error codes */
+enum ipset_errno {
+ IPSET_ERR_PRIVATE = 4096,
+ IPSET_ERR_PROTOCOL,
+ IPSET_ERR_FIND_TYPE,
+ IPSET_ERR_MAX_SETS,
+ IPSET_ERR_BUSY,
+ IPSET_ERR_EXIST_SETNAME2,
+ IPSET_ERR_TYPE_MISMATCH,
+ IPSET_ERR_EXIST,
+ IPSET_ERR_INVALID_CIDR,
+ IPSET_ERR_INVALID_NETMASK,
+ IPSET_ERR_INVALID_FAMILY,
+ IPSET_ERR_TIMEOUT,
+ IPSET_ERR_REFERENCED,
+ IPSET_ERR_IPADDR_IPV4,
+ IPSET_ERR_IPADDR_IPV6,
+ IPSET_ERR_COUNTER,
+ IPSET_ERR_COMMENT,
+ IPSET_ERR_INVALID_MARKMASK,
+ IPSET_ERR_SKBINFO,
+ IPSET_ERR_BITMASK_NETMASK_EXCL,
+
+ /* Type specific error codes */
+ IPSET_ERR_TYPE_SPECIFIC = 4352,
+};
+
+/* Flags at command level or match/target flags, lower half of cmdattrs*/
+enum ipset_cmd_flags {
+ IPSET_FLAG_BIT_EXIST = 0,
+ IPSET_FLAG_EXIST = (1 << IPSET_FLAG_BIT_EXIST),
+ IPSET_FLAG_BIT_LIST_SETNAME = 1,
+ IPSET_FLAG_LIST_SETNAME = (1 << IPSET_FLAG_BIT_LIST_SETNAME),
+ IPSET_FLAG_BIT_LIST_HEADER = 2,
+ IPSET_FLAG_LIST_HEADER = (1 << IPSET_FLAG_BIT_LIST_HEADER),
+ IPSET_FLAG_BIT_SKIP_COUNTER_UPDATE = 3,
+ IPSET_FLAG_SKIP_COUNTER_UPDATE =
+ (1 << IPSET_FLAG_BIT_SKIP_COUNTER_UPDATE),
+ IPSET_FLAG_BIT_SKIP_SUBCOUNTER_UPDATE = 4,
+ IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE =
+ (1 << IPSET_FLAG_BIT_SKIP_SUBCOUNTER_UPDATE),
+ IPSET_FLAG_BIT_MATCH_COUNTERS = 5,
+ IPSET_FLAG_MATCH_COUNTERS = (1 << IPSET_FLAG_BIT_MATCH_COUNTERS),
+ IPSET_FLAG_BIT_RETURN_NOMATCH = 7,
+ IPSET_FLAG_RETURN_NOMATCH = (1 << IPSET_FLAG_BIT_RETURN_NOMATCH),
+ IPSET_FLAG_BIT_MAP_SKBMARK = 8,
+ IPSET_FLAG_MAP_SKBMARK = (1 << IPSET_FLAG_BIT_MAP_SKBMARK),
+ IPSET_FLAG_BIT_MAP_SKBPRIO = 9,
+ IPSET_FLAG_MAP_SKBPRIO = (1 << IPSET_FLAG_BIT_MAP_SKBPRIO),
+ IPSET_FLAG_BIT_MAP_SKBQUEUE = 10,
+ IPSET_FLAG_MAP_SKBQUEUE = (1 << IPSET_FLAG_BIT_MAP_SKBQUEUE),
+ IPSET_FLAG_CMD_MAX = 15,
+};
+
+/* Flags at CADT attribute level, upper half of cmdattrs */
+enum ipset_cadt_flags {
+ IPSET_FLAG_BIT_BEFORE = 0,
+ IPSET_FLAG_BEFORE = (1 << IPSET_FLAG_BIT_BEFORE),
+ IPSET_FLAG_BIT_PHYSDEV = 1,
+ IPSET_FLAG_PHYSDEV = (1 << IPSET_FLAG_BIT_PHYSDEV),
+ IPSET_FLAG_BIT_NOMATCH = 2,
+ IPSET_FLAG_NOMATCH = (1 << IPSET_FLAG_BIT_NOMATCH),
+ IPSET_FLAG_BIT_WITH_COUNTERS = 3,
+ IPSET_FLAG_WITH_COUNTERS = (1 << IPSET_FLAG_BIT_WITH_COUNTERS),
+ IPSET_FLAG_BIT_WITH_COMMENT = 4,
+ IPSET_FLAG_WITH_COMMENT = (1 << IPSET_FLAG_BIT_WITH_COMMENT),
+ IPSET_FLAG_BIT_WITH_FORCEADD = 5,
+ IPSET_FLAG_WITH_FORCEADD = (1 << IPSET_FLAG_BIT_WITH_FORCEADD),
+ IPSET_FLAG_BIT_WITH_SKBINFO = 6,
+ IPSET_FLAG_WITH_SKBINFO = (1 << IPSET_FLAG_BIT_WITH_SKBINFO),
+ IPSET_FLAG_BIT_IFACE_WILDCARD = 7,
+ IPSET_FLAG_IFACE_WILDCARD = (1 << IPSET_FLAG_BIT_IFACE_WILDCARD),
+ IPSET_FLAG_CADT_MAX = 15,
+};
+
+/* The flag bits which correspond to the non-extension create flags */
+enum ipset_create_flags {
+ IPSET_CREATE_FLAG_BIT_FORCEADD = 0,
+ IPSET_CREATE_FLAG_FORCEADD = (1 << IPSET_CREATE_FLAG_BIT_FORCEADD),
+ IPSET_CREATE_FLAG_BIT_BUCKETSIZE = 1,
+ IPSET_CREATE_FLAG_BUCKETSIZE = (1 << IPSET_CREATE_FLAG_BIT_BUCKETSIZE),
+ IPSET_CREATE_FLAG_BIT_MAX = 7,
+};
+
+/* Commands with settype-specific attributes */
+enum ipset_adt {
+ IPSET_ADD,
+ IPSET_DEL,
+ IPSET_TEST,
+ IPSET_ADT_MAX,
+ IPSET_CREATE = IPSET_ADT_MAX,
+ IPSET_CADT_MAX,
+};
+
+/* Sets are identified by an index in kernel space. Tweak with ip_set_id_t
+ * and IPSET_INVALID_ID if you want to increase the max number of sets.
+ * Also, IPSET_ATTR_INDEX must be changed.
+ */
+typedef __u16 ip_set_id_t;
+
+#define IPSET_INVALID_ID 65535
+
+enum ip_set_dim {
+ IPSET_DIM_ZERO = 0,
+ IPSET_DIM_ONE,
+ IPSET_DIM_TWO,
+ IPSET_DIM_THREE,
+ /* Max dimension in elements.
+ * If changed, new revision of iptables match/target is required.
+ */
+ IPSET_DIM_MAX = 6,
+ /* Backward compatibility: set match revision 2 */
+ IPSET_BIT_RETURN_NOMATCH = 7,
+};
+
+/* Option flags for kernel operations */
+enum ip_set_kopt {
+ IPSET_INV_MATCH = (1 << IPSET_DIM_ZERO),
+ IPSET_DIM_ONE_SRC = (1 << IPSET_DIM_ONE),
+ IPSET_DIM_TWO_SRC = (1 << IPSET_DIM_TWO),
+ IPSET_DIM_THREE_SRC = (1 << IPSET_DIM_THREE),
+ IPSET_RETURN_NOMATCH = (1 << IPSET_BIT_RETURN_NOMATCH),
+};
+
+enum {
+ IPSET_COUNTER_NONE = 0,
+ IPSET_COUNTER_EQ,
+ IPSET_COUNTER_NE,
+ IPSET_COUNTER_LT,
+ IPSET_COUNTER_GT,
+};
+
+/* Backward compatibility for set match v3 */
+struct ip_set_counter_match0 {
+ __u8 op;
+ __u64 value;
+};
+
+struct ip_set_counter_match {
+ __aligned_u64 value;
+ __u8 op;
+};
+
+/* Interface to iptables/ip6tables */
+
+#define SO_IP_SET 83
+
+union ip_set_name_index {
+ char name[IPSET_MAXNAMELEN];
+ ip_set_id_t index;
+};
+
+#define IP_SET_OP_GET_BYNAME 0x00000006 /* Get set index by name */
+struct ip_set_req_get_set {
+ unsigned int op;
+ unsigned int version;
+ union ip_set_name_index set;
+};
+
+#define IP_SET_OP_GET_BYINDEX 0x00000007 /* Get set name by index */
+/* Uses ip_set_req_get_set */
+
+#define IP_SET_OP_GET_FNAME 0x00000008 /* Get set index and family */
+struct ip_set_req_get_set_family {
+ unsigned int op;
+ unsigned int version;
+ unsigned int family;
+ union ip_set_name_index set;
+};
+
+#define IP_SET_OP_VERSION 0x00000100 /* Ask kernel version */
+struct ip_set_req_version {
+ unsigned int op;
+ unsigned int version;
+};
+
+#endif /* _IP_SET_H */
diff --git a/include/uapi/linux/netfilter/x_tables.h b/include/uapi/linux/netfilter/x_tables.h
new file mode 100644
index 0000000..15e4a9c
--- /dev/null
+++ b/include/uapi/linux/netfilter/x_tables.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _X_TABLES_H
+#define _X_TABLES_H
+#include <linux/const.h>
+#include <linux/types.h>
+
+#define XT_FUNCTION_MAXNAMELEN 30
+#define XT_EXTENSION_MAXNAMELEN 29
+#define XT_TABLE_MAXNAMELEN 32
+
+struct xt_entry_match {
+ union {
+ struct {
+ __u16 match_size;
+
+ /* Used by userspace */
+ char name[XT_EXTENSION_MAXNAMELEN];
+ __u8 revision;
+ } user;
+ struct {
+ __u16 match_size;
+
+ /* Used inside the kernel */
+ struct xt_match *match;
+ } kernel;
+
+ /* Total length */
+ __u16 match_size;
+ } u;
+
+ unsigned char data[];
+};
+
+struct xt_entry_target {
+ union {
+ struct {
+ __u16 target_size;
+
+ /* Used by userspace */
+ char name[XT_EXTENSION_MAXNAMELEN];
+ __u8 revision;
+ } user;
+ struct {
+ __u16 target_size;
+
+ /* Used inside the kernel */
+ struct xt_target *target;
+ } kernel;
+
+ /* Total length */
+ __u16 target_size;
+ } u;
+
+ unsigned char data[0];
+};
+
+#define XT_TARGET_INIT(__name, __size) \
+{ \
+ .target.u.user = { \
+ .target_size = XT_ALIGN(__size), \
+ .name = __name, \
+ }, \
+}
+
+struct xt_standard_target {
+ struct xt_entry_target target;
+ int verdict;
+};
+
+struct xt_error_target {
+ struct xt_entry_target target;
+ char errorname[XT_FUNCTION_MAXNAMELEN];
+};
+
+/* The argument to IPT_SO_GET_REVISION_*. Returns highest revision
+ * kernel supports, if >= revision. */
+struct xt_get_revision {
+ char name[XT_EXTENSION_MAXNAMELEN];
+ __u8 revision;
+};
+
+/* CONTINUE verdict for targets */
+#define XT_CONTINUE 0xFFFFFFFF
+
+/* For standard target */
+#define XT_RETURN (-NF_REPEAT - 1)
+
+/* this is a dummy structure to find out the alignment requirement for a struct
+ * containing all the fundamental data types that are used in ipt_entry,
+ * ip6t_entry and arpt_entry. This sucks, and it is a hack. It will be my
+ * personal pleasure to remove it -HW
+ */
+struct _xt_align {
+ __u8 u8;
+ __u16 u16;
+ __u32 u32;
+ __u64 u64;
+};
+
+#define XT_ALIGN(s) __ALIGN_KERNEL((s), __alignof__(struct _xt_align))
+
+/* Standard return verdict, or do jump. */
+#define XT_STANDARD_TARGET ""
+/* Error verdict. */
+#define XT_ERROR_TARGET "ERROR"
+
+#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0)
+#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0)
+
+struct xt_counters {
+ __u64 pcnt, bcnt; /* Packet and byte counters */
+};
+
+/* The argument to IPT_SO_ADD_COUNTERS. */
+struct xt_counters_info {
+ /* Which table. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ unsigned int num_counters;
+
+ /* The counters (actually `number' of these). */
+ struct xt_counters counters[];
+};
+
+#define XT_INV_PROTO 0x40 /* Invert the sense of PROTO. */
+
+/* fn returns 0 to continue iteration */
+#define XT_MATCH_ITERATE(type, e, fn, args...) \
+({ \
+ unsigned int __i; \
+ int __ret = 0; \
+ struct xt_entry_match *__m; \
+ \
+ for (__i = sizeof(type); \
+ __i < (e)->target_offset; \
+ __i += __m->u.match_size) { \
+ __m = (void *)e + __i; \
+ \
+ __ret = fn(__m , ## args); \
+ if (__ret != 0) \
+ break; \
+ } \
+ __ret; \
+})
+
+/* fn returns 0 to continue iteration */
+#define XT_ENTRY_ITERATE_CONTINUE(type, entries, size, n, fn, args...) \
+({ \
+ unsigned int __i, __n; \
+ int __ret = 0; \
+ type *__entry; \
+ \
+ for (__i = 0, __n = 0; __i < (size); \
+ __i += __entry->next_offset, __n++) { \
+ __entry = (void *)(entries) + __i; \
+ if (__n < n) \
+ continue; \
+ \
+ __ret = fn(__entry , ## args); \
+ if (__ret != 0) \
+ break; \
+ } \
+ __ret; \
+})
+
+/* fn returns 0 to continue iteration */
+#define XT_ENTRY_ITERATE(type, entries, size, fn, args...) \
+ XT_ENTRY_ITERATE_CONTINUE(type, entries, size, 0, fn, args)
+
+
+/* pos is normally a struct ipt_entry/ip6t_entry/etc. */
+#define xt_entry_foreach(pos, ehead, esize) \
+ for ((pos) = (typeof(pos))(ehead); \
+ (pos) < (typeof(pos))((char *)(ehead) + (esize)); \
+ (pos) = (typeof(pos))((char *)(pos) + (pos)->next_offset))
+
+/* can only be xt_entry_match, so no use of typeof here */
+#define xt_ematch_foreach(pos, entry) \
+ for ((pos) = (struct xt_entry_match *)entry->elems; \
+ (pos) < (struct xt_entry_match *)((char *)(entry) + \
+ (entry)->target_offset); \
+ (pos) = (struct xt_entry_match *)((char *)(pos) + \
+ (pos)->u.match_size))
+
+
+#endif /* _X_TABLES_H */
diff --git a/include/uapi/linux/netfilter/xt_set.h b/include/uapi/linux/netfilter/xt_set.h
new file mode 100644
index 0000000..8c1ca66
--- /dev/null
+++ b/include/uapi/linux/netfilter/xt_set.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _XT_SET_H
+#define _XT_SET_H
+
+#include <linux/types.h>
+#include <linux/netfilter/ipset/ip_set.h>
+
+/* Revision 0 interface: backward compatible with netfilter/iptables */
+
+/*
+ * Option flags for kernel operations (xt_set_info_v0)
+ */
+#define IPSET_SRC 0x01 /* Source match/add */
+#define IPSET_DST 0x02 /* Destination match/add */
+#define IPSET_MATCH_INV 0x04 /* Inverse matching */
+
+struct xt_set_info_v0 {
+ ip_set_id_t index;
+ union {
+ __u32 flags[IPSET_DIM_MAX + 1];
+ struct {
+ __u32 __flags[IPSET_DIM_MAX];
+ __u8 dim;
+ __u8 flags;
+ } compat;
+ } u;
+};
+
+/* match and target infos */
+struct xt_set_info_match_v0 {
+ struct xt_set_info_v0 match_set;
+};
+
+struct xt_set_info_target_v0 {
+ struct xt_set_info_v0 add_set;
+ struct xt_set_info_v0 del_set;
+};
+
+/* Revision 1 match and target */
+
+struct xt_set_info {
+ ip_set_id_t index;
+ __u8 dim;
+ __u8 flags;
+};
+
+/* match and target infos */
+struct xt_set_info_match_v1 {
+ struct xt_set_info match_set;
+};
+
+struct xt_set_info_target_v1 {
+ struct xt_set_info add_set;
+ struct xt_set_info del_set;
+};
+
+/* Revision 2 target */
+
+struct xt_set_info_target_v2 {
+ struct xt_set_info add_set;
+ struct xt_set_info del_set;
+ __u32 flags;
+ __u32 timeout;
+};
+
+/* Revision 3 match */
+
+struct xt_set_info_match_v3 {
+ struct xt_set_info match_set;
+ struct ip_set_counter_match0 packets;
+ struct ip_set_counter_match0 bytes;
+ __u32 flags;
+};
+
+/* Revision 3 target */
+
+struct xt_set_info_target_v3 {
+ struct xt_set_info add_set;
+ struct xt_set_info del_set;
+ struct xt_set_info map_set;
+ __u32 flags;
+ __u32 timeout;
+};
+
+/* Revision 4 match */
+
+struct xt_set_info_match_v4 {
+ struct xt_set_info match_set;
+ struct ip_set_counter_match packets;
+ struct ip_set_counter_match bytes;
+ __u32 flags;
+};
+
+#endif /*_XT_SET_H*/
diff --git a/include/uapi/linux/netfilter/xt_tcpudp.h b/include/uapi/linux/netfilter/xt_tcpudp.h
new file mode 100644
index 0000000..658c169
--- /dev/null
+++ b/include/uapi/linux/netfilter/xt_tcpudp.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _XT_TCPUDP_H
+#define _XT_TCPUDP_H
+
+#include <linux/types.h>
+
+/* TCP matching stuff */
+struct xt_tcp {
+ __u16 spts[2]; /* Source port range. */
+ __u16 dpts[2]; /* Destination port range. */
+ __u8 option; /* TCP Option iff non-zero*/
+ __u8 flg_mask; /* TCP flags mask byte */
+ __u8 flg_cmp; /* TCP flags compare byte */
+ __u8 invflags; /* Inverse flags */
+};
+
+/* Values for "inv" field in struct ipt_tcp. */
+#define XT_TCP_INV_SRCPT 0x01 /* Invert the sense of source ports. */
+#define XT_TCP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */
+#define XT_TCP_INV_FLAGS 0x04 /* Invert the sense of TCP flags. */
+#define XT_TCP_INV_OPTION 0x08 /* Invert the sense of option test. */
+#define XT_TCP_INV_MASK 0x0F /* All possible flags. */
+
+/* UDP matching stuff */
+struct xt_udp {
+ __u16 spts[2]; /* Source port range. */
+ __u16 dpts[2]; /* Destination port range. */
+ __u8 invflags; /* Inverse flags */
+};
+
+/* Values for "invflags" field in struct ipt_udp. */
+#define XT_UDP_INV_SRCPT 0x01 /* Invert the sense of source ports. */
+#define XT_UDP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */
+#define XT_UDP_INV_MASK 0x03 /* All possible flags. */
+
+
+#endif
diff --git a/include/uapi/linux/netfilter_ipv4.h b/include/uapi/linux/netfilter_ipv4.h
new file mode 100644
index 0000000..96979e3
--- /dev/null
+++ b/include/uapi/linux/netfilter_ipv4.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* IPv4-specific defines for netfilter.
+ * (C)1998 Rusty Russell -- This code is GPL.
+ */
+#ifndef __LINUX_IP_NETFILTER_H
+#define __LINUX_IP_NETFILTER_H
+
+
+#include <linux/netfilter.h>
+
+/* only for userspace compatibility */
+
+#include <limits.h> /* for INT_MIN, INT_MAX */
+
+/* IP Hooks */
+/* After promisc drops, checksum checks. */
+#define NF_IP_PRE_ROUTING 0
+/* If the packet is destined for this box. */
+#define NF_IP_LOCAL_IN 1
+/* If the packet is destined for another interface. */
+#define NF_IP_FORWARD 2
+/* Packets coming from a local process. */
+#define NF_IP_LOCAL_OUT 3
+/* Packets about to hit the wire. */
+#define NF_IP_POST_ROUTING 4
+#define NF_IP_NUMHOOKS 5
+
+enum nf_ip_hook_priorities {
+ NF_IP_PRI_FIRST = INT_MIN,
+ NF_IP_PRI_RAW_BEFORE_DEFRAG = -450,
+ NF_IP_PRI_CONNTRACK_DEFRAG = -400,
+ NF_IP_PRI_RAW = -300,
+ NF_IP_PRI_SELINUX_FIRST = -225,
+ NF_IP_PRI_CONNTRACK = -200,
+ NF_IP_PRI_MANGLE = -150,
+ NF_IP_PRI_NAT_DST = -100,
+ NF_IP_PRI_FILTER = 0,
+ NF_IP_PRI_SECURITY = 50,
+ NF_IP_PRI_NAT_SRC = 100,
+ NF_IP_PRI_SELINUX_LAST = 225,
+ NF_IP_PRI_CONNTRACK_HELPER = 300,
+ NF_IP_PRI_CONNTRACK_CONFIRM = INT_MAX,
+ NF_IP_PRI_LAST = INT_MAX,
+};
+
+/* Arguments for setsockopt SOL_IP: */
+/* 2.0 firewalling went from 64 through 71 (and +256, +512, etc). */
+/* 2.2 firewalling (+ masq) went from 64 through 76 */
+/* 2.4 firewalling went 64 through 67. */
+#define SO_ORIGINAL_DST 80
+
+
+#endif /* __LINUX_IP_NETFILTER_H */
diff --git a/include/uapi/linux/netfilter_ipv4/ip_tables.h b/include/uapi/linux/netfilter_ipv4/ip_tables.h
new file mode 100644
index 0000000..52024cb
--- /dev/null
+++ b/include/uapi/linux/netfilter_ipv4/ip_tables.h
@@ -0,0 +1,229 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 25-Jul-1998 Major changes to allow for ip chain table
+ *
+ * 3-Jan-2000 Named tables to allow packet selection for different uses.
+ */
+
+/*
+ * Format of an IP firewall descriptor
+ *
+ * src, dst, src_mask, dst_mask are always stored in network byte order.
+ * flags are stored in host byte order (of course).
+ * Port numbers are stored in HOST byte order.
+ */
+
+#ifndef _IPTABLES_H
+#define _IPTABLES_H
+
+#include <linux/types.h>
+
+#include <linux/if.h>
+#include <linux/netfilter_ipv4.h>
+
+#include <linux/netfilter/x_tables.h>
+
+#define IPT_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN
+#define IPT_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN
+#define ipt_match xt_match
+#define ipt_target xt_target
+#define ipt_table xt_table
+#define ipt_get_revision xt_get_revision
+#define ipt_entry_match xt_entry_match
+#define ipt_entry_target xt_entry_target
+#define ipt_standard_target xt_standard_target
+#define ipt_error_target xt_error_target
+#define ipt_counters xt_counters
+#define IPT_CONTINUE XT_CONTINUE
+#define IPT_RETURN XT_RETURN
+
+/* This group is older than old (iptables < v1.4.0-rc1~89) */
+#include <linux/netfilter/xt_tcpudp.h>
+#define ipt_udp xt_udp
+#define ipt_tcp xt_tcp
+#define IPT_TCP_INV_SRCPT XT_TCP_INV_SRCPT
+#define IPT_TCP_INV_DSTPT XT_TCP_INV_DSTPT
+#define IPT_TCP_INV_FLAGS XT_TCP_INV_FLAGS
+#define IPT_TCP_INV_OPTION XT_TCP_INV_OPTION
+#define IPT_TCP_INV_MASK XT_TCP_INV_MASK
+#define IPT_UDP_INV_SRCPT XT_UDP_INV_SRCPT
+#define IPT_UDP_INV_DSTPT XT_UDP_INV_DSTPT
+#define IPT_UDP_INV_MASK XT_UDP_INV_MASK
+
+/* The argument to IPT_SO_ADD_COUNTERS. */
+#define ipt_counters_info xt_counters_info
+/* Standard return verdict, or do jump. */
+#define IPT_STANDARD_TARGET XT_STANDARD_TARGET
+/* Error verdict. */
+#define IPT_ERROR_TARGET XT_ERROR_TARGET
+
+/* fn returns 0 to continue iteration */
+#define IPT_MATCH_ITERATE(e, fn, args...) \
+ XT_MATCH_ITERATE(struct ipt_entry, e, fn, ## args)
+
+/* fn returns 0 to continue iteration */
+#define IPT_ENTRY_ITERATE(entries, size, fn, args...) \
+ XT_ENTRY_ITERATE(struct ipt_entry, entries, size, fn, ## args)
+
+/* Yes, Virginia, you have to zero the padding. */
+struct ipt_ip {
+ /* Source and destination IP addr */
+ struct in_addr src, dst;
+ /* Mask for src and dest IP addr */
+ struct in_addr smsk, dmsk;
+ char iniface[IFNAMSIZ], outiface[IFNAMSIZ];
+ unsigned char iniface_mask[IFNAMSIZ], outiface_mask[IFNAMSIZ];
+
+ /* Protocol, 0 = ANY */
+ __u16 proto;
+
+ /* Flags word */
+ __u8 flags;
+ /* Inverse flags */
+ __u8 invflags;
+};
+
+/* Values for "flag" field in struct ipt_ip (general ip structure). */
+#define IPT_F_FRAG 0x01 /* Set if rule is a fragment rule */
+#define IPT_F_GOTO 0x02 /* Set if jump is a goto */
+#define IPT_F_MASK 0x03 /* All possible flag bits mask. */
+
+/* Values for "inv" field in struct ipt_ip. */
+#define IPT_INV_VIA_IN 0x01 /* Invert the sense of IN IFACE. */
+#define IPT_INV_VIA_OUT 0x02 /* Invert the sense of OUT IFACE */
+#define IPT_INV_TOS 0x04 /* Invert the sense of TOS. */
+#define IPT_INV_SRCIP 0x08 /* Invert the sense of SRC IP. */
+#define IPT_INV_DSTIP 0x10 /* Invert the sense of DST OP. */
+#define IPT_INV_FRAG 0x20 /* Invert the sense of FRAG. */
+#define IPT_INV_PROTO XT_INV_PROTO
+#define IPT_INV_MASK 0x7F /* All possible flag bits mask. */
+
+/* This structure defines each of the firewall rules. Consists of 3
+ parts which are 1) general IP header stuff 2) match specific
+ stuff 3) the target to perform if the rule matches */
+struct ipt_entry {
+ struct ipt_ip ip;
+
+ /* Mark with fields that we care about. */
+ unsigned int nfcache;
+
+ /* Size of ipt_entry + matches */
+ __u16 target_offset;
+ /* Size of ipt_entry + matches + target */
+ __u16 next_offset;
+
+ /* Back pointer */
+ unsigned int comefrom;
+
+ /* Packet and byte counters. */
+ struct xt_counters counters;
+
+ /* The matches (if any), then the target. */
+ unsigned char elems[];
+};
+
+/*
+ * New IP firewall options for [gs]etsockopt at the RAW IP level.
+ * Unlike BSD Linux inherits IP options so you don't have to use a raw
+ * socket for this. Instead we check rights in the calls.
+ *
+ * ATTENTION: check linux/in.h before adding new number here.
+ */
+#define IPT_BASE_CTL 64
+
+#define IPT_SO_SET_REPLACE (IPT_BASE_CTL)
+#define IPT_SO_SET_ADD_COUNTERS (IPT_BASE_CTL + 1)
+#define IPT_SO_SET_MAX IPT_SO_SET_ADD_COUNTERS
+
+#define IPT_SO_GET_INFO (IPT_BASE_CTL)
+#define IPT_SO_GET_ENTRIES (IPT_BASE_CTL + 1)
+#define IPT_SO_GET_REVISION_MATCH (IPT_BASE_CTL + 2)
+#define IPT_SO_GET_REVISION_TARGET (IPT_BASE_CTL + 3)
+#define IPT_SO_GET_MAX IPT_SO_GET_REVISION_TARGET
+
+/* ICMP matching stuff */
+struct ipt_icmp {
+ __u8 type; /* type to match */
+ __u8 code[2]; /* range of code */
+ __u8 invflags; /* Inverse flags */
+};
+
+/* Values for "inv" field for struct ipt_icmp. */
+#define IPT_ICMP_INV 0x01 /* Invert the sense of type/code test */
+
+/* The argument to IPT_SO_GET_INFO */
+struct ipt_getinfo {
+ /* Which table: caller fills this in. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ /* Kernel fills these in. */
+ /* Which hook entry points are valid: bitmask */
+ unsigned int valid_hooks;
+
+ /* Hook entry points: one per netfilter hook. */
+ unsigned int hook_entry[NF_INET_NUMHOOKS];
+
+ /* Underflow points. */
+ unsigned int underflow[NF_INET_NUMHOOKS];
+
+ /* Number of entries */
+ unsigned int num_entries;
+
+ /* Size of entries. */
+ unsigned int size;
+};
+
+/* The argument to IPT_SO_SET_REPLACE. */
+struct ipt_replace {
+ /* Which table. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ /* Which hook entry points are valid: bitmask. You can't
+ change this. */
+ unsigned int valid_hooks;
+
+ /* Number of entries */
+ unsigned int num_entries;
+
+ /* Total size of new entries */
+ unsigned int size;
+
+ /* Hook entry points. */
+ unsigned int hook_entry[NF_INET_NUMHOOKS];
+
+ /* Underflow points. */
+ unsigned int underflow[NF_INET_NUMHOOKS];
+
+ /* Information about old entries: */
+ /* Number of counters (must be equal to current number of entries). */
+ unsigned int num_counters;
+ /* The old entries' counters. */
+ struct xt_counters *counters;
+
+ /* The entries (hang off end: not really an array). */
+ struct ipt_entry entries[];
+};
+
+/* The argument to IPT_SO_GET_ENTRIES. */
+struct ipt_get_entries {
+ /* Which table: user fills this in. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ /* User fills this in: total entry size. */
+ unsigned int size;
+
+ /* The entries. */
+ struct ipt_entry entrytable[];
+};
+
+/* Helper functions */
+static __inline__ struct xt_entry_target *
+ipt_get_target(struct ipt_entry *e)
+{
+ return (struct xt_entry_target *)((char *)e + e->target_offset);
+}
+
+/*
+ * Main firewall chains definitions and global var's definitions.
+ */
+#endif /* _IPTABLES_H */
diff --git a/include/uapi/linux/netfilter_ipv6.h b/include/uapi/linux/netfilter_ipv6.h
new file mode 100644
index 0000000..eedf7a2
--- /dev/null
+++ b/include/uapi/linux/netfilter_ipv6.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* IPv6-specific defines for netfilter.
+ * (C)1998 Rusty Russell -- This code is GPL.
+ * (C)1999 David Jeffery
+ * this header was blatantly ripped from netfilter_ipv4.h
+ * it's amazing what adding a bunch of 6s can do =8^)
+ */
+#ifndef __LINUX_IP6_NETFILTER_H
+#define __LINUX_IP6_NETFILTER_H
+
+
+#include <linux/netfilter.h>
+
+/* only for userspace compatibility */
+
+#include <limits.h> /* for INT_MIN, INT_MAX */
+
+/* IP6 Hooks */
+/* After promisc drops, checksum checks. */
+#define NF_IP6_PRE_ROUTING 0
+/* If the packet is destined for this box. */
+#define NF_IP6_LOCAL_IN 1
+/* If the packet is destined for another interface. */
+#define NF_IP6_FORWARD 2
+/* Packets coming from a local process. */
+#define NF_IP6_LOCAL_OUT 3
+/* Packets about to hit the wire. */
+#define NF_IP6_POST_ROUTING 4
+#define NF_IP6_NUMHOOKS 5
+
+
+enum nf_ip6_hook_priorities {
+ NF_IP6_PRI_FIRST = INT_MIN,
+ NF_IP6_PRI_RAW_BEFORE_DEFRAG = -450,
+ NF_IP6_PRI_CONNTRACK_DEFRAG = -400,
+ NF_IP6_PRI_RAW = -300,
+ NF_IP6_PRI_SELINUX_FIRST = -225,
+ NF_IP6_PRI_CONNTRACK = -200,
+ NF_IP6_PRI_MANGLE = -150,
+ NF_IP6_PRI_NAT_DST = -100,
+ NF_IP6_PRI_FILTER = 0,
+ NF_IP6_PRI_SECURITY = 50,
+ NF_IP6_PRI_NAT_SRC = 100,
+ NF_IP6_PRI_SELINUX_LAST = 225,
+ NF_IP6_PRI_CONNTRACK_HELPER = 300,
+ NF_IP6_PRI_LAST = INT_MAX,
+};
+
+
+#endif /* __LINUX_IP6_NETFILTER_H */
diff --git a/include/uapi/linux/netfilter_ipv6/ip6_tables.h b/include/uapi/linux/netfilter_ipv6/ip6_tables.h
new file mode 100644
index 0000000..68109ec
--- /dev/null
+++ b/include/uapi/linux/netfilter_ipv6/ip6_tables.h
@@ -0,0 +1,270 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * 25-Jul-1998 Major changes to allow for ip chain table
+ *
+ * 3-Jan-2000 Named tables to allow packet selection for different uses.
+ */
+
+/*
+ * Format of an IP6 firewall descriptor
+ *
+ * src, dst, src_mask, dst_mask are always stored in network byte order.
+ * flags are stored in host byte order (of course).
+ * Port numbers are stored in HOST byte order.
+ */
+
+#ifndef _IP6_TABLES_H
+#define _IP6_TABLES_H
+
+#include <linux/types.h>
+
+#include <linux/if.h>
+#include <linux/netfilter_ipv6.h>
+
+#include <linux/netfilter/x_tables.h>
+
+#define IP6T_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN
+#define IP6T_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN
+#define ip6t_match xt_match
+#define ip6t_target xt_target
+#define ip6t_table xt_table
+#define ip6t_get_revision xt_get_revision
+#define ip6t_entry_match xt_entry_match
+#define ip6t_entry_target xt_entry_target
+#define ip6t_standard_target xt_standard_target
+#define ip6t_error_target xt_error_target
+#define ip6t_counters xt_counters
+#define IP6T_CONTINUE XT_CONTINUE
+#define IP6T_RETURN XT_RETURN
+
+/* Pre-iptables-1.4.0 */
+#include <linux/netfilter/xt_tcpudp.h>
+#define ip6t_tcp xt_tcp
+#define ip6t_udp xt_udp
+#define IP6T_TCP_INV_SRCPT XT_TCP_INV_SRCPT
+#define IP6T_TCP_INV_DSTPT XT_TCP_INV_DSTPT
+#define IP6T_TCP_INV_FLAGS XT_TCP_INV_FLAGS
+#define IP6T_TCP_INV_OPTION XT_TCP_INV_OPTION
+#define IP6T_TCP_INV_MASK XT_TCP_INV_MASK
+#define IP6T_UDP_INV_SRCPT XT_UDP_INV_SRCPT
+#define IP6T_UDP_INV_DSTPT XT_UDP_INV_DSTPT
+#define IP6T_UDP_INV_MASK XT_UDP_INV_MASK
+
+#define ip6t_counters_info xt_counters_info
+#define IP6T_STANDARD_TARGET XT_STANDARD_TARGET
+#define IP6T_ERROR_TARGET XT_ERROR_TARGET
+#define IP6T_MATCH_ITERATE(e, fn, args...) \
+ XT_MATCH_ITERATE(struct ip6t_entry, e, fn, ## args)
+#define IP6T_ENTRY_ITERATE(entries, size, fn, args...) \
+ XT_ENTRY_ITERATE(struct ip6t_entry, entries, size, fn, ## args)
+
+/* Yes, Virginia, you have to zero the padding. */
+struct ip6t_ip6 {
+ /* Source and destination IP6 addr */
+ struct in6_addr src, dst;
+ /* Mask for src and dest IP6 addr */
+ struct in6_addr smsk, dmsk;
+ char iniface[IFNAMSIZ], outiface[IFNAMSIZ];
+ unsigned char iniface_mask[IFNAMSIZ], outiface_mask[IFNAMSIZ];
+
+ /* Upper protocol number
+ * - The allowed value is 0 (any) or protocol number of last parsable
+ * header, which is 50 (ESP), 59 (No Next Header), 135 (MH), or
+ * the non IPv6 extension headers.
+ * - The protocol numbers of IPv6 extension headers except of ESP and
+ * MH do not match any packets.
+ * - You also need to set IP6T_FLAGS_PROTO to "flags" to check protocol.
+ */
+ __u16 proto;
+ /* TOS to match iff flags & IP6T_F_TOS */
+ __u8 tos;
+
+ /* Flags word */
+ __u8 flags;
+ /* Inverse flags */
+ __u8 invflags;
+};
+
+/* Values for "flag" field in struct ip6t_ip6 (general ip6 structure). */
+#define IP6T_F_PROTO 0x01 /* Set if rule cares about upper
+ protocols */
+#define IP6T_F_TOS 0x02 /* Match the TOS. */
+#define IP6T_F_GOTO 0x04 /* Set if jump is a goto */
+#define IP6T_F_MASK 0x07 /* All possible flag bits mask. */
+
+/* Values for "inv" field in struct ip6t_ip6. */
+#define IP6T_INV_VIA_IN 0x01 /* Invert the sense of IN IFACE. */
+#define IP6T_INV_VIA_OUT 0x02 /* Invert the sense of OUT IFACE */
+#define IP6T_INV_TOS 0x04 /* Invert the sense of TOS. */
+#define IP6T_INV_SRCIP 0x08 /* Invert the sense of SRC IP. */
+#define IP6T_INV_DSTIP 0x10 /* Invert the sense of DST OP. */
+#define IP6T_INV_FRAG 0x20 /* Invert the sense of FRAG. */
+#define IP6T_INV_PROTO XT_INV_PROTO
+#define IP6T_INV_MASK 0x7F /* All possible flag bits mask. */
+
+/* This structure defines each of the firewall rules. Consists of 3
+ parts which are 1) general IP header stuff 2) match specific
+ stuff 3) the target to perform if the rule matches */
+struct ip6t_entry {
+ struct ip6t_ip6 ipv6;
+
+ /* Mark with fields that we care about. */
+ unsigned int nfcache;
+
+ /* Size of ipt_entry + matches */
+ __u16 target_offset;
+ /* Size of ipt_entry + matches + target */
+ __u16 next_offset;
+
+ /* Back pointer */
+ unsigned int comefrom;
+
+ /* Packet and byte counters. */
+ struct xt_counters counters;
+
+ /* The matches (if any), then the target. */
+ unsigned char elems[0];
+};
+
+/* Standard entry */
+struct ip6t_standard {
+ struct ip6t_entry entry;
+ struct xt_standard_target target;
+};
+
+struct ip6t_error {
+ struct ip6t_entry entry;
+ struct xt_error_target target;
+};
+
+#define IP6T_ENTRY_INIT(__size) \
+{ \
+ .target_offset = sizeof(struct ip6t_entry), \
+ .next_offset = (__size), \
+}
+
+#define IP6T_STANDARD_INIT(__verdict) \
+{ \
+ .entry = IP6T_ENTRY_INIT(sizeof(struct ip6t_standard)), \
+ .target = XT_TARGET_INIT(XT_STANDARD_TARGET, \
+ sizeof(struct xt_standard_target)), \
+ .target.verdict = -(__verdict) - 1, \
+}
+
+#define IP6T_ERROR_INIT \
+{ \
+ .entry = IP6T_ENTRY_INIT(sizeof(struct ip6t_error)), \
+ .target = XT_TARGET_INIT(XT_ERROR_TARGET, \
+ sizeof(struct xt_error_target)), \
+ .target.errorname = "ERROR", \
+}
+
+/*
+ * New IP firewall options for [gs]etsockopt at the RAW IP level.
+ * Unlike BSD Linux inherits IP options so you don't have to use
+ * a raw socket for this. Instead we check rights in the calls.
+ *
+ * ATTENTION: check linux/in6.h before adding new number here.
+ */
+#define IP6T_BASE_CTL 64
+
+#define IP6T_SO_SET_REPLACE (IP6T_BASE_CTL)
+#define IP6T_SO_SET_ADD_COUNTERS (IP6T_BASE_CTL + 1)
+#define IP6T_SO_SET_MAX IP6T_SO_SET_ADD_COUNTERS
+
+#define IP6T_SO_GET_INFO (IP6T_BASE_CTL)
+#define IP6T_SO_GET_ENTRIES (IP6T_BASE_CTL + 1)
+#define IP6T_SO_GET_REVISION_MATCH (IP6T_BASE_CTL + 4)
+#define IP6T_SO_GET_REVISION_TARGET (IP6T_BASE_CTL + 5)
+#define IP6T_SO_GET_MAX IP6T_SO_GET_REVISION_TARGET
+
+/* obtain original address if REDIRECT'd connection */
+#define IP6T_SO_ORIGINAL_DST 80
+
+/* ICMP matching stuff */
+struct ip6t_icmp {
+ __u8 type; /* type to match */
+ __u8 code[2]; /* range of code */
+ __u8 invflags; /* Inverse flags */
+};
+
+/* Values for "inv" field for struct ipt_icmp. */
+#define IP6T_ICMP_INV 0x01 /* Invert the sense of type/code test */
+
+/* The argument to IP6T_SO_GET_INFO */
+struct ip6t_getinfo {
+ /* Which table: caller fills this in. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ /* Kernel fills these in. */
+ /* Which hook entry points are valid: bitmask */
+ unsigned int valid_hooks;
+
+ /* Hook entry points: one per netfilter hook. */
+ unsigned int hook_entry[NF_INET_NUMHOOKS];
+
+ /* Underflow points. */
+ unsigned int underflow[NF_INET_NUMHOOKS];
+
+ /* Number of entries */
+ unsigned int num_entries;
+
+ /* Size of entries. */
+ unsigned int size;
+};
+
+/* The argument to IP6T_SO_SET_REPLACE. */
+struct ip6t_replace {
+ /* Which table. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ /* Which hook entry points are valid: bitmask. You can't
+ change this. */
+ unsigned int valid_hooks;
+
+ /* Number of entries */
+ unsigned int num_entries;
+
+ /* Total size of new entries */
+ unsigned int size;
+
+ /* Hook entry points. */
+ unsigned int hook_entry[NF_INET_NUMHOOKS];
+
+ /* Underflow points. */
+ unsigned int underflow[NF_INET_NUMHOOKS];
+
+ /* Information about old entries: */
+ /* Number of counters (must be equal to current number of entries). */
+ unsigned int num_counters;
+ /* The old entries' counters. */
+ struct xt_counters *counters;
+
+ /* The entries (hang off end: not really an array). */
+ struct ip6t_entry entries[];
+};
+
+/* The argument to IP6T_SO_GET_ENTRIES. */
+struct ip6t_get_entries {
+ /* Which table: user fills this in. */
+ char name[XT_TABLE_MAXNAMELEN];
+
+ /* User fills this in: total entry size. */
+ unsigned int size;
+
+ /* The entries. */
+ struct ip6t_entry entrytable[];
+};
+
+/* Helper functions */
+static __inline__ struct xt_entry_target *
+ip6t_get_target(struct ip6t_entry *e)
+{
+ return (struct xt_entry_target *)((char *)e + e->target_offset);
+}
+
+/*
+ * Main firewall chains definitions and global var's definitions.
+ */
+
+#endif /* _IP6_TABLES_H */
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
new file mode 100644
index 0000000..ff64eb1
--- /dev/null
+++ b/include/uapi/linux/netlink.h
@@ -0,0 +1,379 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_NETLINK_H
+#define __LINUX_NETLINK_H
+
+#include <linux/const.h>
+#include <linux/socket.h> /* for __kernel_sa_family_t */
+#include <linux/types.h>
+
+#define NETLINK_ROUTE 0 /* Routing/device hook */
+#define NETLINK_UNUSED 1 /* Unused number */
+#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */
+#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */
+#define NETLINK_SOCK_DIAG 4 /* socket monitoring */
+#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */
+#define NETLINK_XFRM 6 /* ipsec */
+#define NETLINK_SELINUX 7 /* SELinux event notifications */
+#define NETLINK_ISCSI 8 /* Open-iSCSI */
+#define NETLINK_AUDIT 9 /* auditing */
+#define NETLINK_FIB_LOOKUP 10
+#define NETLINK_CONNECTOR 11
+#define NETLINK_NETFILTER 12 /* netfilter subsystem */
+#define NETLINK_IP6_FW 13
+#define NETLINK_DNRTMSG 14 /* DECnet routing messages (obsolete) */
+#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */
+#define NETLINK_GENERIC 16
+/* leave room for NETLINK_DM (DM Events) */
+#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */
+#define NETLINK_ECRYPTFS 19
+#define NETLINK_RDMA 20
+#define NETLINK_CRYPTO 21 /* Crypto layer */
+#define NETLINK_SMC 22 /* SMC monitoring */
+
+#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG
+
+#define MAX_LINKS 32
+
+struct sockaddr_nl {
+ __kernel_sa_family_t nl_family; /* AF_NETLINK */
+ unsigned short nl_pad; /* zero */
+ __u32 nl_pid; /* port ID */
+ __u32 nl_groups; /* multicast groups mask */
+};
+
+/**
+ * struct nlmsghdr - fixed format metadata header of Netlink messages
+ * @nlmsg_len: Length of message including header
+ * @nlmsg_type: Message content type
+ * @nlmsg_flags: Additional flags
+ * @nlmsg_seq: Sequence number
+ * @nlmsg_pid: Sending process port ID
+ */
+struct nlmsghdr {
+ __u32 nlmsg_len;
+ __u16 nlmsg_type;
+ __u16 nlmsg_flags;
+ __u32 nlmsg_seq;
+ __u32 nlmsg_pid;
+};
+
+/* Flags values */
+
+#define NLM_F_REQUEST 0x01 /* It is request message. */
+#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */
+#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */
+#define NLM_F_ECHO 0x08 /* Receive resulting notifications */
+#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */
+#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */
+
+/* Modifiers to GET request */
+#define NLM_F_ROOT 0x100 /* specify tree root */
+#define NLM_F_MATCH 0x200 /* return all matching */
+#define NLM_F_ATOMIC 0x400 /* atomic GET */
+#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH)
+
+/* Modifiers to NEW request */
+#define NLM_F_REPLACE 0x100 /* Override existing */
+#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */
+#define NLM_F_CREATE 0x400 /* Create, if it does not exist */
+#define NLM_F_APPEND 0x800 /* Add to end of list */
+
+/* Modifiers to DELETE request */
+#define NLM_F_NONREC 0x100 /* Do not delete recursively */
+#define NLM_F_BULK 0x200 /* Delete multiple objects */
+
+/* Flags for ACK message */
+#define NLM_F_CAPPED 0x100 /* request was capped */
+#define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */
+
+/*
+ 4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL
+ 4.4BSD CHANGE NLM_F_REPLACE
+
+ True CHANGE NLM_F_CREATE|NLM_F_REPLACE
+ Append NLM_F_CREATE
+ Check NLM_F_EXCL
+ */
+
+#define NLMSG_ALIGNTO 4U
+#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) )
+#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
+#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN)
+#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
+#define NLMSG_DATA(nlh) ((void *)(((char *)nlh) + NLMSG_HDRLEN))
+#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
+ (struct nlmsghdr *)(((char *)(nlh)) + \
+ NLMSG_ALIGN((nlh)->nlmsg_len)))
+#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
+ (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
+ (nlh)->nlmsg_len <= (len))
+#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len)))
+
+#define NLMSG_NOOP 0x1 /* Nothing. */
+#define NLMSG_ERROR 0x2 /* Error */
+#define NLMSG_DONE 0x3 /* End of a dump */
+#define NLMSG_OVERRUN 0x4 /* Data lost */
+
+#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */
+
+struct nlmsgerr {
+ int error;
+ struct nlmsghdr msg;
+ /*
+ * followed by the message contents unless NETLINK_CAP_ACK was set
+ * or the ACK indicates success (error == 0)
+ * message length is aligned with NLMSG_ALIGN()
+ */
+ /*
+ * followed by TLVs defined in enum nlmsgerr_attrs
+ * if NETLINK_EXT_ACK was set
+ */
+};
+
+/**
+ * enum nlmsgerr_attrs - nlmsgerr attributes
+ * @NLMSGERR_ATTR_UNUSED: unused
+ * @NLMSGERR_ATTR_MSG: error message string (string)
+ * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original
+ * message, counting from the beginning of the header (u32)
+ * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to
+ * be used - in the success case - to identify a created
+ * object or operation or similar (binary)
+ * @NLMSGERR_ATTR_POLICY: policy for a rejected attribute
+ * @NLMSGERR_ATTR_MISS_TYPE: type of a missing required attribute,
+ * %NLMSGERR_ATTR_MISS_NEST will not be present if the attribute was
+ * missing at the message level
+ * @NLMSGERR_ATTR_MISS_NEST: offset of the nest where attribute was missing
+ * @__NLMSGERR_ATTR_MAX: number of attributes
+ * @NLMSGERR_ATTR_MAX: highest attribute number
+ */
+enum nlmsgerr_attrs {
+ NLMSGERR_ATTR_UNUSED,
+ NLMSGERR_ATTR_MSG,
+ NLMSGERR_ATTR_OFFS,
+ NLMSGERR_ATTR_COOKIE,
+ NLMSGERR_ATTR_POLICY,
+ NLMSGERR_ATTR_MISS_TYPE,
+ NLMSGERR_ATTR_MISS_NEST,
+
+ __NLMSGERR_ATTR_MAX,
+ NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
+};
+
+#define NETLINK_ADD_MEMBERSHIP 1
+#define NETLINK_DROP_MEMBERSHIP 2
+#define NETLINK_PKTINFO 3
+#define NETLINK_BROADCAST_ERROR 4
+#define NETLINK_NO_ENOBUFS 5
+#define NETLINK_RX_RING 6
+#define NETLINK_TX_RING 7
+#define NETLINK_LISTEN_ALL_NSID 8
+#define NETLINK_LIST_MEMBERSHIPS 9
+#define NETLINK_CAP_ACK 10
+#define NETLINK_EXT_ACK 11
+#define NETLINK_GET_STRICT_CHK 12
+
+struct nl_pktinfo {
+ __u32 group;
+};
+
+struct nl_mmap_req {
+ unsigned int nm_block_size;
+ unsigned int nm_block_nr;
+ unsigned int nm_frame_size;
+ unsigned int nm_frame_nr;
+};
+
+struct nl_mmap_hdr {
+ unsigned int nm_status;
+ unsigned int nm_len;
+ __u32 nm_group;
+ /* credentials */
+ __u32 nm_pid;
+ __u32 nm_uid;
+ __u32 nm_gid;
+};
+
+enum nl_mmap_status {
+ NL_MMAP_STATUS_UNUSED,
+ NL_MMAP_STATUS_RESERVED,
+ NL_MMAP_STATUS_VALID,
+ NL_MMAP_STATUS_COPY,
+ NL_MMAP_STATUS_SKIP,
+};
+
+#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO
+#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
+#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
+
+#define NET_MAJOR 36 /* Major 36 is reserved for networking */
+
+enum {
+ NETLINK_UNCONNECTED = 0,
+ NETLINK_CONNECTED,
+};
+
+/*
+ * <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)-->
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ * | Header | Pad | Payload | Pad |
+ * | (struct nlattr) | ing | | ing |
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ * <-------------- nlattr->nla_len -------------->
+ */
+
+struct nlattr {
+ __u16 nla_len;
+ __u16 nla_type;
+};
+
+/*
+ * nla_type (16 bits)
+ * +---+---+-------------------------------+
+ * | N | O | Attribute Type |
+ * +---+---+-------------------------------+
+ * N := Carries nested attributes
+ * O := Payload stored in network byte order
+ *
+ * Note: The N and O flag are mutually exclusive.
+ */
+#define NLA_F_NESTED (1 << 15)
+#define NLA_F_NET_BYTEORDER (1 << 14)
+#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER)
+
+#define NLA_ALIGNTO 4
+#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1))
+#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr)))
+
+/* Generic 32 bitflags attribute content sent to the kernel.
+ *
+ * The value is a bitmap that defines the values being set
+ * The selector is a bitmask that defines which value is legit
+ *
+ * Examples:
+ * value = 0x0, and selector = 0x1
+ * implies we are selecting bit 1 and we want to set its value to 0.
+ *
+ * value = 0x2, and selector = 0x2
+ * implies we are selecting bit 2 and we want to set its value to 1.
+ *
+ */
+struct nla_bitfield32 {
+ __u32 value;
+ __u32 selector;
+};
+
+/*
+ * policy descriptions - it's specific to each family how this is used
+ * Normally, it should be retrieved via a dump inside another attribute
+ * specifying where it applies.
+ */
+
+/**
+ * enum netlink_attribute_type - type of an attribute
+ * @NL_ATTR_TYPE_INVALID: unused
+ * @NL_ATTR_TYPE_FLAG: flag attribute (present/not present)
+ * @NL_ATTR_TYPE_U8: 8-bit unsigned attribute
+ * @NL_ATTR_TYPE_U16: 16-bit unsigned attribute
+ * @NL_ATTR_TYPE_U32: 32-bit unsigned attribute
+ * @NL_ATTR_TYPE_U64: 64-bit unsigned attribute
+ * @NL_ATTR_TYPE_S8: 8-bit signed attribute
+ * @NL_ATTR_TYPE_S16: 16-bit signed attribute
+ * @NL_ATTR_TYPE_S32: 32-bit signed attribute
+ * @NL_ATTR_TYPE_S64: 64-bit signed attribute
+ * @NL_ATTR_TYPE_BINARY: binary data, min/max length may be specified
+ * @NL_ATTR_TYPE_STRING: string, min/max length may be specified
+ * @NL_ATTR_TYPE_NUL_STRING: NUL-terminated string,
+ * min/max length may be specified
+ * @NL_ATTR_TYPE_NESTED: nested, i.e. the content of this attribute
+ * consists of sub-attributes. The nested policy and maxtype
+ * inside may be specified.
+ * @NL_ATTR_TYPE_NESTED_ARRAY: nested array, i.e. the content of this
+ * attribute contains sub-attributes whose type is irrelevant
+ * (just used to separate the array entries) and each such array
+ * entry has attributes again, the policy for those inner ones
+ * and the corresponding maxtype may be specified.
+ * @NL_ATTR_TYPE_BITFIELD32: &struct nla_bitfield32 attribute
+ * @NL_ATTR_TYPE_SINT: 32-bit or 64-bit signed attribute, aligned to 4B
+ * @NL_ATTR_TYPE_UINT: 32-bit or 64-bit unsigned attribute, aligned to 4B
+ */
+enum netlink_attribute_type {
+ NL_ATTR_TYPE_INVALID,
+
+ NL_ATTR_TYPE_FLAG,
+
+ NL_ATTR_TYPE_U8,
+ NL_ATTR_TYPE_U16,
+ NL_ATTR_TYPE_U32,
+ NL_ATTR_TYPE_U64,
+
+ NL_ATTR_TYPE_S8,
+ NL_ATTR_TYPE_S16,
+ NL_ATTR_TYPE_S32,
+ NL_ATTR_TYPE_S64,
+
+ NL_ATTR_TYPE_BINARY,
+ NL_ATTR_TYPE_STRING,
+ NL_ATTR_TYPE_NUL_STRING,
+
+ NL_ATTR_TYPE_NESTED,
+ NL_ATTR_TYPE_NESTED_ARRAY,
+
+ NL_ATTR_TYPE_BITFIELD32,
+
+ NL_ATTR_TYPE_SINT,
+ NL_ATTR_TYPE_UINT,
+};
+
+/**
+ * enum netlink_policy_type_attr - policy type attributes
+ * @NL_POLICY_TYPE_ATTR_UNSPEC: unused
+ * @NL_POLICY_TYPE_ATTR_TYPE: type of the attribute,
+ * &enum netlink_attribute_type (U32)
+ * @NL_POLICY_TYPE_ATTR_MIN_VALUE_S: minimum value for signed
+ * integers (S64)
+ * @NL_POLICY_TYPE_ATTR_MAX_VALUE_S: maximum value for signed
+ * integers (S64)
+ * @NL_POLICY_TYPE_ATTR_MIN_VALUE_U: minimum value for unsigned
+ * integers (U64)
+ * @NL_POLICY_TYPE_ATTR_MAX_VALUE_U: maximum value for unsigned
+ * integers (U64)
+ * @NL_POLICY_TYPE_ATTR_MIN_LENGTH: minimum length for binary
+ * attributes, no minimum if not given (U32)
+ * @NL_POLICY_TYPE_ATTR_MAX_LENGTH: maximum length for binary
+ * attributes, no maximum if not given (U32)
+ * @NL_POLICY_TYPE_ATTR_POLICY_IDX: sub policy for nested and
+ * nested array types (U32)
+ * @NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE: maximum sub policy
+ * attribute for nested and nested array types, this can
+ * in theory be < the size of the policy pointed to by
+ * the index, if limited inside the nesting (U32)
+ * @NL_POLICY_TYPE_ATTR_BITFIELD32_MASK: valid mask for the
+ * bitfield32 type (U32)
+ * @NL_POLICY_TYPE_ATTR_MASK: mask of valid bits for unsigned integers (U64)
+ * @NL_POLICY_TYPE_ATTR_PAD: pad attribute for 64-bit alignment
+ *
+ * @__NL_POLICY_TYPE_ATTR_MAX: number of attributes
+ * @NL_POLICY_TYPE_ATTR_MAX: highest attribute number
+ */
+enum netlink_policy_type_attr {
+ NL_POLICY_TYPE_ATTR_UNSPEC,
+ NL_POLICY_TYPE_ATTR_TYPE,
+ NL_POLICY_TYPE_ATTR_MIN_VALUE_S,
+ NL_POLICY_TYPE_ATTR_MAX_VALUE_S,
+ NL_POLICY_TYPE_ATTR_MIN_VALUE_U,
+ NL_POLICY_TYPE_ATTR_MAX_VALUE_U,
+ NL_POLICY_TYPE_ATTR_MIN_LENGTH,
+ NL_POLICY_TYPE_ATTR_MAX_LENGTH,
+ NL_POLICY_TYPE_ATTR_POLICY_IDX,
+ NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE,
+ NL_POLICY_TYPE_ATTR_BITFIELD32_MASK,
+ NL_POLICY_TYPE_ATTR_PAD,
+ NL_POLICY_TYPE_ATTR_MASK,
+
+ /* keep last */
+ __NL_POLICY_TYPE_ATTR_MAX,
+ NL_POLICY_TYPE_ATTR_MAX = __NL_POLICY_TYPE_ATTR_MAX - 1
+};
+
+#endif /* __LINUX_NETLINK_H */
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
new file mode 100644
index 0000000..4cd0657
--- /dev/null
+++ b/include/uapi/linux/netlink_diag.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __NETLINK_DIAG_H__
+#define __NETLINK_DIAG_H__
+
+#include <linux/types.h>
+
+struct netlink_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u16 pad;
+ __u32 ndiag_ino;
+ __u32 ndiag_show;
+ __u32 ndiag_cookie[2];
+};
+
+struct netlink_diag_msg {
+ __u8 ndiag_family;
+ __u8 ndiag_type;
+ __u8 ndiag_protocol;
+ __u8 ndiag_state;
+
+ __u32 ndiag_portid;
+ __u32 ndiag_dst_portid;
+ __u32 ndiag_dst_group;
+ __u32 ndiag_ino;
+ __u32 ndiag_cookie[2];
+};
+
+struct netlink_diag_ring {
+ __u32 ndr_block_size;
+ __u32 ndr_block_nr;
+ __u32 ndr_frame_size;
+ __u32 ndr_frame_nr;
+};
+
+enum {
+ /* NETLINK_DIAG_NONE, standard nl API requires this attribute! */
+ NETLINK_DIAG_MEMINFO,
+ NETLINK_DIAG_GROUPS,
+ NETLINK_DIAG_RX_RING,
+ NETLINK_DIAG_TX_RING,
+ NETLINK_DIAG_FLAGS,
+
+ __NETLINK_DIAG_MAX,
+};
+
+#define NETLINK_DIAG_MAX (__NETLINK_DIAG_MAX - 1)
+
+#define NDIAG_PROTO_ALL ((__u8) ~0)
+
+#define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */
+#define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */
+/* deprecated since 4.6 */
+#define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */
+#define NDIAG_SHOW_FLAGS 0x00000008 /* show flags of a netlink socket */
+
+/* flags */
+#define NDIAG_FLAG_CB_RUNNING 0x00000001
+#define NDIAG_FLAG_PKTINFO 0x00000002
+#define NDIAG_FLAG_BROADCAST_ERROR 0x00000004
+#define NDIAG_FLAG_NO_ENOBUFS 0x00000008
+#define NDIAG_FLAG_LISTEN_ALL_NSID 0x00000010
+#define NDIAG_FLAG_CAP_ACK 0x00000020
+
+#endif
diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h
new file mode 100644
index 0000000..37b14b4
--- /dev/null
+++ b/include/uapi/linux/nexthop.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_NEXTHOP_H
+#define _LINUX_NEXTHOP_H
+
+#include <linux/types.h>
+
+struct nhmsg {
+ unsigned char nh_family;
+ unsigned char nh_scope; /* return only */
+ unsigned char nh_protocol; /* Routing protocol that installed nh */
+ unsigned char resvd;
+ unsigned int nh_flags; /* RTNH_F flags */
+};
+
+/* entry in a nexthop group */
+struct nexthop_grp {
+ __u32 id; /* nexthop id - must exist */
+ __u8 weight; /* weight of this nexthop */
+ __u8 resvd1;
+ __u16 resvd2;
+};
+
+enum {
+ NEXTHOP_GRP_TYPE_MPATH, /* hash-threshold nexthop group
+ * default type if not specified
+ */
+ NEXTHOP_GRP_TYPE_RES, /* resilient nexthop group */
+ __NEXTHOP_GRP_TYPE_MAX,
+};
+
+#define NEXTHOP_GRP_TYPE_MAX (__NEXTHOP_GRP_TYPE_MAX - 1)
+
+enum {
+ NHA_UNSPEC,
+ NHA_ID, /* u32; id for nexthop. id == 0 means auto-assign */
+
+ NHA_GROUP, /* array of nexthop_grp */
+ NHA_GROUP_TYPE, /* u16 one of NEXTHOP_GRP_TYPE */
+ /* if NHA_GROUP attribute is added, no other attributes can be set */
+
+ NHA_BLACKHOLE, /* flag; nexthop used to blackhole packets */
+ /* if NHA_BLACKHOLE is added, OIF, GATEWAY, ENCAP can not be set */
+
+ NHA_OIF, /* u32; nexthop device */
+ NHA_GATEWAY, /* be32 (IPv4) or in6_addr (IPv6) gw address */
+ NHA_ENCAP_TYPE, /* u16; lwt encap type */
+ NHA_ENCAP, /* lwt encap data */
+
+ /* NHA_OIF can be appended to dump request to return only
+ * nexthops using given device
+ */
+ NHA_GROUPS, /* flag; only return nexthop groups in dump */
+ NHA_MASTER, /* u32; only return nexthops with given master dev */
+
+ NHA_FDB, /* flag; nexthop belongs to a bridge fdb */
+ /* if NHA_FDB is added, OIF, BLACKHOLE, ENCAP cannot be set */
+
+ /* nested; resilient nexthop group attributes */
+ NHA_RES_GROUP,
+ /* nested; nexthop bucket attributes */
+ NHA_RES_BUCKET,
+
+ __NHA_MAX,
+};
+
+#define NHA_MAX (__NHA_MAX - 1)
+
+enum {
+ NHA_RES_GROUP_UNSPEC,
+ /* Pad attribute for 64-bit alignment. */
+ NHA_RES_GROUP_PAD = NHA_RES_GROUP_UNSPEC,
+
+ /* u16; number of nexthop buckets in a resilient nexthop group */
+ NHA_RES_GROUP_BUCKETS,
+ /* clock_t as u32; nexthop bucket idle timer (per-group) */
+ NHA_RES_GROUP_IDLE_TIMER,
+ /* clock_t as u32; nexthop unbalanced timer */
+ NHA_RES_GROUP_UNBALANCED_TIMER,
+ /* clock_t as u64; nexthop unbalanced time */
+ NHA_RES_GROUP_UNBALANCED_TIME,
+
+ __NHA_RES_GROUP_MAX,
+};
+
+#define NHA_RES_GROUP_MAX (__NHA_RES_GROUP_MAX - 1)
+
+enum {
+ NHA_RES_BUCKET_UNSPEC,
+ /* Pad attribute for 64-bit alignment. */
+ NHA_RES_BUCKET_PAD = NHA_RES_BUCKET_UNSPEC,
+
+ /* u16; nexthop bucket index */
+ NHA_RES_BUCKET_INDEX,
+ /* clock_t as u64; nexthop bucket idle time */
+ NHA_RES_BUCKET_IDLE_TIME,
+ /* u32; nexthop id assigned to the nexthop bucket */
+ NHA_RES_BUCKET_NH_ID,
+
+ __NHA_RES_BUCKET_MAX,
+};
+
+#define NHA_RES_BUCKET_MAX (__NHA_RES_BUCKET_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h
new file mode 100644
index 0000000..349ddf0
--- /dev/null
+++ b/include/uapi/linux/packet_diag.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __PACKET_DIAG_H__
+#define __PACKET_DIAG_H__
+
+#include <linux/types.h>
+
+struct packet_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u16 pad;
+ __u32 pdiag_ino;
+ __u32 pdiag_show;
+ __u32 pdiag_cookie[2];
+};
+
+#define PACKET_SHOW_INFO 0x00000001 /* Basic packet_sk information */
+#define PACKET_SHOW_MCLIST 0x00000002 /* A set of packet_diag_mclist-s */
+#define PACKET_SHOW_RING_CFG 0x00000004 /* Rings configuration parameters */
+#define PACKET_SHOW_FANOUT 0x00000008
+#define PACKET_SHOW_MEMINFO 0x00000010
+#define PACKET_SHOW_FILTER 0x00000020
+
+struct packet_diag_msg {
+ __u8 pdiag_family;
+ __u8 pdiag_type;
+ __u16 pdiag_num;
+
+ __u32 pdiag_ino;
+ __u32 pdiag_cookie[2];
+};
+
+enum {
+ /* PACKET_DIAG_NONE, standard nl API requires this attribute! */
+ PACKET_DIAG_INFO,
+ PACKET_DIAG_MCLIST,
+ PACKET_DIAG_RX_RING,
+ PACKET_DIAG_TX_RING,
+ PACKET_DIAG_FANOUT,
+ PACKET_DIAG_UID,
+ PACKET_DIAG_MEMINFO,
+ PACKET_DIAG_FILTER,
+
+ __PACKET_DIAG_MAX,
+};
+
+#define PACKET_DIAG_MAX (__PACKET_DIAG_MAX - 1)
+
+struct packet_diag_info {
+ __u32 pdi_index;
+ __u32 pdi_version;
+ __u32 pdi_reserve;
+ __u32 pdi_copy_thresh;
+ __u32 pdi_tstamp;
+ __u32 pdi_flags;
+
+#define PDI_RUNNING 0x1
+#define PDI_AUXDATA 0x2
+#define PDI_ORIGDEV 0x4
+#define PDI_VNETHDR 0x8
+#define PDI_LOSS 0x10
+};
+
+struct packet_diag_mclist {
+ __u32 pdmc_index;
+ __u32 pdmc_count;
+ __u16 pdmc_type;
+ __u16 pdmc_alen;
+ __u8 pdmc_addr[32]; /* MAX_ADDR_LEN */
+};
+
+struct packet_diag_ring {
+ __u32 pdr_block_size;
+ __u32 pdr_block_nr;
+ __u32 pdr_frame_size;
+ __u32 pdr_frame_nr;
+ __u32 pdr_retire_tmo;
+ __u32 pdr_sizeof_priv;
+ __u32 pdr_features;
+};
+
+#endif
diff --git a/include/uapi/linux/param.h b/include/uapi/linux/param.h
new file mode 100644
index 0000000..94e0c57
--- /dev/null
+++ b/include/uapi/linux/param.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_PARAM_H
+#define _LINUX_PARAM_H
+
+#include <asm/param.h>
+
+#endif
diff --git a/include/uapi/linux/pfkeyv2.h b/include/uapi/linux/pfkeyv2.h
new file mode 100644
index 0000000..8abae1f
--- /dev/null
+++ b/include/uapi/linux/pfkeyv2.h
@@ -0,0 +1,386 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* PF_KEY user interface, this is defined by rfc2367 so
+ * do not make arbitrary modifications or else this header
+ * file will not be compliant.
+ */
+
+#ifndef _LINUX_PFKEY2_H
+#define _LINUX_PFKEY2_H
+
+#include <linux/types.h>
+
+#define PF_KEY_V2 2
+#define PFKEYV2_REVISION 199806L
+
+struct sadb_msg {
+ __u8 sadb_msg_version;
+ __u8 sadb_msg_type;
+ __u8 sadb_msg_errno;
+ __u8 sadb_msg_satype;
+ __u16 sadb_msg_len;
+ __u16 sadb_msg_reserved;
+ __u32 sadb_msg_seq;
+ __u32 sadb_msg_pid;
+} __attribute__((packed));
+/* sizeof(struct sadb_msg) == 16 */
+
+struct sadb_ext {
+ __u16 sadb_ext_len;
+ __u16 sadb_ext_type;
+} __attribute__((packed));
+/* sizeof(struct sadb_ext) == 4 */
+
+struct sadb_sa {
+ __u16 sadb_sa_len;
+ __u16 sadb_sa_exttype;
+ __be32 sadb_sa_spi;
+ __u8 sadb_sa_replay;
+ __u8 sadb_sa_state;
+ __u8 sadb_sa_auth;
+ __u8 sadb_sa_encrypt;
+ __u32 sadb_sa_flags;
+} __attribute__((packed));
+/* sizeof(struct sadb_sa) == 16 */
+
+struct sadb_lifetime {
+ __u16 sadb_lifetime_len;
+ __u16 sadb_lifetime_exttype;
+ __u32 sadb_lifetime_allocations;
+ __u64 sadb_lifetime_bytes;
+ __u64 sadb_lifetime_addtime;
+ __u64 sadb_lifetime_usetime;
+} __attribute__((packed));
+/* sizeof(struct sadb_lifetime) == 32 */
+
+struct sadb_address {
+ __u16 sadb_address_len;
+ __u16 sadb_address_exttype;
+ __u8 sadb_address_proto;
+ __u8 sadb_address_prefixlen;
+ __u16 sadb_address_reserved;
+} __attribute__((packed));
+/* sizeof(struct sadb_address) == 8 */
+
+struct sadb_key {
+ __u16 sadb_key_len;
+ __u16 sadb_key_exttype;
+ __u16 sadb_key_bits;
+ __u16 sadb_key_reserved;
+} __attribute__((packed));
+/* sizeof(struct sadb_key) == 8 */
+
+struct sadb_ident {
+ __u16 sadb_ident_len;
+ __u16 sadb_ident_exttype;
+ __u16 sadb_ident_type;
+ __u16 sadb_ident_reserved;
+ __u64 sadb_ident_id;
+} __attribute__((packed));
+/* sizeof(struct sadb_ident) == 16 */
+
+struct sadb_sens {
+ __u16 sadb_sens_len;
+ __u16 sadb_sens_exttype;
+ __u32 sadb_sens_dpd;
+ __u8 sadb_sens_sens_level;
+ __u8 sadb_sens_sens_len;
+ __u8 sadb_sens_integ_level;
+ __u8 sadb_sens_integ_len;
+ __u32 sadb_sens_reserved;
+} __attribute__((packed));
+/* sizeof(struct sadb_sens) == 16 */
+
+/* followed by:
+ __u64 sadb_sens_bitmap[sens_len];
+ __u64 sadb_integ_bitmap[integ_len]; */
+
+struct sadb_prop {
+ __u16 sadb_prop_len;
+ __u16 sadb_prop_exttype;
+ __u8 sadb_prop_replay;
+ __u8 sadb_prop_reserved[3];
+} __attribute__((packed));
+/* sizeof(struct sadb_prop) == 8 */
+
+/* followed by:
+ struct sadb_comb sadb_combs[(sadb_prop_len +
+ sizeof(__u64) - sizeof(struct sadb_prop)) /
+ sizeof(struct sadb_comb)]; */
+
+struct sadb_comb {
+ __u8 sadb_comb_auth;
+ __u8 sadb_comb_encrypt;
+ __u16 sadb_comb_flags;
+ __u16 sadb_comb_auth_minbits;
+ __u16 sadb_comb_auth_maxbits;
+ __u16 sadb_comb_encrypt_minbits;
+ __u16 sadb_comb_encrypt_maxbits;
+ __u32 sadb_comb_reserved;
+ __u32 sadb_comb_soft_allocations;
+ __u32 sadb_comb_hard_allocations;
+ __u64 sadb_comb_soft_bytes;
+ __u64 sadb_comb_hard_bytes;
+ __u64 sadb_comb_soft_addtime;
+ __u64 sadb_comb_hard_addtime;
+ __u64 sadb_comb_soft_usetime;
+ __u64 sadb_comb_hard_usetime;
+} __attribute__((packed));
+/* sizeof(struct sadb_comb) == 72 */
+
+struct sadb_supported {
+ __u16 sadb_supported_len;
+ __u16 sadb_supported_exttype;
+ __u32 sadb_supported_reserved;
+} __attribute__((packed));
+/* sizeof(struct sadb_supported) == 8 */
+
+/* followed by:
+ struct sadb_alg sadb_algs[(sadb_supported_len +
+ sizeof(__u64) - sizeof(struct sadb_supported)) /
+ sizeof(struct sadb_alg)]; */
+
+struct sadb_alg {
+ __u8 sadb_alg_id;
+ __u8 sadb_alg_ivlen;
+ __u16 sadb_alg_minbits;
+ __u16 sadb_alg_maxbits;
+ __u16 sadb_alg_reserved;
+} __attribute__((packed));
+/* sizeof(struct sadb_alg) == 8 */
+
+struct sadb_spirange {
+ __u16 sadb_spirange_len;
+ __u16 sadb_spirange_exttype;
+ __u32 sadb_spirange_min;
+ __u32 sadb_spirange_max;
+ __u32 sadb_spirange_reserved;
+} __attribute__((packed));
+/* sizeof(struct sadb_spirange) == 16 */
+
+struct sadb_x_kmprivate {
+ __u16 sadb_x_kmprivate_len;
+ __u16 sadb_x_kmprivate_exttype;
+ __u32 sadb_x_kmprivate_reserved;
+} __attribute__((packed));
+/* sizeof(struct sadb_x_kmprivate) == 8 */
+
+struct sadb_x_sa2 {
+ __u16 sadb_x_sa2_len;
+ __u16 sadb_x_sa2_exttype;
+ __u8 sadb_x_sa2_mode;
+ __u8 sadb_x_sa2_reserved1;
+ __u16 sadb_x_sa2_reserved2;
+ __u32 sadb_x_sa2_sequence;
+ __u32 sadb_x_sa2_reqid;
+} __attribute__((packed));
+/* sizeof(struct sadb_x_sa2) == 16 */
+
+struct sadb_x_policy {
+ __u16 sadb_x_policy_len;
+ __u16 sadb_x_policy_exttype;
+ __u16 sadb_x_policy_type;
+ __u8 sadb_x_policy_dir;
+ __u8 sadb_x_policy_reserved;
+ __u32 sadb_x_policy_id;
+ __u32 sadb_x_policy_priority;
+} __attribute__((packed));
+/* sizeof(struct sadb_x_policy) == 16 */
+
+struct sadb_x_ipsecrequest {
+ __u16 sadb_x_ipsecrequest_len;
+ __u16 sadb_x_ipsecrequest_proto;
+ __u8 sadb_x_ipsecrequest_mode;
+ __u8 sadb_x_ipsecrequest_level;
+ __u16 sadb_x_ipsecrequest_reserved1;
+ __u32 sadb_x_ipsecrequest_reqid;
+ __u32 sadb_x_ipsecrequest_reserved2;
+} __attribute__((packed));
+/* sizeof(struct sadb_x_ipsecrequest) == 16 */
+
+/* This defines the TYPE of Nat Traversal in use. Currently only one
+ * type of NAT-T is supported, draft-ietf-ipsec-udp-encaps-06
+ */
+struct sadb_x_nat_t_type {
+ __u16 sadb_x_nat_t_type_len;
+ __u16 sadb_x_nat_t_type_exttype;
+ __u8 sadb_x_nat_t_type_type;
+ __u8 sadb_x_nat_t_type_reserved[3];
+} __attribute__((packed));
+/* sizeof(struct sadb_x_nat_t_type) == 8 */
+
+/* Pass a NAT Traversal port (Source or Dest port) */
+struct sadb_x_nat_t_port {
+ __u16 sadb_x_nat_t_port_len;
+ __u16 sadb_x_nat_t_port_exttype;
+ __be16 sadb_x_nat_t_port_port;
+ __u16 sadb_x_nat_t_port_reserved;
+} __attribute__((packed));
+/* sizeof(struct sadb_x_nat_t_port) == 8 */
+
+/* Generic LSM security context */
+struct sadb_x_sec_ctx {
+ __u16 sadb_x_sec_len;
+ __u16 sadb_x_sec_exttype;
+ __u8 sadb_x_ctx_alg; /* LSMs: e.g., selinux == 1 */
+ __u8 sadb_x_ctx_doi;
+ __u16 sadb_x_ctx_len;
+} __attribute__((packed));
+/* sizeof(struct sadb_sec_ctx) = 8 */
+
+/* Used by MIGRATE to pass addresses IKE will use to perform
+ * negotiation with the peer */
+struct sadb_x_kmaddress {
+ __u16 sadb_x_kmaddress_len;
+ __u16 sadb_x_kmaddress_exttype;
+ __u32 sadb_x_kmaddress_reserved;
+} __attribute__((packed));
+/* sizeof(struct sadb_x_kmaddress) == 8 */
+
+/* To specify the SA dump filter */
+struct sadb_x_filter {
+ __u16 sadb_x_filter_len;
+ __u16 sadb_x_filter_exttype;
+ __u32 sadb_x_filter_saddr[4];
+ __u32 sadb_x_filter_daddr[4];
+ __u16 sadb_x_filter_family;
+ __u8 sadb_x_filter_splen;
+ __u8 sadb_x_filter_dplen;
+} __attribute__((packed));
+/* sizeof(struct sadb_x_filter) == 40 */
+
+/* Message types */
+#define SADB_RESERVED 0
+#define SADB_GETSPI 1
+#define SADB_UPDATE 2
+#define SADB_ADD 3
+#define SADB_DELETE 4
+#define SADB_GET 5
+#define SADB_ACQUIRE 6
+#define SADB_REGISTER 7
+#define SADB_EXPIRE 8
+#define SADB_FLUSH 9
+#define SADB_DUMP 10
+#define SADB_X_PROMISC 11
+#define SADB_X_PCHANGE 12
+#define SADB_X_SPDUPDATE 13
+#define SADB_X_SPDADD 14
+#define SADB_X_SPDDELETE 15
+#define SADB_X_SPDGET 16
+#define SADB_X_SPDACQUIRE 17
+#define SADB_X_SPDDUMP 18
+#define SADB_X_SPDFLUSH 19
+#define SADB_X_SPDSETIDX 20
+#define SADB_X_SPDEXPIRE 21
+#define SADB_X_SPDDELETE2 22
+#define SADB_X_NAT_T_NEW_MAPPING 23
+#define SADB_X_MIGRATE 24
+#define SADB_MAX 24
+
+/* Security Association flags */
+#define SADB_SAFLAGS_PFS 1
+#define SADB_SAFLAGS_NOPMTUDISC 0x20000000
+#define SADB_SAFLAGS_DECAP_DSCP 0x40000000
+#define SADB_SAFLAGS_NOECN 0x80000000
+
+/* Security Association states */
+#define SADB_SASTATE_LARVAL 0
+#define SADB_SASTATE_MATURE 1
+#define SADB_SASTATE_DYING 2
+#define SADB_SASTATE_DEAD 3
+#define SADB_SASTATE_MAX 3
+
+/* Security Association types */
+#define SADB_SATYPE_UNSPEC 0
+#define SADB_SATYPE_AH 2
+#define SADB_SATYPE_ESP 3
+#define SADB_SATYPE_RSVP 5
+#define SADB_SATYPE_OSPFV2 6
+#define SADB_SATYPE_RIPV2 7
+#define SADB_SATYPE_MIP 8
+#define SADB_X_SATYPE_IPCOMP 9
+#define SADB_SATYPE_MAX 9
+
+/* Authentication algorithms */
+#define SADB_AALG_NONE 0
+#define SADB_AALG_MD5HMAC 2
+#define SADB_AALG_SHA1HMAC 3
+#define SADB_X_AALG_SHA2_256HMAC 5
+#define SADB_X_AALG_SHA2_384HMAC 6
+#define SADB_X_AALG_SHA2_512HMAC 7
+#define SADB_X_AALG_RIPEMD160HMAC 8
+#define SADB_X_AALG_AES_XCBC_MAC 9
+#define SADB_X_AALG_SM3_256HMAC 10
+#define SADB_X_AALG_NULL 251 /* kame */
+#define SADB_AALG_MAX 251
+
+/* Encryption algorithms */
+#define SADB_EALG_NONE 0
+#define SADB_EALG_DESCBC 2
+#define SADB_EALG_3DESCBC 3
+#define SADB_X_EALG_CASTCBC 6
+#define SADB_X_EALG_BLOWFISHCBC 7
+#define SADB_EALG_NULL 11
+#define SADB_X_EALG_AESCBC 12
+#define SADB_X_EALG_AESCTR 13
+#define SADB_X_EALG_AES_CCM_ICV8 14
+#define SADB_X_EALG_AES_CCM_ICV12 15
+#define SADB_X_EALG_AES_CCM_ICV16 16
+#define SADB_X_EALG_AES_GCM_ICV8 18
+#define SADB_X_EALG_AES_GCM_ICV12 19
+#define SADB_X_EALG_AES_GCM_ICV16 20
+#define SADB_X_EALG_CAMELLIACBC 22
+#define SADB_X_EALG_NULL_AES_GMAC 23
+#define SADB_X_EALG_SM4CBC 24
+#define SADB_EALG_MAX 253 /* last EALG */
+/* private allocations should use 249-255 (RFC2407) */
+#define SADB_X_EALG_SERPENTCBC 252 /* draft-ietf-ipsec-ciph-aes-cbc-00 */
+#define SADB_X_EALG_TWOFISHCBC 253 /* draft-ietf-ipsec-ciph-aes-cbc-00 */
+
+/* Compression algorithms */
+#define SADB_X_CALG_NONE 0
+#define SADB_X_CALG_OUI 1
+#define SADB_X_CALG_DEFLATE 2
+#define SADB_X_CALG_LZS 3
+#define SADB_X_CALG_LZJH 4
+#define SADB_X_CALG_MAX 4
+
+/* Extension Header values */
+#define SADB_EXT_RESERVED 0
+#define SADB_EXT_SA 1
+#define SADB_EXT_LIFETIME_CURRENT 2
+#define SADB_EXT_LIFETIME_HARD 3
+#define SADB_EXT_LIFETIME_SOFT 4
+#define SADB_EXT_ADDRESS_SRC 5
+#define SADB_EXT_ADDRESS_DST 6
+#define SADB_EXT_ADDRESS_PROXY 7
+#define SADB_EXT_KEY_AUTH 8
+#define SADB_EXT_KEY_ENCRYPT 9
+#define SADB_EXT_IDENTITY_SRC 10
+#define SADB_EXT_IDENTITY_DST 11
+#define SADB_EXT_SENSITIVITY 12
+#define SADB_EXT_PROPOSAL 13
+#define SADB_EXT_SUPPORTED_AUTH 14
+#define SADB_EXT_SUPPORTED_ENCRYPT 15
+#define SADB_EXT_SPIRANGE 16
+#define SADB_X_EXT_KMPRIVATE 17
+#define SADB_X_EXT_POLICY 18
+#define SADB_X_EXT_SA2 19
+/* The next four entries are for setting up NAT Traversal */
+#define SADB_X_EXT_NAT_T_TYPE 20
+#define SADB_X_EXT_NAT_T_SPORT 21
+#define SADB_X_EXT_NAT_T_DPORT 22
+#define SADB_X_EXT_NAT_T_OA 23
+#define SADB_X_EXT_SEC_CTX 24
+/* Used with MIGRATE to pass @ to IKE for negotiation */
+#define SADB_X_EXT_KMADDRESS 25
+#define SADB_X_EXT_FILTER 26
+#define SADB_EXT_MAX 26
+
+/* Identity Extension values */
+#define SADB_IDENTTYPE_RESERVED 0
+#define SADB_IDENTTYPE_PREFIX 1
+#define SADB_IDENTTYPE_FQDN 2
+#define SADB_IDENTTYPE_USERFQDN 3
+#define SADB_IDENTTYPE_MAX 3
+
+#endif /* !(_LINUX_PFKEY2_H) */
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
new file mode 100644
index 0000000..ea27703
--- /dev/null
+++ b/include/uapi/linux/pkt_cls.h
@@ -0,0 +1,773 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TC_COOKIE_MAX_SIZE 16
+
+/* Action attributes */
+enum {
+ TCA_ACT_UNSPEC,
+ TCA_ACT_KIND,
+ TCA_ACT_OPTIONS,
+ TCA_ACT_INDEX,
+ TCA_ACT_STATS,
+ TCA_ACT_PAD,
+ TCA_ACT_COOKIE,
+ TCA_ACT_FLAGS,
+ TCA_ACT_HW_STATS,
+ TCA_ACT_USED_HW_STATS,
+ TCA_ACT_IN_HW_COUNT,
+ __TCA_ACT_MAX
+};
+
+/* See other TCA_ACT_FLAGS_ * flags in include/net/act_api.h. */
+#define TCA_ACT_FLAGS_NO_PERCPU_STATS (1 << 0) /* Don't use percpu allocator for
+ * actions stats.
+ */
+#define TCA_ACT_FLAGS_SKIP_HW (1 << 1) /* don't offload action to HW */
+#define TCA_ACT_FLAGS_SKIP_SW (1 << 2) /* don't use action in SW */
+
+/* tca HW stats type
+ * When user does not pass the attribute, he does not care.
+ * It is the same as if he would pass the attribute with
+ * all supported bits set.
+ * In case no bits are set, user is not interested in getting any HW statistics.
+ */
+#define TCA_ACT_HW_STATS_IMMEDIATE (1 << 0) /* Means that in dump, user
+ * gets the current HW stats
+ * state from the device
+ * queried at the dump time.
+ */
+#define TCA_ACT_HW_STATS_DELAYED (1 << 1) /* Means that in dump, user gets
+ * HW stats that might be out of date
+ * for some time, maybe couple of
+ * seconds. This is the case when
+ * driver polls stats updates
+ * periodically or when it gets async
+ * stats update from the device.
+ */
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND 1
+#define TCA_ACT_NOBIND 0
+#define TCA_ACT_UNBIND 1
+#define TCA_ACT_NOUNBIND 0
+#define TCA_ACT_REPLACE 1
+#define TCA_ACT_NOREPLACE 0
+
+#define TC_ACT_UNSPEC (-1)
+#define TC_ACT_OK 0
+#define TC_ACT_RECLASSIFY 1
+#define TC_ACT_SHOT 2
+#define TC_ACT_PIPE 3
+#define TC_ACT_STOLEN 4
+#define TC_ACT_QUEUED 5
+#define TC_ACT_REPEAT 6
+#define TC_ACT_REDIRECT 7
+#define TC_ACT_TRAP 8 /* For hw path, this means "trap to cpu"
+ * and don't further process the frame
+ * in hardware. For sw path, this is
+ * equivalent of TC_ACT_STOLEN - drop
+ * the skb and act like everything
+ * is alright.
+ */
+#define TC_ACT_VALUE_MAX TC_ACT_TRAP
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN
+
+/* These macros are put here for binary compatibility with userspace apps that
+ * make use of them. For kernel code and new userspace apps, use the TCA_ID_*
+ * versions.
+ */
+#define TCA_ACT_GACT 5
+#define TCA_ACT_IPT 6 /* obsoleted, can be reused */
+#define TCA_ACT_PEDIT 7
+#define TCA_ACT_MIRRED 8
+#define TCA_ACT_NAT 9
+#define TCA_ACT_XT 10
+#define TCA_ACT_SKBEDIT 11
+#define TCA_ACT_VLAN 12
+#define TCA_ACT_BPF 13
+#define TCA_ACT_CONNMARK 14
+#define TCA_ACT_SKBMOD 15
+#define TCA_ACT_CSUM 16
+#define TCA_ACT_TUNNEL_KEY 17
+#define TCA_ACT_SIMP 22
+#define TCA_ACT_IFE 25
+#define TCA_ACT_SAMPLE 26
+
+/* Action type identifiers*/
+enum tca_id {
+ TCA_ID_UNSPEC = 0,
+ TCA_ID_POLICE = 1,
+ TCA_ID_GACT = TCA_ACT_GACT,
+ TCA_ID_IPT = TCA_ACT_IPT, /* Obsoleted, can be reused */
+ TCA_ID_PEDIT = TCA_ACT_PEDIT,
+ TCA_ID_MIRRED = TCA_ACT_MIRRED,
+ TCA_ID_NAT = TCA_ACT_NAT,
+ TCA_ID_XT = TCA_ACT_XT,
+ TCA_ID_SKBEDIT = TCA_ACT_SKBEDIT,
+ TCA_ID_VLAN = TCA_ACT_VLAN,
+ TCA_ID_BPF = TCA_ACT_BPF,
+ TCA_ID_CONNMARK = TCA_ACT_CONNMARK,
+ TCA_ID_SKBMOD = TCA_ACT_SKBMOD,
+ TCA_ID_CSUM = TCA_ACT_CSUM,
+ TCA_ID_TUNNEL_KEY = TCA_ACT_TUNNEL_KEY,
+ TCA_ID_SIMP = TCA_ACT_SIMP,
+ TCA_ID_IFE = TCA_ACT_IFE,
+ TCA_ID_SAMPLE = TCA_ACT_SAMPLE,
+ TCA_ID_CTINFO,
+ TCA_ID_MPLS,
+ TCA_ID_CT,
+ TCA_ID_GATE,
+ /* other actions go here */
+ __TCA_ID_MAX = 255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+ __u32 index;
+ int action;
+#define TC_POLICE_UNSPEC TC_ACT_UNSPEC
+#define TC_POLICE_OK TC_ACT_OK
+#define TC_POLICE_RECLASSIFY TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT TC_ACT_SHOT
+#define TC_POLICE_PIPE TC_ACT_PIPE
+
+ __u32 limit;
+ __u32 burst;
+ __u32 mtu;
+ struct tc_ratespec rate;
+ struct tc_ratespec peakrate;
+ int refcnt;
+ int bindcnt;
+ __u32 capab;
+};
+
+struct tcf_t {
+ __u64 install;
+ __u64 lastuse;
+ __u64 expires;
+ __u64 firstuse;
+};
+
+struct tc_cnt {
+ int refcnt;
+ int bindcnt;
+};
+
+#define tc_gen \
+ __u32 index; \
+ __u32 capab; \
+ int action; \
+ int refcnt; \
+ int bindcnt
+
+enum {
+ TCA_POLICE_UNSPEC,
+ TCA_POLICE_TBF,
+ TCA_POLICE_RATE,
+ TCA_POLICE_PEAKRATE,
+ TCA_POLICE_AVRATE,
+ TCA_POLICE_RESULT,
+ TCA_POLICE_TM,
+ TCA_POLICE_PAD,
+ TCA_POLICE_RATE64,
+ TCA_POLICE_PEAKRATE64,
+ TCA_POLICE_PKTRATE64,
+ TCA_POLICE_PKTBURST64,
+ __TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW (1 << 0) /* don't offload filter to HW */
+#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) /* don't use filter in SW */
+#define TCA_CLS_FLAGS_IN_HW (1 << 2) /* filter is offloaded to HW */
+#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE (1 << 4) /* verbose logging */
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC 0
+#define TC_U32_ROOT (0xFFF00000)
+
+enum {
+ TCA_U32_UNSPEC,
+ TCA_U32_CLASSID,
+ TCA_U32_HASH,
+ TCA_U32_LINK,
+ TCA_U32_DIVISOR,
+ TCA_U32_SEL,
+ TCA_U32_POLICE,
+ TCA_U32_ACT,
+ TCA_U32_INDEV,
+ TCA_U32_PCNT,
+ TCA_U32_MARK,
+ TCA_U32_FLAGS,
+ TCA_U32_PAD,
+ __TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+ __be32 mask;
+ __be32 val;
+ int off;
+ int offmask;
+};
+
+struct tc_u32_sel {
+ unsigned char flags;
+ unsigned char offshift;
+ unsigned char nkeys;
+
+ __be16 offmask;
+ __u16 off;
+ short offoff;
+
+ short hoff;
+ __be32 hmask;
+ struct tc_u32_key keys[];
+};
+
+struct tc_u32_mark {
+ __u32 val;
+ __u32 mask;
+ __u32 success;
+};
+
+struct tc_u32_pcnt {
+ __u64 rcnt;
+ __u64 rhit;
+ __u64 kcnts[];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL 1
+#define TC_U32_OFFSET 2
+#define TC_U32_VAROFFSET 4
+#define TC_U32_EAT 8
+
+#define TC_U32_MAXDEPTH 8
+
+/* ROUTE filter */
+
+enum {
+ TCA_ROUTE4_UNSPEC,
+ TCA_ROUTE4_CLASSID,
+ TCA_ROUTE4_TO,
+ TCA_ROUTE4_FROM,
+ TCA_ROUTE4_IIF,
+ TCA_ROUTE4_POLICE,
+ TCA_ROUTE4_ACT,
+ __TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+ TCA_FW_UNSPEC,
+ TCA_FW_CLASSID,
+ TCA_FW_POLICE,
+ TCA_FW_INDEV,
+ TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+ TCA_FW_MASK,
+ __TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* Flow filter */
+
+enum {
+ FLOW_KEY_SRC,
+ FLOW_KEY_DST,
+ FLOW_KEY_PROTO,
+ FLOW_KEY_PROTO_SRC,
+ FLOW_KEY_PROTO_DST,
+ FLOW_KEY_IIF,
+ FLOW_KEY_PRIORITY,
+ FLOW_KEY_MARK,
+ FLOW_KEY_NFCT,
+ FLOW_KEY_NFCT_SRC,
+ FLOW_KEY_NFCT_DST,
+ FLOW_KEY_NFCT_PROTO_SRC,
+ FLOW_KEY_NFCT_PROTO_DST,
+ FLOW_KEY_RTCLASSID,
+ FLOW_KEY_SKUID,
+ FLOW_KEY_SKGID,
+ FLOW_KEY_VLAN_TAG,
+ FLOW_KEY_RXHASH,
+ __FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX (__FLOW_KEY_MAX - 1)
+
+enum {
+ FLOW_MODE_MAP,
+ FLOW_MODE_HASH,
+};
+
+enum {
+ TCA_FLOW_UNSPEC,
+ TCA_FLOW_KEYS,
+ TCA_FLOW_MODE,
+ TCA_FLOW_BASECLASS,
+ TCA_FLOW_RSHIFT,
+ TCA_FLOW_ADDEND,
+ TCA_FLOW_MASK,
+ TCA_FLOW_XOR,
+ TCA_FLOW_DIVISOR,
+ TCA_FLOW_ACT,
+ TCA_FLOW_POLICE,
+ TCA_FLOW_EMATCHES,
+ TCA_FLOW_PERTURB,
+ __TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX (__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+struct tc_basic_pcnt {
+ __u64 rcnt;
+ __u64 rhit;
+};
+
+enum {
+ TCA_BASIC_UNSPEC,
+ TCA_BASIC_CLASSID,
+ TCA_BASIC_EMATCHES,
+ TCA_BASIC_ACT,
+ TCA_BASIC_POLICE,
+ TCA_BASIC_PCNT,
+ TCA_BASIC_PAD,
+ __TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+ TCA_CGROUP_UNSPEC,
+ TCA_CGROUP_ACT,
+ TCA_CGROUP_POLICE,
+ TCA_CGROUP_EMATCHES,
+ __TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0)
+
+enum {
+ TCA_BPF_UNSPEC,
+ TCA_BPF_ACT,
+ TCA_BPF_POLICE,
+ TCA_BPF_CLASSID,
+ TCA_BPF_OPS_LEN,
+ TCA_BPF_OPS,
+ TCA_BPF_FD,
+ TCA_BPF_NAME,
+ TCA_BPF_FLAGS,
+ TCA_BPF_FLAGS_GEN,
+ TCA_BPF_TAG,
+ TCA_BPF_ID,
+ __TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+ TCA_FLOWER_UNSPEC,
+ TCA_FLOWER_CLASSID,
+ TCA_FLOWER_INDEV,
+ TCA_FLOWER_ACT,
+ TCA_FLOWER_KEY_ETH_DST, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_DST_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_SRC, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_SRC_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_TYPE, /* be16 */
+ TCA_FLOWER_KEY_IP_PROTO, /* u8 */
+ TCA_FLOWER_KEY_IPV4_SRC, /* be32 */
+ TCA_FLOWER_KEY_IPV4_SRC_MASK, /* be32 */
+ TCA_FLOWER_KEY_IPV4_DST, /* be32 */
+ TCA_FLOWER_KEY_IPV4_DST_MASK, /* be32 */
+ TCA_FLOWER_KEY_IPV6_SRC, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_SRC_MASK, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_DST, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_DST_MASK, /* struct in6_addr */
+ TCA_FLOWER_KEY_TCP_SRC, /* be16 */
+ TCA_FLOWER_KEY_TCP_DST, /* be16 */
+ TCA_FLOWER_KEY_UDP_SRC, /* be16 */
+ TCA_FLOWER_KEY_UDP_DST, /* be16 */
+
+ TCA_FLOWER_FLAGS,
+ TCA_FLOWER_KEY_VLAN_ID, /* be16 */
+ TCA_FLOWER_KEY_VLAN_PRIO, /* u8 */
+ TCA_FLOWER_KEY_VLAN_ETH_TYPE, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_KEY_ID, /* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_SRC, /* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_DST, /* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+ TCA_FLOWER_KEY_ENC_IPV6_SRC, /* struct in6_addr */
+ TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+ TCA_FLOWER_KEY_ENC_IPV6_DST, /* struct in6_addr */
+ TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
+ TCA_FLOWER_KEY_TCP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */
+ TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */
+ TCA_FLOWER_KEY_SCTP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_SCTP_DST_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_SCTP_SRC, /* be16 */
+ TCA_FLOWER_KEY_SCTP_DST, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_FLAGS, /* be32 */
+ TCA_FLOWER_KEY_FLAGS_MASK, /* be32 */
+
+ TCA_FLOWER_KEY_ICMPV4_CODE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */
+ TCA_FLOWER_KEY_ICMPV4_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */
+ TCA_FLOWER_KEY_ICMPV6_CODE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */
+ TCA_FLOWER_KEY_ICMPV6_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */
+
+ TCA_FLOWER_KEY_ARP_SIP, /* be32 */
+ TCA_FLOWER_KEY_ARP_SIP_MASK, /* be32 */
+ TCA_FLOWER_KEY_ARP_TIP, /* be32 */
+ TCA_FLOWER_KEY_ARP_TIP_MASK, /* be32 */
+ TCA_FLOWER_KEY_ARP_OP, /* u8 */
+ TCA_FLOWER_KEY_ARP_OP_MASK, /* u8 */
+ TCA_FLOWER_KEY_ARP_SHA, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ARP_SHA_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ARP_THA, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ARP_THA_MASK, /* ETH_ALEN */
+
+ TCA_FLOWER_KEY_MPLS_TTL, /* u8 - 8 bits */
+ TCA_FLOWER_KEY_MPLS_BOS, /* u8 - 1 bit */
+ TCA_FLOWER_KEY_MPLS_TC, /* u8 - 3 bits */
+ TCA_FLOWER_KEY_MPLS_LABEL, /* be32 - 20 bits */
+
+ TCA_FLOWER_KEY_TCP_FLAGS, /* be16 */
+ TCA_FLOWER_KEY_TCP_FLAGS_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_IP_TOS, /* u8 */
+ TCA_FLOWER_KEY_IP_TOS_MASK, /* u8 */
+ TCA_FLOWER_KEY_IP_TTL, /* u8 */
+ TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */
+
+ TCA_FLOWER_KEY_CVLAN_ID, /* be16 */
+ TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */
+ TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_IP_TOS, /* u8 */
+ TCA_FLOWER_KEY_ENC_IP_TOS_MASK, /* u8 */
+ TCA_FLOWER_KEY_ENC_IP_TTL, /* u8 */
+ TCA_FLOWER_KEY_ENC_IP_TTL_MASK, /* u8 */
+
+ TCA_FLOWER_KEY_ENC_OPTS,
+ TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
+ TCA_FLOWER_IN_HW_COUNT,
+
+ TCA_FLOWER_KEY_PORT_SRC_MIN, /* be16 */
+ TCA_FLOWER_KEY_PORT_SRC_MAX, /* be16 */
+ TCA_FLOWER_KEY_PORT_DST_MIN, /* be16 */
+ TCA_FLOWER_KEY_PORT_DST_MAX, /* be16 */
+
+ TCA_FLOWER_KEY_CT_STATE, /* u16 */
+ TCA_FLOWER_KEY_CT_STATE_MASK, /* u16 */
+ TCA_FLOWER_KEY_CT_ZONE, /* u16 */
+ TCA_FLOWER_KEY_CT_ZONE_MASK, /* u16 */
+ TCA_FLOWER_KEY_CT_MARK, /* u32 */
+ TCA_FLOWER_KEY_CT_MARK_MASK, /* u32 */
+ TCA_FLOWER_KEY_CT_LABELS, /* u128 */
+ TCA_FLOWER_KEY_CT_LABELS_MASK, /* u128 */
+
+ TCA_FLOWER_KEY_MPLS_OPTS,
+
+ TCA_FLOWER_KEY_HASH, /* u32 */
+ TCA_FLOWER_KEY_HASH_MASK, /* u32 */
+
+ TCA_FLOWER_KEY_NUM_OF_VLANS, /* u8 */
+
+ TCA_FLOWER_KEY_PPPOE_SID, /* be16 */
+ TCA_FLOWER_KEY_PPP_PROTO, /* be16 */
+
+ TCA_FLOWER_KEY_L2TPV3_SID, /* be32 */
+
+ TCA_FLOWER_L2_MISS, /* u8 */
+
+ TCA_FLOWER_KEY_CFM, /* nested */
+
+ TCA_FLOWER_KEY_SPI, /* be32 */
+ TCA_FLOWER_KEY_SPI_MASK, /* be32 */
+
+ __TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_CT_FLAGS_NEW = 1 << 0, /* Beginning of a new connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */
+ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */
+ TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */
+ TCA_FLOWER_KEY_CT_FLAGS_REPLY = 1 << 5, /* Packet is in the reply direction. */
+ __TCA_FLOWER_KEY_CT_FLAGS_MAX,
+};
+
+enum {
+ TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+ * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+ * attributes
+ */
+ TCA_FLOWER_KEY_ENC_OPTS_VXLAN, /* Nested
+ * TCA_FLOWER_KEY_ENC_OPT_VXLAN_
+ * attributes
+ */
+ TCA_FLOWER_KEY_ENC_OPTS_ERSPAN, /* Nested
+ * TCA_FLOWER_KEY_ENC_OPT_ERSPAN_
+ * attributes
+ */
+ TCA_FLOWER_KEY_ENC_OPTS_GTP, /* Nested
+ * TCA_FLOWER_KEY_ENC_OPT_GTP_
+ * attributes
+ */
+ __TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, /* u16 */
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */
+
+ __TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+ (__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_ENC_OPT_VXLAN_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP, /* u32 */
+ __TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX \
+ (__TCA_FLOWER_KEY_ENC_OPT_VXLAN_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_ENC_OPT_ERSPAN_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPT_ERSPAN_VER, /* u8 */
+ TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX, /* be32 */
+ TCA_FLOWER_KEY_ENC_OPT_ERSPAN_DIR, /* u8 */
+ TCA_FLOWER_KEY_ENC_OPT_ERSPAN_HWID, /* u8 */
+ __TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX \
+ (__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_ENC_OPT_GTP_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ENC_OPT_GTP_QFI, /* u8 */
+
+ __TCA_FLOWER_KEY_ENC_OPT_GTP_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GTP_MAX \
+ (__TCA_FLOWER_KEY_ENC_OPT_GTP_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC,
+ TCA_FLOWER_KEY_MPLS_OPTS_LSE,
+ __TCA_FLOWER_KEY_MPLS_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPTS_MAX (__TCA_FLOWER_KEY_MPLS_OPTS_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_UNSPEC,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_TC,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL,
+ __TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX \
+ (__TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+ TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+};
+
+enum {
+ TCA_FLOWER_KEY_CFM_OPT_UNSPEC,
+ TCA_FLOWER_KEY_CFM_MD_LEVEL,
+ TCA_FLOWER_KEY_CFM_OPCODE,
+ __TCA_FLOWER_KEY_CFM_OPT_MAX,
+};
+
+#define TCA_FLOWER_KEY_CFM_OPT_MAX (__TCA_FLOWER_KEY_CFM_OPT_MAX - 1)
+
+#define TCA_FLOWER_MASK_FLAGS_RANGE (1 << 0) /* Range-based match */
+
+/* Match-all classifier */
+
+struct tc_matchall_pcnt {
+ __u64 rhit;
+};
+
+enum {
+ TCA_MATCHALL_UNSPEC,
+ TCA_MATCHALL_CLASSID,
+ TCA_MATCHALL_ACT,
+ TCA_MATCHALL_FLAGS,
+ TCA_MATCHALL_PCNT,
+ TCA_MATCHALL_PAD,
+ __TCA_MATCHALL_MAX,
+};
+
+#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+ __u16 nmatches;
+ __u16 progid;
+};
+
+enum {
+ TCA_EMATCH_TREE_UNSPEC,
+ TCA_EMATCH_TREE_HDR,
+ TCA_EMATCH_TREE_LIST,
+ __TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+ __u16 matchid;
+ __u16 kind;
+ __u16 flags;
+ __u16 pad; /* currently unused */
+};
+
+/* 0 1
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5
+ * +-----------------------+-+-+---+
+ * | Unused |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ * where: 0 0 END (last ematch)
+ * 0 1 AND
+ * 1 0 OR
+ * 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END 0
+#define TCF_EM_REL_AND (1<<0)
+#define TCF_EM_REL_OR (1<<1)
+#define TCF_EM_INVERT (1<<2)
+#define TCF_EM_SIMPLE (1<<3)
+
+#define TCF_EM_REL_MASK 3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+ TCF_LAYER_LINK,
+ TCF_LAYER_NETWORK,
+ TCF_LAYER_TRANSPORT,
+ __TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ * 1..32767 Reserved for ematches inside kernel tree
+ * 32768..65535 Free to use, not reliable
+ */
+#define TCF_EM_CONTAINER 0
+#define TCF_EM_CMP 1
+#define TCF_EM_NBYTE 2
+#define TCF_EM_U32 3
+#define TCF_EM_META 4
+#define TCF_EM_TEXT 5
+#define TCF_EM_VLAN 6
+#define TCF_EM_CANID 7
+#define TCF_EM_IPSET 8
+#define TCF_EM_IPT 9
+#define TCF_EM_MAX 9
+
+enum {
+ TCF_EM_PROG_TC
+};
+
+enum {
+ TCF_EM_OPND_EQ,
+ TCF_EM_OPND_GT,
+ TCF_EM_OPND_LT
+};
+
+#endif
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
new file mode 100644
index 0000000..a3cd0c2
--- /dev/null
+++ b/include/uapi/linux/pkt_sched.h
@@ -0,0 +1,1211 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_SCHED_H
+#define __LINUX_PKT_SCHED_H
+
+#include <linux/const.h>
+#include <linux/types.h>
+
+/* Logical priority bands not depending on specific packet scheduler.
+ Every scheduler will map them to real traffic classes, if it has
+ no more precise mechanism to classify packets.
+
+ These numbers have no special meaning, though their coincidence
+ with obsolete IPv6 values is not occasional :-). New IPv6 drafts
+ preferred full anarchy inspired by diffserv group.
+
+ Note: TC_PRIO_BESTEFFORT does not mean that it is the most unhappy
+ class, actually, as rule it will be handled with more care than
+ filler or even bulk.
+ */
+
+#define TC_PRIO_BESTEFFORT 0
+#define TC_PRIO_FILLER 1
+#define TC_PRIO_BULK 2
+#define TC_PRIO_INTERACTIVE_BULK 4
+#define TC_PRIO_INTERACTIVE 6
+#define TC_PRIO_CONTROL 7
+
+#define TC_PRIO_MAX 15
+
+/* Generic queue statistics, available for all the elements.
+ Particular schedulers may have also their private records.
+ */
+
+struct tc_stats {
+ __u64 bytes; /* Number of enqueued bytes */
+ __u32 packets; /* Number of enqueued packets */
+ __u32 drops; /* Packets dropped because of lack of resources */
+ __u32 overlimits; /* Number of throttle events when this
+ * flow goes out of allocated bandwidth */
+ __u32 bps; /* Current flow byte rate */
+ __u32 pps; /* Current flow packet rate */
+ __u32 qlen;
+ __u32 backlog;
+};
+
+struct tc_estimator {
+ signed char interval;
+ unsigned char ewma_log;
+};
+
+/* "Handles"
+ ---------
+
+ All the traffic control objects have 32bit identifiers, or "handles".
+
+ They can be considered as opaque numbers from user API viewpoint,
+ but actually they always consist of two fields: major and
+ minor numbers, which are interpreted by kernel specially,
+ that may be used by applications, though not recommended.
+
+ F.e. qdisc handles always have minor number equal to zero,
+ classes (or flows) have major equal to parent qdisc major, and
+ minor uniquely identifying class inside qdisc.
+
+ Macros to manipulate handles:
+ */
+
+#define TC_H_MAJ_MASK (0xFFFF0000U)
+#define TC_H_MIN_MASK (0x0000FFFFU)
+#define TC_H_MAJ(h) ((h)&TC_H_MAJ_MASK)
+#define TC_H_MIN(h) ((h)&TC_H_MIN_MASK)
+#define TC_H_MAKE(maj,min) (((maj)&TC_H_MAJ_MASK)|((min)&TC_H_MIN_MASK))
+
+#define TC_H_UNSPEC (0U)
+#define TC_H_ROOT (0xFFFFFFFFU)
+#define TC_H_INGRESS (0xFFFFFFF1U)
+#define TC_H_CLSACT TC_H_INGRESS
+
+#define TC_H_MIN_PRIORITY 0xFFE0U
+#define TC_H_MIN_INGRESS 0xFFF2U
+#define TC_H_MIN_EGRESS 0xFFF3U
+
+/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */
+enum tc_link_layer {
+ TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */
+ TC_LINKLAYER_ETHERNET,
+ TC_LINKLAYER_ATM,
+};
+#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */
+
+struct tc_ratespec {
+ unsigned char cell_log;
+ __u8 linklayer; /* lower 4 bits */
+ unsigned short overhead;
+ short cell_align;
+ unsigned short mpu;
+ __u32 rate;
+};
+
+#define TC_RTAB_SIZE 1024
+
+struct tc_sizespec {
+ unsigned char cell_log;
+ unsigned char size_log;
+ short cell_align;
+ int overhead;
+ unsigned int linklayer;
+ unsigned int mpu;
+ unsigned int mtu;
+ unsigned int tsize;
+};
+
+enum {
+ TCA_STAB_UNSPEC,
+ TCA_STAB_BASE,
+ TCA_STAB_DATA,
+ __TCA_STAB_MAX
+};
+
+#define TCA_STAB_MAX (__TCA_STAB_MAX - 1)
+
+/* FIFO section */
+
+struct tc_fifo_qopt {
+ __u32 limit; /* Queue length: bytes for bfifo, packets for pfifo */
+};
+
+/* SKBPRIO section */
+
+/*
+ * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1).
+ * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able
+ * to map one to one the DS field of IPV4 and IPV6 headers.
+ * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY.
+ */
+
+#define SKBPRIO_MAX_PRIORITY 64
+
+struct tc_skbprio_qopt {
+ __u32 limit; /* Queue length in packets. */
+};
+
+/* PRIO section */
+
+#define TCQ_PRIO_BANDS 16
+#define TCQ_MIN_PRIO_BANDS 2
+
+struct tc_prio_qopt {
+ int bands; /* Number of bands */
+ __u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */
+};
+
+/* MULTIQ section */
+
+struct tc_multiq_qopt {
+ __u16 bands; /* Number of bands */
+ __u16 max_bands; /* Maximum number of queues */
+};
+
+/* PLUG section */
+
+#define TCQ_PLUG_BUFFER 0
+#define TCQ_PLUG_RELEASE_ONE 1
+#define TCQ_PLUG_RELEASE_INDEFINITE 2
+#define TCQ_PLUG_LIMIT 3
+
+struct tc_plug_qopt {
+ /* TCQ_PLUG_BUFFER: Inset a plug into the queue and
+ * buffer any incoming packets
+ * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head
+ * to beginning of the next plug.
+ * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue.
+ * Stop buffering packets until the next TCQ_PLUG_BUFFER
+ * command is received (just act as a pass-thru queue).
+ * TCQ_PLUG_LIMIT: Increase/decrease queue size
+ */
+ int action;
+ __u32 limit;
+};
+
+/* TBF section */
+
+struct tc_tbf_qopt {
+ struct tc_ratespec rate;
+ struct tc_ratespec peakrate;
+ __u32 limit;
+ __u32 buffer;
+ __u32 mtu;
+};
+
+enum {
+ TCA_TBF_UNSPEC,
+ TCA_TBF_PARMS,
+ TCA_TBF_RTAB,
+ TCA_TBF_PTAB,
+ TCA_TBF_RATE64,
+ TCA_TBF_PRATE64,
+ TCA_TBF_BURST,
+ TCA_TBF_PBURST,
+ TCA_TBF_PAD,
+ __TCA_TBF_MAX,
+};
+
+#define TCA_TBF_MAX (__TCA_TBF_MAX - 1)
+
+
+/* TEQL section */
+
+/* TEQL does not require any parameters */
+
+/* SFQ section */
+
+struct tc_sfq_qopt {
+ unsigned quantum; /* Bytes per round allocated to flow */
+ int perturb_period; /* Period of hash perturbation */
+ __u32 limit; /* Maximal packets in queue */
+ unsigned divisor; /* Hash divisor */
+ unsigned flows; /* Maximal number of flows */
+};
+
+struct tc_sfqred_stats {
+ __u32 prob_drop; /* Early drops, below max threshold */
+ __u32 forced_drop; /* Early drops, after max threshold */
+ __u32 prob_mark; /* Marked packets, below max threshold */
+ __u32 forced_mark; /* Marked packets, after max threshold */
+ __u32 prob_mark_head; /* Marked packets, below max threshold */
+ __u32 forced_mark_head;/* Marked packets, after max threshold */
+};
+
+struct tc_sfq_qopt_v1 {
+ struct tc_sfq_qopt v0;
+ unsigned int depth; /* max number of packets per flow */
+ unsigned int headdrop;
+/* SFQRED parameters */
+ __u32 limit; /* HARD maximal flow queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags;
+ __u32 max_P; /* probability, high resolution */
+/* SFQRED stats */
+ struct tc_sfqred_stats stats;
+};
+
+
+struct tc_sfq_xstats {
+ __s32 allot;
+};
+
+/* RED section */
+
+enum {
+ TCA_RED_UNSPEC,
+ TCA_RED_PARMS,
+ TCA_RED_STAB,
+ TCA_RED_MAX_P,
+ TCA_RED_FLAGS, /* bitfield32 */
+ TCA_RED_EARLY_DROP_BLOCK, /* u32 */
+ TCA_RED_MARK_BLOCK, /* u32 */
+ __TCA_RED_MAX,
+};
+
+#define TCA_RED_MAX (__TCA_RED_MAX - 1)
+
+struct tc_red_qopt {
+ __u32 limit; /* HARD maximal queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+
+ /* This field can be used for flags that a RED-like qdisc has
+ * historically supported. E.g. when configuring RED, it can be used for
+ * ECN, HARDDROP and ADAPTATIVE. For SFQ it can be used for ECN,
+ * HARDDROP. Etc. Because this field has not been validated, and is
+ * copied back on dump, any bits besides those to which a given qdisc
+ * has assigned a historical meaning need to be considered for free use
+ * by userspace tools.
+ *
+ * Any further flags need to be passed differently, e.g. through an
+ * attribute (such as TCA_RED_FLAGS above). Such attribute should allow
+ * passing both recent and historic flags in one value.
+ */
+ unsigned char flags;
+#define TC_RED_ECN 1
+#define TC_RED_HARDDROP 2
+#define TC_RED_ADAPTATIVE 4
+#define TC_RED_NODROP 8
+};
+
+#define TC_RED_HISTORIC_FLAGS (TC_RED_ECN | TC_RED_HARDDROP | TC_RED_ADAPTATIVE)
+
+struct tc_red_xstats {
+ __u32 early; /* Early drops */
+ __u32 pdrop; /* Drops due to queue limits */
+ __u32 other; /* Drops due to drop() calls */
+ __u32 marked; /* Marked packets */
+};
+
+/* GRED section */
+
+#define MAX_DPs 16
+
+enum {
+ TCA_GRED_UNSPEC,
+ TCA_GRED_PARMS,
+ TCA_GRED_STAB,
+ TCA_GRED_DPS,
+ TCA_GRED_MAX_P,
+ TCA_GRED_LIMIT,
+ TCA_GRED_VQ_LIST, /* nested TCA_GRED_VQ_ENTRY */
+ __TCA_GRED_MAX,
+};
+
+#define TCA_GRED_MAX (__TCA_GRED_MAX - 1)
+
+enum {
+ TCA_GRED_VQ_ENTRY_UNSPEC,
+ TCA_GRED_VQ_ENTRY, /* nested TCA_GRED_VQ_* */
+ __TCA_GRED_VQ_ENTRY_MAX,
+};
+#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1)
+
+enum {
+ TCA_GRED_VQ_UNSPEC,
+ TCA_GRED_VQ_PAD,
+ TCA_GRED_VQ_DP, /* u32 */
+ TCA_GRED_VQ_STAT_BYTES, /* u64 */
+ TCA_GRED_VQ_STAT_PACKETS, /* u32 */
+ TCA_GRED_VQ_STAT_BACKLOG, /* u32 */
+ TCA_GRED_VQ_STAT_PROB_DROP, /* u32 */
+ TCA_GRED_VQ_STAT_PROB_MARK, /* u32 */
+ TCA_GRED_VQ_STAT_FORCED_DROP, /* u32 */
+ TCA_GRED_VQ_STAT_FORCED_MARK, /* u32 */
+ TCA_GRED_VQ_STAT_PDROP, /* u32 */
+ TCA_GRED_VQ_STAT_OTHER, /* u32 */
+ TCA_GRED_VQ_FLAGS, /* u32 */
+ __TCA_GRED_VQ_MAX
+};
+
+#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1)
+
+struct tc_gred_qopt {
+ __u32 limit; /* HARD maximal queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ __u32 DP; /* up to 2^32 DPs */
+ __u32 backlog;
+ __u32 qave;
+ __u32 forced;
+ __u32 early;
+ __u32 other;
+ __u32 pdrop;
+ __u8 Wlog; /* log(W) */
+ __u8 Plog; /* log(P_max/(qth_max-qth_min)) */
+ __u8 Scell_log; /* cell size for idle damping */
+ __u8 prio; /* prio of this VQ */
+ __u32 packets;
+ __u32 bytesin;
+};
+
+/* gred setup */
+struct tc_gred_sopt {
+ __u32 DPs;
+ __u32 def_DP;
+ __u8 grio;
+ __u8 flags;
+ __u16 pad1;
+};
+
+/* CHOKe section */
+
+enum {
+ TCA_CHOKE_UNSPEC,
+ TCA_CHOKE_PARMS,
+ TCA_CHOKE_STAB,
+ TCA_CHOKE_MAX_P,
+ __TCA_CHOKE_MAX,
+};
+
+#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1)
+
+struct tc_choke_qopt {
+ __u32 limit; /* Hard queue length (packets) */
+ __u32 qth_min; /* Min average threshold (packets) */
+ __u32 qth_max; /* Max average threshold (packets) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags; /* see RED flags */
+};
+
+struct tc_choke_xstats {
+ __u32 early; /* Early drops */
+ __u32 pdrop; /* Drops due to queue limits */
+ __u32 other; /* Drops due to drop() calls */
+ __u32 marked; /* Marked packets */
+ __u32 matched; /* Drops due to flow match */
+};
+
+/* HTB section */
+#define TC_HTB_NUMPRIO 8
+#define TC_HTB_MAXDEPTH 8
+#define TC_HTB_PROTOVER 3 /* the same as HTB and TC's major */
+
+struct tc_htb_opt {
+ struct tc_ratespec rate;
+ struct tc_ratespec ceil;
+ __u32 buffer;
+ __u32 cbuffer;
+ __u32 quantum;
+ __u32 level; /* out only */
+ __u32 prio;
+};
+struct tc_htb_glob {
+ __u32 version; /* to match HTB/TC */
+ __u32 rate2quantum; /* bps->quantum divisor */
+ __u32 defcls; /* default class number */
+ __u32 debug; /* debug flags */
+
+ /* stats */
+ __u32 direct_pkts; /* count of non shaped packets */
+};
+enum {
+ TCA_HTB_UNSPEC,
+ TCA_HTB_PARMS,
+ TCA_HTB_INIT,
+ TCA_HTB_CTAB,
+ TCA_HTB_RTAB,
+ TCA_HTB_DIRECT_QLEN,
+ TCA_HTB_RATE64,
+ TCA_HTB_CEIL64,
+ TCA_HTB_PAD,
+ TCA_HTB_OFFLOAD,
+ __TCA_HTB_MAX,
+};
+
+#define TCA_HTB_MAX (__TCA_HTB_MAX - 1)
+
+struct tc_htb_xstats {
+ __u32 lends;
+ __u32 borrows;
+ __u32 giants; /* unused since 'Make HTB scheduler work with TSO.' */
+ __s32 tokens;
+ __s32 ctokens;
+};
+
+/* HFSC section */
+
+struct tc_hfsc_qopt {
+ __u16 defcls; /* default class */
+};
+
+struct tc_service_curve {
+ __u32 m1; /* slope of the first segment in bps */
+ __u32 d; /* x-projection of the first segment in us */
+ __u32 m2; /* slope of the second segment in bps */
+};
+
+struct tc_hfsc_stats {
+ __u64 work; /* total work done */
+ __u64 rtwork; /* work done by real-time criteria */
+ __u32 period; /* current period */
+ __u32 level; /* class level in hierarchy */
+};
+
+enum {
+ TCA_HFSC_UNSPEC,
+ TCA_HFSC_RSC,
+ TCA_HFSC_FSC,
+ TCA_HFSC_USC,
+ __TCA_HFSC_MAX,
+};
+
+#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
+
+/* Network emulator */
+
+enum {
+ TCA_NETEM_UNSPEC,
+ TCA_NETEM_CORR,
+ TCA_NETEM_DELAY_DIST,
+ TCA_NETEM_REORDER,
+ TCA_NETEM_CORRUPT,
+ TCA_NETEM_LOSS,
+ TCA_NETEM_RATE,
+ TCA_NETEM_ECN,
+ TCA_NETEM_RATE64,
+ TCA_NETEM_PAD,
+ TCA_NETEM_LATENCY64,
+ TCA_NETEM_JITTER64,
+ TCA_NETEM_SLOT,
+ TCA_NETEM_SLOT_DIST,
+ TCA_NETEM_PRNG_SEED,
+ __TCA_NETEM_MAX,
+};
+
+#define TCA_NETEM_MAX (__TCA_NETEM_MAX - 1)
+
+struct tc_netem_qopt {
+ __u32 latency; /* added delay (us) */
+ __u32 limit; /* fifo limit (packets) */
+ __u32 loss; /* random packet loss (0=none ~0=100%) */
+ __u32 gap; /* re-ordering gap (0 for none) */
+ __u32 duplicate; /* random packet dup (0=none ~0=100%) */
+ __u32 jitter; /* random jitter in latency (us) */
+};
+
+struct tc_netem_corr {
+ __u32 delay_corr; /* delay correlation */
+ __u32 loss_corr; /* packet loss correlation */
+ __u32 dup_corr; /* duplicate correlation */
+};
+
+struct tc_netem_reorder {
+ __u32 probability;
+ __u32 correlation;
+};
+
+struct tc_netem_corrupt {
+ __u32 probability;
+ __u32 correlation;
+};
+
+struct tc_netem_rate {
+ __u32 rate; /* byte/s */
+ __s32 packet_overhead;
+ __u32 cell_size;
+ __s32 cell_overhead;
+};
+
+struct tc_netem_slot {
+ __s64 min_delay; /* nsec */
+ __s64 max_delay;
+ __s32 max_packets;
+ __s32 max_bytes;
+ __s64 dist_delay; /* nsec */
+ __s64 dist_jitter; /* nsec */
+};
+
+enum {
+ NETEM_LOSS_UNSPEC,
+ NETEM_LOSS_GI, /* General Intuitive - 4 state model */
+ NETEM_LOSS_GE, /* Gilbert Elliot models */
+ __NETEM_LOSS_MAX
+};
+#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
+
+/* State transition probabilities for 4 state model */
+struct tc_netem_gimodel {
+ __u32 p13;
+ __u32 p31;
+ __u32 p32;
+ __u32 p14;
+ __u32 p23;
+};
+
+/* Gilbert-Elliot models */
+struct tc_netem_gemodel {
+ __u32 p;
+ __u32 r;
+ __u32 h;
+ __u32 k1;
+};
+
+#define NETEM_DIST_SCALE 8192
+#define NETEM_DIST_MAX 16384
+
+/* DRR */
+
+enum {
+ TCA_DRR_UNSPEC,
+ TCA_DRR_QUANTUM,
+ __TCA_DRR_MAX
+};
+
+#define TCA_DRR_MAX (__TCA_DRR_MAX - 1)
+
+struct tc_drr_stats {
+ __u32 deficit;
+};
+
+/* MQPRIO */
+#define TC_QOPT_BITMASK 15
+#define TC_QOPT_MAX_QUEUE 16
+
+enum {
+ TC_MQPRIO_HW_OFFLOAD_NONE, /* no offload requested */
+ TC_MQPRIO_HW_OFFLOAD_TCS, /* offload TCs, no queue counts */
+ __TC_MQPRIO_HW_OFFLOAD_MAX
+};
+
+#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1)
+
+enum {
+ TC_MQPRIO_MODE_DCB,
+ TC_MQPRIO_MODE_CHANNEL,
+ __TC_MQPRIO_MODE_MAX
+};
+
+#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1)
+
+enum {
+ TC_MQPRIO_SHAPER_DCB,
+ TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */
+ __TC_MQPRIO_SHAPER_MAX
+};
+
+#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1)
+
+enum {
+ TC_FP_EXPRESS = 1,
+ TC_FP_PREEMPTIBLE = 2,
+};
+
+struct tc_mqprio_qopt {
+ __u8 num_tc;
+ __u8 prio_tc_map[TC_QOPT_BITMASK + 1];
+ __u8 hw;
+ __u16 count[TC_QOPT_MAX_QUEUE];
+ __u16 offset[TC_QOPT_MAX_QUEUE];
+};
+
+#define TC_MQPRIO_F_MODE 0x1
+#define TC_MQPRIO_F_SHAPER 0x2
+#define TC_MQPRIO_F_MIN_RATE 0x4
+#define TC_MQPRIO_F_MAX_RATE 0x8
+
+enum {
+ TCA_MQPRIO_TC_ENTRY_UNSPEC,
+ TCA_MQPRIO_TC_ENTRY_INDEX, /* u32 */
+ TCA_MQPRIO_TC_ENTRY_FP, /* u32 */
+
+ /* add new constants above here */
+ __TCA_MQPRIO_TC_ENTRY_CNT,
+ TCA_MQPRIO_TC_ENTRY_MAX = (__TCA_MQPRIO_TC_ENTRY_CNT - 1)
+};
+
+enum {
+ TCA_MQPRIO_UNSPEC,
+ TCA_MQPRIO_MODE,
+ TCA_MQPRIO_SHAPER,
+ TCA_MQPRIO_MIN_RATE64,
+ TCA_MQPRIO_MAX_RATE64,
+ TCA_MQPRIO_TC_ENTRY,
+ __TCA_MQPRIO_MAX,
+};
+
+#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1)
+
+/* SFB */
+
+enum {
+ TCA_SFB_UNSPEC,
+ TCA_SFB_PARMS,
+ __TCA_SFB_MAX,
+};
+
+#define TCA_SFB_MAX (__TCA_SFB_MAX - 1)
+
+/*
+ * Note: increment, decrement are Q0.16 fixed-point values.
+ */
+struct tc_sfb_qopt {
+ __u32 rehash_interval; /* delay between hash move, in ms */
+ __u32 warmup_time; /* double buffering warmup time in ms (warmup_time < rehash_interval) */
+ __u32 max; /* max len of qlen_min */
+ __u32 bin_size; /* maximum queue length per bin */
+ __u32 increment; /* probability increment, (d1 in Blue) */
+ __u32 decrement; /* probability decrement, (d2 in Blue) */
+ __u32 limit; /* max SFB queue length */
+ __u32 penalty_rate; /* inelastic flows are rate limited to 'rate' pps */
+ __u32 penalty_burst;
+};
+
+struct tc_sfb_xstats {
+ __u32 earlydrop;
+ __u32 penaltydrop;
+ __u32 bucketdrop;
+ __u32 queuedrop;
+ __u32 childdrop; /* drops in child qdisc */
+ __u32 marked;
+ __u32 maxqlen;
+ __u32 maxprob;
+ __u32 avgprob;
+};
+
+#define SFB_MAX_PROB 0xFFFF
+
+/* QFQ */
+enum {
+ TCA_QFQ_UNSPEC,
+ TCA_QFQ_WEIGHT,
+ TCA_QFQ_LMAX,
+ __TCA_QFQ_MAX
+};
+
+#define TCA_QFQ_MAX (__TCA_QFQ_MAX - 1)
+
+struct tc_qfq_stats {
+ __u32 weight;
+ __u32 lmax;
+};
+
+/* CODEL */
+
+enum {
+ TCA_CODEL_UNSPEC,
+ TCA_CODEL_TARGET,
+ TCA_CODEL_LIMIT,
+ TCA_CODEL_INTERVAL,
+ TCA_CODEL_ECN,
+ TCA_CODEL_CE_THRESHOLD,
+ __TCA_CODEL_MAX
+};
+
+#define TCA_CODEL_MAX (__TCA_CODEL_MAX - 1)
+
+struct tc_codel_xstats {
+ __u32 maxpacket; /* largest packet we've seen so far */
+ __u32 count; /* how many drops we've done since the last time we
+ * entered dropping state
+ */
+ __u32 lastcount; /* count at entry to dropping state */
+ __u32 ldelay; /* in-queue delay seen by most recently dequeued packet */
+ __s32 drop_next; /* time to drop next packet */
+ __u32 drop_overlimit; /* number of time max qdisc packet limit was hit */
+ __u32 ecn_mark; /* number of packets we ECN marked instead of dropped */
+ __u32 dropping; /* are we in dropping state ? */
+ __u32 ce_mark; /* number of CE marked packets because of ce_threshold */
+};
+
+/* FQ_CODEL */
+
+#define FQ_CODEL_QUANTUM_MAX (1 << 20)
+
+enum {
+ TCA_FQ_CODEL_UNSPEC,
+ TCA_FQ_CODEL_TARGET,
+ TCA_FQ_CODEL_LIMIT,
+ TCA_FQ_CODEL_INTERVAL,
+ TCA_FQ_CODEL_ECN,
+ TCA_FQ_CODEL_FLOWS,
+ TCA_FQ_CODEL_QUANTUM,
+ TCA_FQ_CODEL_CE_THRESHOLD,
+ TCA_FQ_CODEL_DROP_BATCH_SIZE,
+ TCA_FQ_CODEL_MEMORY_LIMIT,
+ TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR,
+ TCA_FQ_CODEL_CE_THRESHOLD_MASK,
+ __TCA_FQ_CODEL_MAX
+};
+
+#define TCA_FQ_CODEL_MAX (__TCA_FQ_CODEL_MAX - 1)
+
+enum {
+ TCA_FQ_CODEL_XSTATS_QDISC,
+ TCA_FQ_CODEL_XSTATS_CLASS,
+};
+
+struct tc_fq_codel_qd_stats {
+ __u32 maxpacket; /* largest packet we've seen so far */
+ __u32 drop_overlimit; /* number of time max qdisc
+ * packet limit was hit
+ */
+ __u32 ecn_mark; /* number of packets we ECN marked
+ * instead of being dropped
+ */
+ __u32 new_flow_count; /* number of time packets
+ * created a 'new flow'
+ */
+ __u32 new_flows_len; /* count of flows in new list */
+ __u32 old_flows_len; /* count of flows in old list */
+ __u32 ce_mark; /* packets above ce_threshold */
+ __u32 memory_usage; /* in bytes */
+ __u32 drop_overmemory;
+};
+
+struct tc_fq_codel_cl_stats {
+ __s32 deficit;
+ __u32 ldelay; /* in-queue delay seen by most recently
+ * dequeued packet
+ */
+ __u32 count;
+ __u32 lastcount;
+ __u32 dropping;
+ __s32 drop_next;
+};
+
+struct tc_fq_codel_xstats {
+ __u32 type;
+ union {
+ struct tc_fq_codel_qd_stats qdisc_stats;
+ struct tc_fq_codel_cl_stats class_stats;
+ };
+};
+
+/* FQ */
+
+enum {
+ TCA_FQ_UNSPEC,
+
+ TCA_FQ_PLIMIT, /* limit of total number of packets in queue */
+
+ TCA_FQ_FLOW_PLIMIT, /* limit of packets per flow */
+
+ TCA_FQ_QUANTUM, /* RR quantum */
+
+ TCA_FQ_INITIAL_QUANTUM, /* RR quantum for new flow */
+
+ TCA_FQ_RATE_ENABLE, /* enable/disable rate limiting */
+
+ TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */
+
+ TCA_FQ_FLOW_MAX_RATE, /* per flow max rate */
+
+ TCA_FQ_BUCKETS_LOG, /* log2(number of buckets) */
+
+ TCA_FQ_FLOW_REFILL_DELAY, /* flow credit refill delay in usec */
+
+ TCA_FQ_ORPHAN_MASK, /* mask applied to orphaned skb hashes */
+
+ TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */
+
+ TCA_FQ_CE_THRESHOLD, /* DCTCP-like CE-marking threshold */
+
+ TCA_FQ_TIMER_SLACK, /* timer slack */
+
+ TCA_FQ_HORIZON, /* time horizon in us */
+
+ TCA_FQ_HORIZON_DROP, /* drop packets beyond horizon, or cap their EDT */
+
+ TCA_FQ_PRIOMAP, /* prio2band */
+
+ TCA_FQ_WEIGHTS, /* Weights for each band */
+
+ __TCA_FQ_MAX
+};
+
+#define TCA_FQ_MAX (__TCA_FQ_MAX - 1)
+
+#define FQ_BANDS 3
+#define FQ_MIN_WEIGHT 16384
+
+struct tc_fq_qd_stats {
+ __u64 gc_flows;
+ __u64 highprio_packets; /* obsolete */
+ __u64 tcp_retrans; /* obsolete */
+ __u64 throttled;
+ __u64 flows_plimit;
+ __u64 pkts_too_long;
+ __u64 allocation_errors;
+ __s64 time_next_delayed_flow;
+ __u32 flows;
+ __u32 inactive_flows;
+ __u32 throttled_flows;
+ __u32 unthrottle_latency_ns;
+ __u64 ce_mark; /* packets above ce_threshold */
+ __u64 horizon_drops;
+ __u64 horizon_caps;
+ __u64 fastpath_packets;
+ __u64 band_drops[FQ_BANDS];
+ __u32 band_pkt_count[FQ_BANDS];
+ __u32 pad;
+};
+
+/* Heavy-Hitter Filter */
+
+enum {
+ TCA_HHF_UNSPEC,
+ TCA_HHF_BACKLOG_LIMIT,
+ TCA_HHF_QUANTUM,
+ TCA_HHF_HH_FLOWS_LIMIT,
+ TCA_HHF_RESET_TIMEOUT,
+ TCA_HHF_ADMIT_BYTES,
+ TCA_HHF_EVICT_TIMEOUT,
+ TCA_HHF_NON_HH_WEIGHT,
+ __TCA_HHF_MAX
+};
+
+#define TCA_HHF_MAX (__TCA_HHF_MAX - 1)
+
+struct tc_hhf_xstats {
+ __u32 drop_overlimit; /* number of times max qdisc packet limit
+ * was hit
+ */
+ __u32 hh_overlimit; /* number of times max heavy-hitters was hit */
+ __u32 hh_tot_count; /* number of captured heavy-hitters so far */
+ __u32 hh_cur_count; /* number of current heavy-hitters */
+};
+
+/* PIE */
+enum {
+ TCA_PIE_UNSPEC,
+ TCA_PIE_TARGET,
+ TCA_PIE_LIMIT,
+ TCA_PIE_TUPDATE,
+ TCA_PIE_ALPHA,
+ TCA_PIE_BETA,
+ TCA_PIE_ECN,
+ TCA_PIE_BYTEMODE,
+ TCA_PIE_DQ_RATE_ESTIMATOR,
+ __TCA_PIE_MAX
+};
+#define TCA_PIE_MAX (__TCA_PIE_MAX - 1)
+
+struct tc_pie_xstats {
+ __u64 prob; /* current probability */
+ __u32 delay; /* current delay in ms */
+ __u32 avg_dq_rate; /* current average dq_rate in
+ * bits/pie_time
+ */
+ __u32 dq_rate_estimating; /* is avg_dq_rate being calculated? */
+ __u32 packets_in; /* total number of packets enqueued */
+ __u32 dropped; /* packets dropped due to pie_action */
+ __u32 overlimit; /* dropped due to lack of space
+ * in queue
+ */
+ __u32 maxq; /* maximum queue size */
+ __u32 ecn_mark; /* packets marked with ecn*/
+};
+
+/* FQ PIE */
+enum {
+ TCA_FQ_PIE_UNSPEC,
+ TCA_FQ_PIE_LIMIT,
+ TCA_FQ_PIE_FLOWS,
+ TCA_FQ_PIE_TARGET,
+ TCA_FQ_PIE_TUPDATE,
+ TCA_FQ_PIE_ALPHA,
+ TCA_FQ_PIE_BETA,
+ TCA_FQ_PIE_QUANTUM,
+ TCA_FQ_PIE_MEMORY_LIMIT,
+ TCA_FQ_PIE_ECN_PROB,
+ TCA_FQ_PIE_ECN,
+ TCA_FQ_PIE_BYTEMODE,
+ TCA_FQ_PIE_DQ_RATE_ESTIMATOR,
+ __TCA_FQ_PIE_MAX
+};
+#define TCA_FQ_PIE_MAX (__TCA_FQ_PIE_MAX - 1)
+
+struct tc_fq_pie_xstats {
+ __u32 packets_in; /* total number of packets enqueued */
+ __u32 dropped; /* packets dropped due to fq_pie_action */
+ __u32 overlimit; /* dropped due to lack of space in queue */
+ __u32 overmemory; /* dropped due to lack of memory in queue */
+ __u32 ecn_mark; /* packets marked with ecn */
+ __u32 new_flow_count; /* count of new flows created by packets */
+ __u32 new_flows_len; /* count of flows in new list */
+ __u32 old_flows_len; /* count of flows in old list */
+ __u32 memory_usage; /* total memory across all queues */
+};
+
+/* CBS */
+struct tc_cbs_qopt {
+ __u8 offload;
+ __u8 _pad[3];
+ __s32 hicredit;
+ __s32 locredit;
+ __s32 idleslope;
+ __s32 sendslope;
+};
+
+enum {
+ TCA_CBS_UNSPEC,
+ TCA_CBS_PARMS,
+ __TCA_CBS_MAX,
+};
+
+#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
+
+/* ETF */
+struct tc_etf_qopt {
+ __s32 delta;
+ __s32 clockid;
+ __u32 flags;
+#define TC_ETF_DEADLINE_MODE_ON _BITUL(0)
+#define TC_ETF_OFFLOAD_ON _BITUL(1)
+#define TC_ETF_SKIP_SOCK_CHECK _BITUL(2)
+};
+
+enum {
+ TCA_ETF_UNSPEC,
+ TCA_ETF_PARMS,
+ __TCA_ETF_MAX,
+};
+
+#define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
+
+
+/* CAKE */
+enum {
+ TCA_CAKE_UNSPEC,
+ TCA_CAKE_PAD,
+ TCA_CAKE_BASE_RATE64,
+ TCA_CAKE_DIFFSERV_MODE,
+ TCA_CAKE_ATM,
+ TCA_CAKE_FLOW_MODE,
+ TCA_CAKE_OVERHEAD,
+ TCA_CAKE_RTT,
+ TCA_CAKE_TARGET,
+ TCA_CAKE_AUTORATE,
+ TCA_CAKE_MEMORY,
+ TCA_CAKE_NAT,
+ TCA_CAKE_RAW,
+ TCA_CAKE_WASH,
+ TCA_CAKE_MPU,
+ TCA_CAKE_INGRESS,
+ TCA_CAKE_ACK_FILTER,
+ TCA_CAKE_SPLIT_GSO,
+ TCA_CAKE_FWMARK,
+ __TCA_CAKE_MAX
+};
+#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1)
+
+enum {
+ __TCA_CAKE_STATS_INVALID,
+ TCA_CAKE_STATS_PAD,
+ TCA_CAKE_STATS_CAPACITY_ESTIMATE64,
+ TCA_CAKE_STATS_MEMORY_LIMIT,
+ TCA_CAKE_STATS_MEMORY_USED,
+ TCA_CAKE_STATS_AVG_NETOFF,
+ TCA_CAKE_STATS_MIN_NETLEN,
+ TCA_CAKE_STATS_MAX_NETLEN,
+ TCA_CAKE_STATS_MIN_ADJLEN,
+ TCA_CAKE_STATS_MAX_ADJLEN,
+ TCA_CAKE_STATS_TIN_STATS,
+ TCA_CAKE_STATS_DEFICIT,
+ TCA_CAKE_STATS_COBALT_COUNT,
+ TCA_CAKE_STATS_DROPPING,
+ TCA_CAKE_STATS_DROP_NEXT_US,
+ TCA_CAKE_STATS_P_DROP,
+ TCA_CAKE_STATS_BLUE_TIMER_US,
+ __TCA_CAKE_STATS_MAX
+};
+#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1)
+
+enum {
+ __TCA_CAKE_TIN_STATS_INVALID,
+ TCA_CAKE_TIN_STATS_PAD,
+ TCA_CAKE_TIN_STATS_SENT_PACKETS,
+ TCA_CAKE_TIN_STATS_SENT_BYTES64,
+ TCA_CAKE_TIN_STATS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64,
+ TCA_CAKE_TIN_STATS_BACKLOG_PACKETS,
+ TCA_CAKE_TIN_STATS_BACKLOG_BYTES,
+ TCA_CAKE_TIN_STATS_THRESHOLD_RATE64,
+ TCA_CAKE_TIN_STATS_TARGET_US,
+ TCA_CAKE_TIN_STATS_INTERVAL_US,
+ TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS,
+ TCA_CAKE_TIN_STATS_WAY_MISSES,
+ TCA_CAKE_TIN_STATS_WAY_COLLISIONS,
+ TCA_CAKE_TIN_STATS_PEAK_DELAY_US,
+ TCA_CAKE_TIN_STATS_AVG_DELAY_US,
+ TCA_CAKE_TIN_STATS_BASE_DELAY_US,
+ TCA_CAKE_TIN_STATS_SPARSE_FLOWS,
+ TCA_CAKE_TIN_STATS_BULK_FLOWS,
+ TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS,
+ TCA_CAKE_TIN_STATS_MAX_SKBLEN,
+ TCA_CAKE_TIN_STATS_FLOW_QUANTUM,
+ __TCA_CAKE_TIN_STATS_MAX
+};
+#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1)
+#define TC_CAKE_MAX_TINS (8)
+
+enum {
+ CAKE_FLOW_NONE = 0,
+ CAKE_FLOW_SRC_IP,
+ CAKE_FLOW_DST_IP,
+ CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */
+ CAKE_FLOW_FLOWS,
+ CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_MAX,
+};
+
+enum {
+ CAKE_DIFFSERV_DIFFSERV3 = 0,
+ CAKE_DIFFSERV_DIFFSERV4,
+ CAKE_DIFFSERV_DIFFSERV8,
+ CAKE_DIFFSERV_BESTEFFORT,
+ CAKE_DIFFSERV_PRECEDENCE,
+ CAKE_DIFFSERV_MAX
+};
+
+enum {
+ CAKE_ACK_NONE = 0,
+ CAKE_ACK_FILTER,
+ CAKE_ACK_AGGRESSIVE,
+ CAKE_ACK_MAX
+};
+
+enum {
+ CAKE_ATM_NONE = 0,
+ CAKE_ATM_ATM,
+ CAKE_ATM_PTM,
+ CAKE_ATM_MAX
+};
+
+
+/* TAPRIO */
+enum {
+ TC_TAPRIO_CMD_SET_GATES = 0x00,
+ TC_TAPRIO_CMD_SET_AND_HOLD = 0x01,
+ TC_TAPRIO_CMD_SET_AND_RELEASE = 0x02,
+};
+
+enum {
+ TCA_TAPRIO_SCHED_ENTRY_UNSPEC,
+ TCA_TAPRIO_SCHED_ENTRY_INDEX, /* u32 */
+ TCA_TAPRIO_SCHED_ENTRY_CMD, /* u8 */
+ TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, /* u32 */
+ TCA_TAPRIO_SCHED_ENTRY_INTERVAL, /* u32 */
+ __TCA_TAPRIO_SCHED_ENTRY_MAX,
+};
+#define TCA_TAPRIO_SCHED_ENTRY_MAX (__TCA_TAPRIO_SCHED_ENTRY_MAX - 1)
+
+/* The format for schedule entry list is:
+ * [TCA_TAPRIO_SCHED_ENTRY_LIST]
+ * [TCA_TAPRIO_SCHED_ENTRY]
+ * [TCA_TAPRIO_SCHED_ENTRY_CMD]
+ * [TCA_TAPRIO_SCHED_ENTRY_GATES]
+ * [TCA_TAPRIO_SCHED_ENTRY_INTERVAL]
+ */
+enum {
+ TCA_TAPRIO_SCHED_UNSPEC,
+ TCA_TAPRIO_SCHED_ENTRY,
+ __TCA_TAPRIO_SCHED_MAX,
+};
+
+#define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1)
+
+/* The format for the admin sched (dump only):
+ * [TCA_TAPRIO_SCHED_ADMIN_SCHED]
+ * [TCA_TAPRIO_ATTR_SCHED_BASE_TIME]
+ * [TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]
+ * [TCA_TAPRIO_ATTR_SCHED_ENTRY]
+ * [TCA_TAPRIO_ATTR_SCHED_ENTRY_CMD]
+ * [TCA_TAPRIO_ATTR_SCHED_ENTRY_GATES]
+ * [TCA_TAPRIO_ATTR_SCHED_ENTRY_INTERVAL]
+ */
+
+#define TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST _BITUL(0)
+#define TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD _BITUL(1)
+
+enum {
+ TCA_TAPRIO_TC_ENTRY_UNSPEC,
+ TCA_TAPRIO_TC_ENTRY_INDEX, /* u32 */
+ TCA_TAPRIO_TC_ENTRY_MAX_SDU, /* u32 */
+ TCA_TAPRIO_TC_ENTRY_FP, /* u32 */
+
+ /* add new constants above here */
+ __TCA_TAPRIO_TC_ENTRY_CNT,
+ TCA_TAPRIO_TC_ENTRY_MAX = (__TCA_TAPRIO_TC_ENTRY_CNT - 1)
+};
+
+enum {
+ TCA_TAPRIO_OFFLOAD_STATS_PAD = 1, /* u64 */
+ TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS, /* u64 */
+ TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS, /* u64 */
+
+ /* add new constants above here */
+ __TCA_TAPRIO_OFFLOAD_STATS_CNT,
+ TCA_TAPRIO_OFFLOAD_STATS_MAX = (__TCA_TAPRIO_OFFLOAD_STATS_CNT - 1)
+};
+
+enum {
+ TCA_TAPRIO_ATTR_UNSPEC,
+ TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */
+ TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */
+ TCA_TAPRIO_ATTR_SCHED_BASE_TIME, /* s64 */
+ TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */
+ TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */
+ TCA_TAPRIO_PAD,
+ TCA_TAPRIO_ATTR_ADMIN_SCHED, /* The admin sched, only used in dump */
+ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */
+ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */
+ TCA_TAPRIO_ATTR_FLAGS, /* u32 */
+ TCA_TAPRIO_ATTR_TXTIME_DELAY, /* u32 */
+ TCA_TAPRIO_ATTR_TC_ENTRY, /* nest */
+ __TCA_TAPRIO_ATTR_MAX,
+};
+
+#define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1)
+
+/* ETS */
+
+#define TCQ_ETS_MAX_BANDS 16
+
+enum {
+ TCA_ETS_UNSPEC,
+ TCA_ETS_NBANDS, /* u8 */
+ TCA_ETS_NSTRICT, /* u8 */
+ TCA_ETS_QUANTA, /* nested TCA_ETS_QUANTA_BAND */
+ TCA_ETS_QUANTA_BAND, /* u32 */
+ TCA_ETS_PRIOMAP, /* nested TCA_ETS_PRIOMAP_BAND */
+ TCA_ETS_PRIOMAP_BAND, /* u8 */
+ __TCA_ETS_MAX,
+};
+
+#define TCA_ETS_MAX (__TCA_ETS_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/posix_types.h b/include/uapi/linux/posix_types.h
new file mode 100644
index 0000000..9a7a740
--- /dev/null
+++ b/include/uapi/linux/posix_types.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_POSIX_TYPES_H
+#define _LINUX_POSIX_TYPES_H
+
+#include <linux/stddef.h>
+
+/*
+ * This allows for 1024 file descriptors: if NR_OPEN is ever grown
+ * beyond that you'll have to change this too. But 1024 fd's seem to be
+ * enough even for such "real" unices like OSF/1, so hopefully this is
+ * one limit that doesn't have to be changed [again].
+ *
+ * Note that POSIX wants the FD_CLEAR(fd,fdsetp) defines to be in
+ * <sys/time.h> (and thus <linux/time.h>) - but this is a more logical
+ * place for them. Solved by having dummy defines in <sys/time.h>.
+ */
+
+/*
+ * This macro may have been defined in <gnu/types.h>. But we always
+ * use the one here.
+ */
+#undef __FD_SETSIZE
+#define __FD_SETSIZE 1024
+
+typedef struct {
+ unsigned long fds_bits[__FD_SETSIZE / (8 * sizeof(long))];
+} __kernel_fd_set;
+
+/* Type of a signal handler. */
+typedef void (*__kernel_sighandler_t)(int);
+
+/* Type of a SYSV IPC key. */
+typedef int __kernel_key_t;
+typedef int __kernel_mqd_t;
+
+#include <asm/posix_types.h>
+
+#endif /* _LINUX_POSIX_TYPES_H */
diff --git a/include/uapi/linux/ppp_defs.h b/include/uapi/linux/ppp_defs.h
new file mode 100644
index 0000000..b2cbb3b
--- /dev/null
+++ b/include/uapi/linux/ppp_defs.h
@@ -0,0 +1,165 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * ppp_defs.h - PPP definitions.
+ *
+ * Copyright 1994-2000 Paul Mackerras.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+#include <linux/types.h>
+
+#ifndef _PPP_DEFS_H_
+#define _PPP_DEFS_H_
+
+/*
+ * The basic PPP frame.
+ */
+#define PPP_HDRLEN 4 /* octets for standard ppp header */
+#define PPP_FCSLEN 2 /* octets for FCS */
+#define PPP_MRU 1500 /* default MRU = max length of info field */
+
+#define PPP_ADDRESS(p) (((__u8 *)(p))[0])
+#define PPP_CONTROL(p) (((__u8 *)(p))[1])
+#define PPP_PROTOCOL(p) ((((__u8 *)(p))[2] << 8) + ((__u8 *)(p))[3])
+
+/*
+ * Significant octet values.
+ */
+#define PPP_ALLSTATIONS 0xff /* All-Stations broadcast address */
+#define PPP_UI 0x03 /* Unnumbered Information */
+#define PPP_FLAG 0x7e /* Flag Sequence */
+#define PPP_ESCAPE 0x7d /* Asynchronous Control Escape */
+#define PPP_TRANS 0x20 /* Asynchronous transparency modifier */
+
+/*
+ * Protocol field values.
+ */
+#define PPP_IP 0x21 /* Internet Protocol */
+#define PPP_AT 0x29 /* AppleTalk Protocol */
+#define PPP_IPX 0x2b /* IPX protocol */
+#define PPP_VJC_COMP 0x2d /* VJ compressed TCP */
+#define PPP_VJC_UNCOMP 0x2f /* VJ uncompressed TCP */
+#define PPP_MP 0x3d /* Multilink protocol */
+#define PPP_IPV6 0x57 /* Internet Protocol Version 6 */
+#define PPP_COMPFRAG 0xfb /* fragment compressed below bundle */
+#define PPP_COMP 0xfd /* compressed packet */
+#define PPP_MPLS_UC 0x0281 /* Multi Protocol Label Switching - Unicast */
+#define PPP_MPLS_MC 0x0283 /* Multi Protocol Label Switching - Multicast */
+#define PPP_IPCP 0x8021 /* IP Control Protocol */
+#define PPP_ATCP 0x8029 /* AppleTalk Control Protocol */
+#define PPP_IPXCP 0x802b /* IPX Control Protocol */
+#define PPP_IPV6CP 0x8057 /* IPv6 Control Protocol */
+#define PPP_CCPFRAG 0x80fb /* CCP at link level (below MP bundle) */
+#define PPP_CCP 0x80fd /* Compression Control Protocol */
+#define PPP_MPLSCP 0x80fd /* MPLS Control Protocol */
+#define PPP_LCP 0xc021 /* Link Control Protocol */
+#define PPP_PAP 0xc023 /* Password Authentication Protocol */
+#define PPP_LQR 0xc025 /* Link Quality Report protocol */
+#define PPP_CHAP 0xc223 /* Cryptographic Handshake Auth. Protocol */
+#define PPP_CBCP 0xc029 /* Callback Control Protocol */
+
+/*
+ * Values for FCS calculations.
+ */
+
+#define PPP_INITFCS 0xffff /* Initial FCS value */
+#define PPP_GOODFCS 0xf0b8 /* Good final FCS value */
+
+
+/*
+ * Extended asyncmap - allows any character to be escaped.
+ */
+
+typedef __u32 ext_accm[8];
+
+/*
+ * What to do with network protocol (NP) packets.
+ */
+enum NPmode {
+ NPMODE_PASS, /* pass the packet through */
+ NPMODE_DROP, /* silently drop the packet */
+ NPMODE_ERROR, /* return an error */
+ NPMODE_QUEUE /* save it up for later. */
+};
+
+/*
+ * Statistics for LQRP and pppstats
+ */
+struct pppstat {
+ __u32 ppp_discards; /* # frames discarded */
+
+ __u32 ppp_ibytes; /* bytes received */
+ __u32 ppp_ioctects; /* bytes received not in error */
+ __u32 ppp_ipackets; /* packets received */
+ __u32 ppp_ierrors; /* receive errors */
+ __u32 ppp_ilqrs; /* # LQR frames received */
+
+ __u32 ppp_obytes; /* raw bytes sent */
+ __u32 ppp_ooctects; /* frame bytes sent */
+ __u32 ppp_opackets; /* packets sent */
+ __u32 ppp_oerrors; /* transmit errors */
+ __u32 ppp_olqrs; /* # LQR frames sent */
+};
+
+struct vjstat {
+ __u32 vjs_packets; /* outbound packets */
+ __u32 vjs_compressed; /* outbound compressed packets */
+ __u32 vjs_searches; /* searches for connection state */
+ __u32 vjs_misses; /* times couldn't find conn. state */
+ __u32 vjs_uncompressedin; /* inbound uncompressed packets */
+ __u32 vjs_compressedin; /* inbound compressed packets */
+ __u32 vjs_errorin; /* inbound unknown type packets */
+ __u32 vjs_tossed; /* inbound packets tossed because of error */
+};
+
+struct compstat {
+ __u32 unc_bytes; /* total uncompressed bytes */
+ __u32 unc_packets; /* total uncompressed packets */
+ __u32 comp_bytes; /* compressed bytes */
+ __u32 comp_packets; /* compressed packets */
+ __u32 inc_bytes; /* incompressible bytes */
+ __u32 inc_packets; /* incompressible packets */
+
+ /* the compression ratio is defined as in_count / bytes_out */
+ __u32 in_count; /* Bytes received */
+ __u32 bytes_out; /* Bytes transmitted */
+
+ double ratio; /* not computed in kernel. */
+};
+
+struct ppp_stats {
+ struct pppstat p; /* basic PPP statistics */
+ struct vjstat vj; /* VJ header compression statistics */
+};
+
+struct ppp_comp_stats {
+ struct compstat c; /* packet compression statistics */
+ struct compstat d; /* packet decompression statistics */
+};
+
+/*
+ * The following structure records the time in seconds since
+ * the last NP packet was sent or received.
+ *
+ * Linux implements both 32-bit and 64-bit time_t versions
+ * for compatibility with user space that defines ppp_idle
+ * based on the libc time_t.
+ */
+struct ppp_idle {
+ __kernel_old_time_t xmit_idle; /* time since last NP packet sent */
+ __kernel_old_time_t recv_idle; /* time since last NP packet received */
+};
+
+struct ppp_idle32 {
+ __s32 xmit_idle; /* time since last NP packet sent */
+ __s32 recv_idle; /* time since last NP packet received */
+};
+
+struct ppp_idle64 {
+ __s64 xmit_idle; /* time since last NP packet sent */
+ __s64 recv_idle; /* time since last NP packet received */
+};
+
+#endif /* _PPP_DEFS_H_ */
diff --git a/include/uapi/linux/rose.h b/include/uapi/linux/rose.h
new file mode 100644
index 0000000..19aa469
--- /dev/null
+++ b/include/uapi/linux/rose.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * These are the public elements of the Linux kernel Rose implementation.
+ * For kernel AX.25 see the file ax25.h. This file requires ax25.h for the
+ * definition of the ax25_address structure.
+ */
+
+#ifndef ROSE_KERNEL_H
+#define ROSE_KERNEL_H
+
+#include <linux/socket.h>
+#include <linux/ax25.h>
+
+#define ROSE_MTU 251
+
+#define ROSE_MAX_DIGIS 6
+
+#define ROSE_DEFER 1
+#define ROSE_T1 2
+#define ROSE_T2 3
+#define ROSE_T3 4
+#define ROSE_IDLE 5
+#define ROSE_QBITINCL 6
+#define ROSE_HOLDBACK 7
+
+#define SIOCRSGCAUSE (SIOCPROTOPRIVATE+0)
+#define SIOCRSSCAUSE (SIOCPROTOPRIVATE+1)
+#define SIOCRSL2CALL (SIOCPROTOPRIVATE+2)
+#define SIOCRSSL2CALL (SIOCPROTOPRIVATE+2)
+#define SIOCRSACCEPT (SIOCPROTOPRIVATE+3)
+#define SIOCRSCLRRT (SIOCPROTOPRIVATE+4)
+#define SIOCRSGL2CALL (SIOCPROTOPRIVATE+5)
+#define SIOCRSGFACILITIES (SIOCPROTOPRIVATE+6)
+
+#define ROSE_DTE_ORIGINATED 0x00
+#define ROSE_NUMBER_BUSY 0x01
+#define ROSE_INVALID_FACILITY 0x03
+#define ROSE_NETWORK_CONGESTION 0x05
+#define ROSE_OUT_OF_ORDER 0x09
+#define ROSE_ACCESS_BARRED 0x0B
+#define ROSE_NOT_OBTAINABLE 0x0D
+#define ROSE_REMOTE_PROCEDURE 0x11
+#define ROSE_LOCAL_PROCEDURE 0x13
+#define ROSE_SHIP_ABSENT 0x39
+
+typedef struct {
+ char rose_addr[5];
+} rose_address;
+
+struct sockaddr_rose {
+ __kernel_sa_family_t srose_family;
+ rose_address srose_addr;
+ ax25_address srose_call;
+ int srose_ndigis;
+ ax25_address srose_digi;
+};
+
+struct full_sockaddr_rose {
+ __kernel_sa_family_t srose_family;
+ rose_address srose_addr;
+ ax25_address srose_call;
+ unsigned int srose_ndigis;
+ ax25_address srose_digis[ROSE_MAX_DIGIS];
+};
+
+struct rose_route_struct {
+ rose_address address;
+ unsigned short mask;
+ ax25_address neighbour;
+ char device[16];
+ unsigned char ndigis;
+ ax25_address digipeaters[AX25_MAX_DIGIS];
+};
+
+struct rose_cause_struct {
+ unsigned char cause;
+ unsigned char diagnostic;
+};
+
+struct rose_facilities_struct {
+ rose_address source_addr, dest_addr;
+ ax25_address source_call, dest_call;
+ unsigned char source_ndigis, dest_ndigis;
+ ax25_address source_digis[ROSE_MAX_DIGIS];
+ ax25_address dest_digis[ROSE_MAX_DIGIS];
+ unsigned int rand;
+ rose_address fail_addr;
+ ax25_address fail_call;
+};
+
+#endif
diff --git a/include/uapi/linux/rpl.h b/include/uapi/linux/rpl.h
new file mode 100644
index 0000000..42580b3
--- /dev/null
+++ b/include/uapi/linux/rpl.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * IPv6 RPL-SR implementation
+ *
+ * Author:
+ * (C) 2020 Alexander Aring <alex.aring@gmail.com>
+ */
+
+#ifndef _LINUX_RPL_H
+#define _LINUX_RPL_H
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+#include <linux/in6.h>
+
+/*
+ * RPL SR Header
+ */
+struct ipv6_rpl_sr_hdr {
+ __u8 nexthdr;
+ __u8 hdrlen;
+ __u8 type;
+ __u8 segments_left;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u32 cmpre:4,
+ cmpri:4,
+ reserved:4,
+ pad:4,
+ reserved1:16;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u32 cmpri:4,
+ cmpre:4,
+ pad:4,
+ reserved:20;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+
+ union {
+ __DECLARE_FLEX_ARRAY(struct in6_addr, addr);
+ __DECLARE_FLEX_ARRAY(__u8, data);
+ } segments;
+} __attribute__((packed));
+
+#define rpl_segaddr segments.addr
+#define rpl_segdata segments.data
+
+#endif
diff --git a/include/uapi/linux/rpl_iptunnel.h b/include/uapi/linux/rpl_iptunnel.h
new file mode 100644
index 0000000..c255b92
--- /dev/null
+++ b/include/uapi/linux/rpl_iptunnel.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * IPv6 RPL-SR implementation
+ *
+ * Author:
+ * (C) 2020 Alexander Aring <alex.aring@gmail.com>
+ */
+
+#ifndef _LINUX_RPL_IPTUNNEL_H
+#define _LINUX_RPL_IPTUNNEL_H
+
+enum {
+ RPL_IPTUNNEL_UNSPEC,
+ RPL_IPTUNNEL_SRH,
+ __RPL_IPTUNNEL_MAX,
+};
+#define RPL_IPTUNNEL_MAX (__RPL_IPTUNNEL_MAX - 1)
+
+#define RPL_IPTUNNEL_SRH_SIZE(srh) (((srh)->hdrlen + 1) << 3)
+
+#endif
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
new file mode 100644
index 0000000..4e6c8e1
--- /dev/null
+++ b/include/uapi/linux/rtnetlink.h
@@ -0,0 +1,830 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_RTNETLINK_H
+#define __LINUX_RTNETLINK_H
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+#include <linux/if_link.h>
+#include <linux/if_addr.h>
+#include <linux/neighbour.h>
+
+/* rtnetlink families. Values up to 127 are reserved for real address
+ * families, values above 128 may be used arbitrarily.
+ */
+#define RTNL_FAMILY_IPMR 128
+#define RTNL_FAMILY_IP6MR 129
+#define RTNL_FAMILY_MAX 129
+
+/****
+ * Routing/neighbour discovery messages.
+ ****/
+
+/* Types of messages */
+
+enum {
+ RTM_BASE = 16,
+#define RTM_BASE RTM_BASE
+
+ RTM_NEWLINK = 16,
+#define RTM_NEWLINK RTM_NEWLINK
+ RTM_DELLINK,
+#define RTM_DELLINK RTM_DELLINK
+ RTM_GETLINK,
+#define RTM_GETLINK RTM_GETLINK
+ RTM_SETLINK,
+#define RTM_SETLINK RTM_SETLINK
+
+ RTM_NEWADDR = 20,
+#define RTM_NEWADDR RTM_NEWADDR
+ RTM_DELADDR,
+#define RTM_DELADDR RTM_DELADDR
+ RTM_GETADDR,
+#define RTM_GETADDR RTM_GETADDR
+
+ RTM_NEWROUTE = 24,
+#define RTM_NEWROUTE RTM_NEWROUTE
+ RTM_DELROUTE,
+#define RTM_DELROUTE RTM_DELROUTE
+ RTM_GETROUTE,
+#define RTM_GETROUTE RTM_GETROUTE
+
+ RTM_NEWNEIGH = 28,
+#define RTM_NEWNEIGH RTM_NEWNEIGH
+ RTM_DELNEIGH,
+#define RTM_DELNEIGH RTM_DELNEIGH
+ RTM_GETNEIGH,
+#define RTM_GETNEIGH RTM_GETNEIGH
+
+ RTM_NEWRULE = 32,
+#define RTM_NEWRULE RTM_NEWRULE
+ RTM_DELRULE,
+#define RTM_DELRULE RTM_DELRULE
+ RTM_GETRULE,
+#define RTM_GETRULE RTM_GETRULE
+
+ RTM_NEWQDISC = 36,
+#define RTM_NEWQDISC RTM_NEWQDISC
+ RTM_DELQDISC,
+#define RTM_DELQDISC RTM_DELQDISC
+ RTM_GETQDISC,
+#define RTM_GETQDISC RTM_GETQDISC
+
+ RTM_NEWTCLASS = 40,
+#define RTM_NEWTCLASS RTM_NEWTCLASS
+ RTM_DELTCLASS,
+#define RTM_DELTCLASS RTM_DELTCLASS
+ RTM_GETTCLASS,
+#define RTM_GETTCLASS RTM_GETTCLASS
+
+ RTM_NEWTFILTER = 44,
+#define RTM_NEWTFILTER RTM_NEWTFILTER
+ RTM_DELTFILTER,
+#define RTM_DELTFILTER RTM_DELTFILTER
+ RTM_GETTFILTER,
+#define RTM_GETTFILTER RTM_GETTFILTER
+
+ RTM_NEWACTION = 48,
+#define RTM_NEWACTION RTM_NEWACTION
+ RTM_DELACTION,
+#define RTM_DELACTION RTM_DELACTION
+ RTM_GETACTION,
+#define RTM_GETACTION RTM_GETACTION
+
+ RTM_NEWPREFIX = 52,
+#define RTM_NEWPREFIX RTM_NEWPREFIX
+
+ RTM_GETMULTICAST = 58,
+#define RTM_GETMULTICAST RTM_GETMULTICAST
+
+ RTM_GETANYCAST = 62,
+#define RTM_GETANYCAST RTM_GETANYCAST
+
+ RTM_NEWNEIGHTBL = 64,
+#define RTM_NEWNEIGHTBL RTM_NEWNEIGHTBL
+ RTM_GETNEIGHTBL = 66,
+#define RTM_GETNEIGHTBL RTM_GETNEIGHTBL
+ RTM_SETNEIGHTBL,
+#define RTM_SETNEIGHTBL RTM_SETNEIGHTBL
+
+ RTM_NEWNDUSEROPT = 68,
+#define RTM_NEWNDUSEROPT RTM_NEWNDUSEROPT
+
+ RTM_NEWADDRLABEL = 72,
+#define RTM_NEWADDRLABEL RTM_NEWADDRLABEL
+ RTM_DELADDRLABEL,
+#define RTM_DELADDRLABEL RTM_DELADDRLABEL
+ RTM_GETADDRLABEL,
+#define RTM_GETADDRLABEL RTM_GETADDRLABEL
+
+ RTM_GETDCB = 78,
+#define RTM_GETDCB RTM_GETDCB
+ RTM_SETDCB,
+#define RTM_SETDCB RTM_SETDCB
+
+ RTM_NEWNETCONF = 80,
+#define RTM_NEWNETCONF RTM_NEWNETCONF
+ RTM_DELNETCONF,
+#define RTM_DELNETCONF RTM_DELNETCONF
+ RTM_GETNETCONF = 82,
+#define RTM_GETNETCONF RTM_GETNETCONF
+
+ RTM_NEWMDB = 84,
+#define RTM_NEWMDB RTM_NEWMDB
+ RTM_DELMDB = 85,
+#define RTM_DELMDB RTM_DELMDB
+ RTM_GETMDB = 86,
+#define RTM_GETMDB RTM_GETMDB
+
+ RTM_NEWNSID = 88,
+#define RTM_NEWNSID RTM_NEWNSID
+ RTM_DELNSID = 89,
+#define RTM_DELNSID RTM_DELNSID
+ RTM_GETNSID = 90,
+#define RTM_GETNSID RTM_GETNSID
+
+ RTM_NEWSTATS = 92,
+#define RTM_NEWSTATS RTM_NEWSTATS
+ RTM_GETSTATS = 94,
+#define RTM_GETSTATS RTM_GETSTATS
+ RTM_SETSTATS,
+#define RTM_SETSTATS RTM_SETSTATS
+
+ RTM_NEWCACHEREPORT = 96,
+#define RTM_NEWCACHEREPORT RTM_NEWCACHEREPORT
+
+ RTM_NEWCHAIN = 100,
+#define RTM_NEWCHAIN RTM_NEWCHAIN
+ RTM_DELCHAIN,
+#define RTM_DELCHAIN RTM_DELCHAIN
+ RTM_GETCHAIN,
+#define RTM_GETCHAIN RTM_GETCHAIN
+
+ RTM_NEWNEXTHOP = 104,
+#define RTM_NEWNEXTHOP RTM_NEWNEXTHOP
+ RTM_DELNEXTHOP,
+#define RTM_DELNEXTHOP RTM_DELNEXTHOP
+ RTM_GETNEXTHOP,
+#define RTM_GETNEXTHOP RTM_GETNEXTHOP
+
+ RTM_NEWLINKPROP = 108,
+#define RTM_NEWLINKPROP RTM_NEWLINKPROP
+ RTM_DELLINKPROP,
+#define RTM_DELLINKPROP RTM_DELLINKPROP
+ RTM_GETLINKPROP,
+#define RTM_GETLINKPROP RTM_GETLINKPROP
+
+ RTM_NEWVLAN = 112,
+#define RTM_NEWNVLAN RTM_NEWVLAN
+ RTM_DELVLAN,
+#define RTM_DELVLAN RTM_DELVLAN
+ RTM_GETVLAN,
+#define RTM_GETVLAN RTM_GETVLAN
+
+ RTM_NEWNEXTHOPBUCKET = 116,
+#define RTM_NEWNEXTHOPBUCKET RTM_NEWNEXTHOPBUCKET
+ RTM_DELNEXTHOPBUCKET,
+#define RTM_DELNEXTHOPBUCKET RTM_DELNEXTHOPBUCKET
+ RTM_GETNEXTHOPBUCKET,
+#define RTM_GETNEXTHOPBUCKET RTM_GETNEXTHOPBUCKET
+
+ RTM_NEWTUNNEL = 120,
+#define RTM_NEWTUNNEL RTM_NEWTUNNEL
+ RTM_DELTUNNEL,
+#define RTM_DELTUNNEL RTM_DELTUNNEL
+ RTM_GETTUNNEL,
+#define RTM_GETTUNNEL RTM_GETTUNNEL
+
+ __RTM_MAX,
+#define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1)
+};
+
+#define RTM_NR_MSGTYPES (RTM_MAX + 1 - RTM_BASE)
+#define RTM_NR_FAMILIES (RTM_NR_MSGTYPES >> 2)
+#define RTM_FAM(cmd) (((cmd) - RTM_BASE) >> 2)
+
+/*
+ Generic structure for encapsulation of optional route information.
+ It is reminiscent of sockaddr, but with sa_family replaced
+ with attribute type.
+ */
+
+struct rtattr {
+ unsigned short rta_len;
+ unsigned short rta_type;
+};
+
+/* Macros to handle rtattributes */
+
+#define RTA_ALIGNTO 4U
+#define RTA_ALIGN(len) ( ((len)+RTA_ALIGNTO-1) & ~(RTA_ALIGNTO-1) )
+#define RTA_OK(rta,len) ((len) >= (int)sizeof(struct rtattr) && \
+ (rta)->rta_len >= sizeof(struct rtattr) && \
+ (rta)->rta_len <= (len))
+#define RTA_NEXT(rta,attrlen) ((attrlen) -= RTA_ALIGN((rta)->rta_len), \
+ (struct rtattr*)(((char*)(rta)) + RTA_ALIGN((rta)->rta_len)))
+#define RTA_LENGTH(len) (RTA_ALIGN(sizeof(struct rtattr)) + (len))
+#define RTA_SPACE(len) RTA_ALIGN(RTA_LENGTH(len))
+#define RTA_DATA(rta) ((void*)(((char*)(rta)) + RTA_LENGTH(0)))
+#define RTA_PAYLOAD(rta) ((int)((rta)->rta_len) - RTA_LENGTH(0))
+
+
+
+
+/******************************************************************************
+ * Definitions used in routing table administration.
+ ****/
+
+struct rtmsg {
+ unsigned char rtm_family;
+ unsigned char rtm_dst_len;
+ unsigned char rtm_src_len;
+ unsigned char rtm_tos;
+
+ unsigned char rtm_table; /* Routing table id */
+ unsigned char rtm_protocol; /* Routing protocol; see below */
+ unsigned char rtm_scope; /* See below */
+ unsigned char rtm_type; /* See below */
+
+ unsigned rtm_flags;
+};
+
+/* rtm_type */
+
+enum {
+ RTN_UNSPEC,
+ RTN_UNICAST, /* Gateway or direct route */
+ RTN_LOCAL, /* Accept locally */
+ RTN_BROADCAST, /* Accept locally as broadcast,
+ send as broadcast */
+ RTN_ANYCAST, /* Accept locally as broadcast,
+ but send as unicast */
+ RTN_MULTICAST, /* Multicast route */
+ RTN_BLACKHOLE, /* Drop */
+ RTN_UNREACHABLE, /* Destination is unreachable */
+ RTN_PROHIBIT, /* Administratively prohibited */
+ RTN_THROW, /* Not in this table */
+ RTN_NAT, /* Translate this address */
+ RTN_XRESOLVE, /* Use external resolver */
+ __RTN_MAX
+};
+
+#define RTN_MAX (__RTN_MAX - 1)
+
+
+/* rtm_protocol */
+
+#define RTPROT_UNSPEC 0
+#define RTPROT_REDIRECT 1 /* Route installed by ICMP redirects;
+ not used by current IPv4 */
+#define RTPROT_KERNEL 2 /* Route installed by kernel */
+#define RTPROT_BOOT 3 /* Route installed during boot */
+#define RTPROT_STATIC 4 /* Route installed by administrator */
+
+/* Values of protocol >= RTPROT_STATIC are not interpreted by kernel;
+ they are just passed from user and back as is.
+ It will be used by hypothetical multiple routing daemons.
+ Note that protocol values should be standardized in order to
+ avoid conflicts.
+ */
+
+#define RTPROT_GATED 8 /* Apparently, GateD */
+#define RTPROT_RA 9 /* RDISC/ND router advertisements */
+#define RTPROT_MRT 10 /* Merit MRT */
+#define RTPROT_ZEBRA 11 /* Zebra */
+#define RTPROT_BIRD 12 /* BIRD */
+#define RTPROT_DNROUTED 13 /* DECnet routing daemon */
+#define RTPROT_XORP 14 /* XORP */
+#define RTPROT_NTK 15 /* Netsukuku */
+#define RTPROT_DHCP 16 /* DHCP client */
+#define RTPROT_MROUTED 17 /* Multicast daemon */
+#define RTPROT_KEEPALIVED 18 /* Keepalived daemon */
+#define RTPROT_BABEL 42 /* Babel daemon */
+#define RTPROT_OPENR 99 /* Open Routing (Open/R) Routes */
+#define RTPROT_BGP 186 /* BGP Routes */
+#define RTPROT_ISIS 187 /* ISIS Routes */
+#define RTPROT_OSPF 188 /* OSPF Routes */
+#define RTPROT_RIP 189 /* RIP Routes */
+#define RTPROT_EIGRP 192 /* EIGRP Routes */
+
+/* rtm_scope
+
+ Really it is not scope, but sort of distance to the destination.
+ NOWHERE are reserved for not existing destinations, HOST is our
+ local addresses, LINK are destinations, located on directly attached
+ link and UNIVERSE is everywhere in the Universe.
+
+ Intermediate values are also possible f.e. interior routes
+ could be assigned a value between UNIVERSE and LINK.
+*/
+
+enum rt_scope_t {
+ RT_SCOPE_UNIVERSE=0,
+/* User defined values */
+ RT_SCOPE_SITE=200,
+ RT_SCOPE_LINK=253,
+ RT_SCOPE_HOST=254,
+ RT_SCOPE_NOWHERE=255
+};
+
+/* rtm_flags */
+
+#define RTM_F_NOTIFY 0x100 /* Notify user of route change */
+#define RTM_F_CLONED 0x200 /* This route is cloned */
+#define RTM_F_EQUALIZE 0x400 /* Multipath equalizer: NI */
+#define RTM_F_PREFIX 0x800 /* Prefix addresses */
+#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */
+#define RTM_F_FIB_MATCH 0x2000 /* return full fib lookup match */
+#define RTM_F_OFFLOAD 0x4000 /* route is offloaded */
+#define RTM_F_TRAP 0x8000 /* route is trapping packets */
+#define RTM_F_OFFLOAD_FAILED 0x20000000 /* route offload failed, this value
+ * is chosen to avoid conflicts with
+ * other flags defined in
+ * include/uapi/linux/ipv6_route.h
+ */
+
+/* Reserved table identifiers */
+
+enum rt_class_t {
+ RT_TABLE_UNSPEC=0,
+/* User defined values */
+ RT_TABLE_COMPAT=252,
+ RT_TABLE_DEFAULT=253,
+ RT_TABLE_MAIN=254,
+ RT_TABLE_LOCAL=255,
+ RT_TABLE_MAX=0xFFFFFFFF
+};
+
+
+/* Routing message attributes */
+
+enum rtattr_type_t {
+ RTA_UNSPEC,
+ RTA_DST,
+ RTA_SRC,
+ RTA_IIF,
+ RTA_OIF,
+ RTA_GATEWAY,
+ RTA_PRIORITY,
+ RTA_PREFSRC,
+ RTA_METRICS,
+ RTA_MULTIPATH,
+ RTA_PROTOINFO, /* no longer used */
+ RTA_FLOW,
+ RTA_CACHEINFO,
+ RTA_SESSION, /* no longer used */
+ RTA_MP_ALGO, /* no longer used */
+ RTA_TABLE,
+ RTA_MARK,
+ RTA_MFC_STATS,
+ RTA_VIA,
+ RTA_NEWDST,
+ RTA_PREF,
+ RTA_ENCAP_TYPE,
+ RTA_ENCAP,
+ RTA_EXPIRES,
+ RTA_PAD,
+ RTA_UID,
+ RTA_TTL_PROPAGATE,
+ RTA_IP_PROTO,
+ RTA_SPORT,
+ RTA_DPORT,
+ RTA_NH_ID,
+ __RTA_MAX
+};
+
+#define RTA_MAX (__RTA_MAX - 1)
+
+#define RTM_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct rtmsg))))
+#define RTM_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct rtmsg))
+
+/* RTM_MULTIPATH --- array of struct rtnexthop.
+ *
+ * "struct rtnexthop" describes all necessary nexthop information,
+ * i.e. parameters of path to a destination via this nexthop.
+ *
+ * At the moment it is impossible to set different prefsrc, mtu, window
+ * and rtt for different paths from multipath.
+ */
+
+struct rtnexthop {
+ unsigned short rtnh_len;
+ unsigned char rtnh_flags;
+ unsigned char rtnh_hops;
+ int rtnh_ifindex;
+};
+
+/* rtnh_flags */
+
+#define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */
+#define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */
+#define RTNH_F_ONLINK 4 /* Gateway is forced on link */
+#define RTNH_F_OFFLOAD 8 /* Nexthop is offloaded */
+#define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */
+#define RTNH_F_UNRESOLVED 32 /* The entry is unresolved (ipmr) */
+#define RTNH_F_TRAP 64 /* Nexthop is trapping packets */
+
+#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | \
+ RTNH_F_OFFLOAD | RTNH_F_TRAP)
+
+/* Macros to handle hexthops */
+
+#define RTNH_ALIGNTO 4
+#define RTNH_ALIGN(len) ( ((len)+RTNH_ALIGNTO-1) & ~(RTNH_ALIGNTO-1) )
+#define RTNH_OK(rtnh,len) ((rtnh)->rtnh_len >= sizeof(struct rtnexthop) && \
+ ((int)(rtnh)->rtnh_len) <= (len))
+#define RTNH_NEXT(rtnh) ((struct rtnexthop*)(((char*)(rtnh)) + RTNH_ALIGN((rtnh)->rtnh_len)))
+#define RTNH_LENGTH(len) (RTNH_ALIGN(sizeof(struct rtnexthop)) + (len))
+#define RTNH_SPACE(len) RTNH_ALIGN(RTNH_LENGTH(len))
+#define RTNH_DATA(rtnh) ((struct rtattr*)(((char*)(rtnh)) + RTNH_LENGTH(0)))
+
+/* RTA_VIA */
+struct rtvia {
+ __kernel_sa_family_t rtvia_family;
+ __u8 rtvia_addr[];
+};
+
+/* RTM_CACHEINFO */
+
+struct rta_cacheinfo {
+ __u32 rta_clntref;
+ __u32 rta_lastuse;
+ __s32 rta_expires;
+ __u32 rta_error;
+ __u32 rta_used;
+
+#define RTNETLINK_HAVE_PEERINFO 1
+ __u32 rta_id;
+ __u32 rta_ts;
+ __u32 rta_tsage;
+};
+
+/* RTM_METRICS --- array of struct rtattr with types of RTAX_* */
+
+enum {
+ RTAX_UNSPEC,
+#define RTAX_UNSPEC RTAX_UNSPEC
+ RTAX_LOCK,
+#define RTAX_LOCK RTAX_LOCK
+ RTAX_MTU,
+#define RTAX_MTU RTAX_MTU
+ RTAX_WINDOW,
+#define RTAX_WINDOW RTAX_WINDOW
+ RTAX_RTT,
+#define RTAX_RTT RTAX_RTT
+ RTAX_RTTVAR,
+#define RTAX_RTTVAR RTAX_RTTVAR
+ RTAX_SSTHRESH,
+#define RTAX_SSTHRESH RTAX_SSTHRESH
+ RTAX_CWND,
+#define RTAX_CWND RTAX_CWND
+ RTAX_ADVMSS,
+#define RTAX_ADVMSS RTAX_ADVMSS
+ RTAX_REORDERING,
+#define RTAX_REORDERING RTAX_REORDERING
+ RTAX_HOPLIMIT,
+#define RTAX_HOPLIMIT RTAX_HOPLIMIT
+ RTAX_INITCWND,
+#define RTAX_INITCWND RTAX_INITCWND
+ RTAX_FEATURES,
+#define RTAX_FEATURES RTAX_FEATURES
+ RTAX_RTO_MIN,
+#define RTAX_RTO_MIN RTAX_RTO_MIN
+ RTAX_INITRWND,
+#define RTAX_INITRWND RTAX_INITRWND
+ RTAX_QUICKACK,
+#define RTAX_QUICKACK RTAX_QUICKACK
+ RTAX_CC_ALGO,
+#define RTAX_CC_ALGO RTAX_CC_ALGO
+ RTAX_FASTOPEN_NO_COOKIE,
+#define RTAX_FASTOPEN_NO_COOKIE RTAX_FASTOPEN_NO_COOKIE
+ __RTAX_MAX
+};
+
+#define RTAX_MAX (__RTAX_MAX - 1)
+
+#define RTAX_FEATURE_ECN (1 << 0)
+#define RTAX_FEATURE_SACK (1 << 1) /* unused */
+#define RTAX_FEATURE_TIMESTAMP (1 << 2) /* unused */
+#define RTAX_FEATURE_ALLFRAG (1 << 3) /* unused */
+#define RTAX_FEATURE_TCP_USEC_TS (1 << 4)
+
+#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | \
+ RTAX_FEATURE_SACK | \
+ RTAX_FEATURE_TIMESTAMP | \
+ RTAX_FEATURE_ALLFRAG | \
+ RTAX_FEATURE_TCP_USEC_TS)
+
+struct rta_session {
+ __u8 proto;
+ __u8 pad1;
+ __u16 pad2;
+
+ union {
+ struct {
+ __u16 sport;
+ __u16 dport;
+ } ports;
+
+ struct {
+ __u8 type;
+ __u8 code;
+ __u16 ident;
+ } icmpt;
+
+ __u32 spi;
+ } u;
+};
+
+struct rta_mfc_stats {
+ __u64 mfcs_packets;
+ __u64 mfcs_bytes;
+ __u64 mfcs_wrong_if;
+};
+
+/****
+ * General form of address family dependent message.
+ ****/
+
+struct rtgenmsg {
+ unsigned char rtgen_family;
+};
+
+/*****************************************************************
+ * Link layer specific messages.
+ ****/
+
+/* struct ifinfomsg
+ * passes link level specific information, not dependent
+ * on network protocol.
+ */
+
+struct ifinfomsg {
+ unsigned char ifi_family;
+ unsigned char __ifi_pad;
+ unsigned short ifi_type; /* ARPHRD_* */
+ int ifi_index; /* Link index */
+ unsigned ifi_flags; /* IFF_* flags */
+ unsigned ifi_change; /* IFF_* change mask */
+};
+
+/********************************************************************
+ * prefix information
+ ****/
+
+struct prefixmsg {
+ unsigned char prefix_family;
+ unsigned char prefix_pad1;
+ unsigned short prefix_pad2;
+ int prefix_ifindex;
+ unsigned char prefix_type;
+ unsigned char prefix_len;
+ unsigned char prefix_flags;
+ unsigned char prefix_pad3;
+};
+
+enum
+{
+ PREFIX_UNSPEC,
+ PREFIX_ADDRESS,
+ PREFIX_CACHEINFO,
+ __PREFIX_MAX
+};
+
+#define PREFIX_MAX (__PREFIX_MAX - 1)
+
+struct prefix_cacheinfo {
+ __u32 preferred_time;
+ __u32 valid_time;
+};
+
+
+/*****************************************************************
+ * Traffic control messages.
+ ****/
+
+struct tcmsg {
+ unsigned char tcm_family;
+ unsigned char tcm__pad1;
+ unsigned short tcm__pad2;
+ int tcm_ifindex;
+ __u32 tcm_handle;
+ __u32 tcm_parent;
+/* tcm_block_index is used instead of tcm_parent
+ * in case tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK
+ */
+#define tcm_block_index tcm_parent
+ __u32 tcm_info;
+};
+
+/* For manipulation of filters in shared block, tcm_ifindex is set to
+ * TCM_IFINDEX_MAGIC_BLOCK, and tcm_parent is aliased to tcm_block_index
+ * which is the block index.
+ */
+#define TCM_IFINDEX_MAGIC_BLOCK (0xFFFFFFFFU)
+
+enum {
+ TCA_UNSPEC,
+ TCA_KIND,
+ TCA_OPTIONS,
+ TCA_STATS,
+ TCA_XSTATS,
+ TCA_RATE,
+ TCA_FCNT,
+ TCA_STATS2,
+ TCA_STAB,
+ TCA_PAD,
+ TCA_DUMP_INVISIBLE,
+ TCA_CHAIN,
+ TCA_HW_OFFLOAD,
+ TCA_INGRESS_BLOCK,
+ TCA_EGRESS_BLOCK,
+ TCA_DUMP_FLAGS,
+ TCA_EXT_WARN_MSG,
+ __TCA_MAX
+};
+
+#define TCA_MAX (__TCA_MAX - 1)
+
+#define TCA_DUMP_FLAGS_TERSE (1 << 0) /* Means that in dump user gets only basic
+ * data necessary to identify the objects
+ * (handle, cookie, etc.) and stats.
+ */
+
+#define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg))))
+#define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg))
+
+/********************************************************************
+ * Neighbor Discovery userland options
+ ****/
+
+struct nduseroptmsg {
+ unsigned char nduseropt_family;
+ unsigned char nduseropt_pad1;
+ unsigned short nduseropt_opts_len; /* Total length of options */
+ int nduseropt_ifindex;
+ __u8 nduseropt_icmp_type;
+ __u8 nduseropt_icmp_code;
+ unsigned short nduseropt_pad2;
+ unsigned int nduseropt_pad3;
+ /* Followed by one or more ND options */
+};
+
+enum {
+ NDUSEROPT_UNSPEC,
+ NDUSEROPT_SRCADDR,
+ __NDUSEROPT_MAX
+};
+
+#define NDUSEROPT_MAX (__NDUSEROPT_MAX - 1)
+
+/* RTnetlink multicast groups - backwards compatibility for userspace */
+#define RTMGRP_LINK 1
+#define RTMGRP_NOTIFY 2
+#define RTMGRP_NEIGH 4
+#define RTMGRP_TC 8
+
+#define RTMGRP_IPV4_IFADDR 0x10
+#define RTMGRP_IPV4_MROUTE 0x20
+#define RTMGRP_IPV4_ROUTE 0x40
+#define RTMGRP_IPV4_RULE 0x80
+
+#define RTMGRP_IPV6_IFADDR 0x100
+#define RTMGRP_IPV6_MROUTE 0x200
+#define RTMGRP_IPV6_ROUTE 0x400
+#define RTMGRP_IPV6_IFINFO 0x800
+
+#define RTMGRP_DECnet_IFADDR 0x1000
+#define RTMGRP_DECnet_ROUTE 0x4000
+
+#define RTMGRP_IPV6_PREFIX 0x20000
+
+/* RTnetlink multicast groups */
+enum rtnetlink_groups {
+ RTNLGRP_NONE,
+#define RTNLGRP_NONE RTNLGRP_NONE
+ RTNLGRP_LINK,
+#define RTNLGRP_LINK RTNLGRP_LINK
+ RTNLGRP_NOTIFY,
+#define RTNLGRP_NOTIFY RTNLGRP_NOTIFY
+ RTNLGRP_NEIGH,
+#define RTNLGRP_NEIGH RTNLGRP_NEIGH
+ RTNLGRP_TC,
+#define RTNLGRP_TC RTNLGRP_TC
+ RTNLGRP_IPV4_IFADDR,
+#define RTNLGRP_IPV4_IFADDR RTNLGRP_IPV4_IFADDR
+ RTNLGRP_IPV4_MROUTE,
+#define RTNLGRP_IPV4_MROUTE RTNLGRP_IPV4_MROUTE
+ RTNLGRP_IPV4_ROUTE,
+#define RTNLGRP_IPV4_ROUTE RTNLGRP_IPV4_ROUTE
+ RTNLGRP_IPV4_RULE,
+#define RTNLGRP_IPV4_RULE RTNLGRP_IPV4_RULE
+ RTNLGRP_IPV6_IFADDR,
+#define RTNLGRP_IPV6_IFADDR RTNLGRP_IPV6_IFADDR
+ RTNLGRP_IPV6_MROUTE,
+#define RTNLGRP_IPV6_MROUTE RTNLGRP_IPV6_MROUTE
+ RTNLGRP_IPV6_ROUTE,
+#define RTNLGRP_IPV6_ROUTE RTNLGRP_IPV6_ROUTE
+ RTNLGRP_IPV6_IFINFO,
+#define RTNLGRP_IPV6_IFINFO RTNLGRP_IPV6_IFINFO
+ RTNLGRP_DECnet_IFADDR,
+#define RTNLGRP_DECnet_IFADDR RTNLGRP_DECnet_IFADDR
+ RTNLGRP_NOP2,
+ RTNLGRP_DECnet_ROUTE,
+#define RTNLGRP_DECnet_ROUTE RTNLGRP_DECnet_ROUTE
+ RTNLGRP_DECnet_RULE,
+#define RTNLGRP_DECnet_RULE RTNLGRP_DECnet_RULE
+ RTNLGRP_NOP4,
+ RTNLGRP_IPV6_PREFIX,
+#define RTNLGRP_IPV6_PREFIX RTNLGRP_IPV6_PREFIX
+ RTNLGRP_IPV6_RULE,
+#define RTNLGRP_IPV6_RULE RTNLGRP_IPV6_RULE
+ RTNLGRP_ND_USEROPT,
+#define RTNLGRP_ND_USEROPT RTNLGRP_ND_USEROPT
+ RTNLGRP_PHONET_IFADDR,
+#define RTNLGRP_PHONET_IFADDR RTNLGRP_PHONET_IFADDR
+ RTNLGRP_PHONET_ROUTE,
+#define RTNLGRP_PHONET_ROUTE RTNLGRP_PHONET_ROUTE
+ RTNLGRP_DCB,
+#define RTNLGRP_DCB RTNLGRP_DCB
+ RTNLGRP_IPV4_NETCONF,
+#define RTNLGRP_IPV4_NETCONF RTNLGRP_IPV4_NETCONF
+ RTNLGRP_IPV6_NETCONF,
+#define RTNLGRP_IPV6_NETCONF RTNLGRP_IPV6_NETCONF
+ RTNLGRP_MDB,
+#define RTNLGRP_MDB RTNLGRP_MDB
+ RTNLGRP_MPLS_ROUTE,
+#define RTNLGRP_MPLS_ROUTE RTNLGRP_MPLS_ROUTE
+ RTNLGRP_NSID,
+#define RTNLGRP_NSID RTNLGRP_NSID
+ RTNLGRP_MPLS_NETCONF,
+#define RTNLGRP_MPLS_NETCONF RTNLGRP_MPLS_NETCONF
+ RTNLGRP_IPV4_MROUTE_R,
+#define RTNLGRP_IPV4_MROUTE_R RTNLGRP_IPV4_MROUTE_R
+ RTNLGRP_IPV6_MROUTE_R,
+#define RTNLGRP_IPV6_MROUTE_R RTNLGRP_IPV6_MROUTE_R
+ RTNLGRP_NEXTHOP,
+#define RTNLGRP_NEXTHOP RTNLGRP_NEXTHOP
+ RTNLGRP_BRVLAN,
+#define RTNLGRP_BRVLAN RTNLGRP_BRVLAN
+ RTNLGRP_MCTP_IFADDR,
+#define RTNLGRP_MCTP_IFADDR RTNLGRP_MCTP_IFADDR
+ RTNLGRP_TUNNEL,
+#define RTNLGRP_TUNNEL RTNLGRP_TUNNEL
+ RTNLGRP_STATS,
+#define RTNLGRP_STATS RTNLGRP_STATS
+ __RTNLGRP_MAX
+};
+#define RTNLGRP_MAX (__RTNLGRP_MAX - 1)
+
+/* TC action piece */
+struct tcamsg {
+ unsigned char tca_family;
+ unsigned char tca__pad1;
+ unsigned short tca__pad2;
+};
+
+enum {
+ TCA_ROOT_UNSPEC,
+ TCA_ROOT_TAB,
+#define TCA_ACT_TAB TCA_ROOT_TAB
+#define TCAA_MAX TCA_ROOT_TAB
+ TCA_ROOT_FLAGS,
+ TCA_ROOT_COUNT,
+ TCA_ROOT_TIME_DELTA, /* in msecs */
+ TCA_ROOT_EXT_WARN_MSG,
+ __TCA_ROOT_MAX,
+#define TCA_ROOT_MAX (__TCA_ROOT_MAX - 1)
+};
+
+#define TA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcamsg))))
+#define TA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcamsg))
+/* tcamsg flags stored in attribute TCA_ROOT_FLAGS
+ *
+ * TCA_ACT_FLAG_LARGE_DUMP_ON user->kernel to request for larger than
+ * TCA_ACT_MAX_PRIO actions in a dump. All dump responses will contain the
+ * number of actions being dumped stored in for user app's consumption in
+ * TCA_ROOT_COUNT
+ *
+ * TCA_ACT_FLAG_TERSE_DUMP user->kernel to request terse (brief) dump that only
+ * includes essential action info (kind, index, etc.)
+ *
+ */
+#define TCA_FLAG_LARGE_DUMP_ON (1 << 0)
+#define TCA_ACT_FLAG_LARGE_DUMP_ON TCA_FLAG_LARGE_DUMP_ON
+#define TCA_ACT_FLAG_TERSE_DUMP (1 << 1)
+
+/* New extended info filters for IFLA_EXT_MASK */
+#define RTEXT_FILTER_VF (1 << 0)
+#define RTEXT_FILTER_BRVLAN (1 << 1)
+#define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2)
+#define RTEXT_FILTER_SKIP_STATS (1 << 3)
+#define RTEXT_FILTER_MRP (1 << 4)
+#define RTEXT_FILTER_CFM_CONFIG (1 << 5)
+#define RTEXT_FILTER_CFM_STATUS (1 << 6)
+#define RTEXT_FILTER_MST (1 << 7)
+
+/* End of information exported to user level */
+
+
+
+#endif /* __LINUX_RTNETLINK_H */
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
new file mode 100644
index 0000000..d52e122
--- /dev/null
+++ b/include/uapi/linux/sctp.h
@@ -0,0 +1,1220 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/* SCTP kernel implementation
+ * (C) Copyright IBM Corp. 2001, 2004
+ * Copyright (c) 1999-2000 Cisco, Inc.
+ * Copyright (c) 1999-2001 Motorola, Inc.
+ * Copyright (c) 2002 Intel Corp.
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * This header represents the structures and constants needed to support
+ * the SCTP Extension to the Sockets API.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ * ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING. If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email address(es):
+ * lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Or submit a bug report through the following website:
+ * http://www.sf.net/projects/lksctp
+ *
+ * Written or modified by:
+ * La Monte H.P. Yarroll <piggy@acm.org>
+ * R. Stewart <randall@sctp.chicago.il.us>
+ * K. Morneau <kmorneau@cisco.com>
+ * Q. Xie <qxie1@email.mot.com>
+ * Karl Knutson <karl@athena.chicago.il.us>
+ * Jon Grimm <jgrimm@us.ibm.com>
+ * Daisy Chang <daisyc@us.ibm.com>
+ * Ryan Layer <rmlayer@us.ibm.com>
+ * Ardelle Fan <ardelle.fan@intel.com>
+ * Sridhar Samudrala <sri@us.ibm.com>
+ * Inaky Perez-Gonzalez <inaky.gonzalez@intel.com>
+ * Vlad Yasevich <vladislav.yasevich@hp.com>
+ *
+ * Any bugs reported given to us we will try to fix... any fixes shared will
+ * be incorporated into the next SCTP release.
+ */
+
+#ifndef _SCTP_H
+#define _SCTP_H
+
+#include <linux/types.h>
+#include <linux/socket.h>
+
+typedef __s32 sctp_assoc_t;
+
+#define SCTP_FUTURE_ASSOC 0
+#define SCTP_CURRENT_ASSOC 1
+#define SCTP_ALL_ASSOC 2
+
+/* The following symbols come from the Sockets API Extensions for
+ * SCTP <draft-ietf-tsvwg-sctpsocket-07.txt>.
+ */
+#define SCTP_RTOINFO 0
+#define SCTP_ASSOCINFO 1
+#define SCTP_INITMSG 2
+#define SCTP_NODELAY 3 /* Get/set nodelay option. */
+#define SCTP_AUTOCLOSE 4
+#define SCTP_SET_PEER_PRIMARY_ADDR 5
+#define SCTP_PRIMARY_ADDR 6
+#define SCTP_ADAPTATION_LAYER 7
+#define SCTP_DISABLE_FRAGMENTS 8
+#define SCTP_PEER_ADDR_PARAMS 9
+#define SCTP_DEFAULT_SEND_PARAM 10
+#define SCTP_EVENTS 11
+#define SCTP_I_WANT_MAPPED_V4_ADDR 12 /* Turn on/off mapped v4 addresses */
+#define SCTP_MAXSEG 13 /* Get/set maximum fragment. */
+#define SCTP_STATUS 14
+#define SCTP_GET_PEER_ADDR_INFO 15
+#define SCTP_DELAYED_ACK_TIME 16
+#define SCTP_DELAYED_ACK SCTP_DELAYED_ACK_TIME
+#define SCTP_DELAYED_SACK SCTP_DELAYED_ACK_TIME
+#define SCTP_CONTEXT 17
+#define SCTP_FRAGMENT_INTERLEAVE 18
+#define SCTP_PARTIAL_DELIVERY_POINT 19 /* Set/Get partial delivery point */
+#define SCTP_MAX_BURST 20 /* Set/Get max burst */
+#define SCTP_AUTH_CHUNK 21 /* Set only: add a chunk type to authenticate */
+#define SCTP_HMAC_IDENT 22
+#define SCTP_AUTH_KEY 23
+#define SCTP_AUTH_ACTIVE_KEY 24
+#define SCTP_AUTH_DELETE_KEY 25
+#define SCTP_PEER_AUTH_CHUNKS 26 /* Read only */
+#define SCTP_LOCAL_AUTH_CHUNKS 27 /* Read only */
+#define SCTP_GET_ASSOC_NUMBER 28 /* Read only */
+#define SCTP_GET_ASSOC_ID_LIST 29 /* Read only */
+#define SCTP_AUTO_ASCONF 30
+#define SCTP_PEER_ADDR_THLDS 31
+#define SCTP_RECVRCVINFO 32
+#define SCTP_RECVNXTINFO 33
+#define SCTP_DEFAULT_SNDINFO 34
+#define SCTP_AUTH_DEACTIVATE_KEY 35
+#define SCTP_REUSE_PORT 36
+#define SCTP_PEER_ADDR_THLDS_V2 37
+
+/* Internal Socket Options. Some of the sctp library functions are
+ * implemented using these socket options.
+ */
+#define SCTP_SOCKOPT_BINDX_ADD 100 /* BINDX requests for adding addrs */
+#define SCTP_SOCKOPT_BINDX_REM 101 /* BINDX requests for removing addrs. */
+#define SCTP_SOCKOPT_PEELOFF 102 /* peel off association. */
+/* Options 104-106 are deprecated and removed. Do not use this space */
+#define SCTP_SOCKOPT_CONNECTX_OLD 107 /* CONNECTX old requests. */
+#define SCTP_GET_PEER_ADDRS 108 /* Get all peer address. */
+#define SCTP_GET_LOCAL_ADDRS 109 /* Get all local address. */
+#define SCTP_SOCKOPT_CONNECTX 110 /* CONNECTX requests. */
+#define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */
+#define SCTP_GET_ASSOC_STATS 112 /* Read only */
+#define SCTP_PR_SUPPORTED 113
+#define SCTP_DEFAULT_PRINFO 114
+#define SCTP_PR_ASSOC_STATUS 115
+#define SCTP_PR_STREAM_STATUS 116
+#define SCTP_RECONFIG_SUPPORTED 117
+#define SCTP_ENABLE_STREAM_RESET 118
+#define SCTP_RESET_STREAMS 119
+#define SCTP_RESET_ASSOC 120
+#define SCTP_ADD_STREAMS 121
+#define SCTP_SOCKOPT_PEELOFF_FLAGS 122
+#define SCTP_STREAM_SCHEDULER 123
+#define SCTP_STREAM_SCHEDULER_VALUE 124
+#define SCTP_INTERLEAVING_SUPPORTED 125
+#define SCTP_SENDMSG_CONNECT 126
+#define SCTP_EVENT 127
+#define SCTP_ASCONF_SUPPORTED 128
+#define SCTP_AUTH_SUPPORTED 129
+#define SCTP_ECN_SUPPORTED 130
+#define SCTP_EXPOSE_POTENTIALLY_FAILED_STATE 131
+#define SCTP_EXPOSE_PF_STATE SCTP_EXPOSE_POTENTIALLY_FAILED_STATE
+#define SCTP_REMOTE_UDP_ENCAPS_PORT 132
+#define SCTP_PLPMTUD_PROBE_INTERVAL 133
+
+/* PR-SCTP policies */
+#define SCTP_PR_SCTP_NONE 0x0000
+#define SCTP_PR_SCTP_TTL 0x0010
+#define SCTP_PR_SCTP_RTX 0x0020
+#define SCTP_PR_SCTP_PRIO 0x0030
+#define SCTP_PR_SCTP_MAX SCTP_PR_SCTP_PRIO
+#define SCTP_PR_SCTP_MASK 0x0030
+
+#define __SCTP_PR_INDEX(x) ((x >> 4) - 1)
+#define SCTP_PR_INDEX(x) __SCTP_PR_INDEX(SCTP_PR_SCTP_ ## x)
+
+#define SCTP_PR_POLICY(x) ((x) & SCTP_PR_SCTP_MASK)
+#define SCTP_PR_SET_POLICY(flags, x) \
+ do { \
+ flags &= ~SCTP_PR_SCTP_MASK; \
+ flags |= x; \
+ } while (0)
+
+#define SCTP_PR_TTL_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_TTL)
+#define SCTP_PR_RTX_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_RTX)
+#define SCTP_PR_PRIO_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_PRIO)
+
+/* For enable stream reset */
+#define SCTP_ENABLE_RESET_STREAM_REQ 0x01
+#define SCTP_ENABLE_RESET_ASSOC_REQ 0x02
+#define SCTP_ENABLE_CHANGE_ASSOC_REQ 0x04
+#define SCTP_ENABLE_STRRESET_MASK 0x07
+
+#define SCTP_STREAM_RESET_INCOMING 0x01
+#define SCTP_STREAM_RESET_OUTGOING 0x02
+
+/* These are bit fields for msghdr->msg_flags. See section 5.1. */
+/* On user space Linux, these live in <bits/socket.h> as an enum. */
+enum sctp_msg_flags {
+ MSG_NOTIFICATION = 0x8000,
+#define MSG_NOTIFICATION MSG_NOTIFICATION
+};
+
+/* 5.3.1 SCTP Initiation Structure (SCTP_INIT)
+ *
+ * This cmsghdr structure provides information for initializing new
+ * SCTP associations with sendmsg(). The SCTP_INITMSG socket option
+ * uses this same data structure. This structure is not used for
+ * recvmsg().
+ *
+ * cmsg_level cmsg_type cmsg_data[]
+ * ------------ ------------ ----------------------
+ * IPPROTO_SCTP SCTP_INIT struct sctp_initmsg
+ */
+struct sctp_initmsg {
+ __u16 sinit_num_ostreams;
+ __u16 sinit_max_instreams;
+ __u16 sinit_max_attempts;
+ __u16 sinit_max_init_timeo;
+};
+
+/* 5.3.2 SCTP Header Information Structure (SCTP_SNDRCV)
+ *
+ * This cmsghdr structure specifies SCTP options for sendmsg() and
+ * describes SCTP header information about a received message through
+ * recvmsg().
+ *
+ * cmsg_level cmsg_type cmsg_data[]
+ * ------------ ------------ ----------------------
+ * IPPROTO_SCTP SCTP_SNDRCV struct sctp_sndrcvinfo
+ */
+struct sctp_sndrcvinfo {
+ __u16 sinfo_stream;
+ __u16 sinfo_ssn;
+ __u16 sinfo_flags;
+ __u32 sinfo_ppid;
+ __u32 sinfo_context;
+ __u32 sinfo_timetolive;
+ __u32 sinfo_tsn;
+ __u32 sinfo_cumtsn;
+ sctp_assoc_t sinfo_assoc_id;
+};
+
+/* 5.3.4 SCTP Send Information Structure (SCTP_SNDINFO)
+ *
+ * This cmsghdr structure specifies SCTP options for sendmsg().
+ *
+ * cmsg_level cmsg_type cmsg_data[]
+ * ------------ ------------ -------------------
+ * IPPROTO_SCTP SCTP_SNDINFO struct sctp_sndinfo
+ */
+struct sctp_sndinfo {
+ __u16 snd_sid;
+ __u16 snd_flags;
+ __u32 snd_ppid;
+ __u32 snd_context;
+ sctp_assoc_t snd_assoc_id;
+};
+
+/* 5.3.5 SCTP Receive Information Structure (SCTP_RCVINFO)
+ *
+ * This cmsghdr structure describes SCTP receive information
+ * about a received message through recvmsg().
+ *
+ * cmsg_level cmsg_type cmsg_data[]
+ * ------------ ------------ -------------------
+ * IPPROTO_SCTP SCTP_RCVINFO struct sctp_rcvinfo
+ */
+struct sctp_rcvinfo {
+ __u16 rcv_sid;
+ __u16 rcv_ssn;
+ __u16 rcv_flags;
+ __u32 rcv_ppid;
+ __u32 rcv_tsn;
+ __u32 rcv_cumtsn;
+ __u32 rcv_context;
+ sctp_assoc_t rcv_assoc_id;
+};
+
+/* 5.3.6 SCTP Next Receive Information Structure (SCTP_NXTINFO)
+ *
+ * This cmsghdr structure describes SCTP receive information
+ * of the next message that will be delivered through recvmsg()
+ * if this information is already available when delivering
+ * the current message.
+ *
+ * cmsg_level cmsg_type cmsg_data[]
+ * ------------ ------------ -------------------
+ * IPPROTO_SCTP SCTP_NXTINFO struct sctp_nxtinfo
+ */
+struct sctp_nxtinfo {
+ __u16 nxt_sid;
+ __u16 nxt_flags;
+ __u32 nxt_ppid;
+ __u32 nxt_length;
+ sctp_assoc_t nxt_assoc_id;
+};
+
+/* 5.3.7 SCTP PR-SCTP Information Structure (SCTP_PRINFO)
+ *
+ * This cmsghdr structure specifies SCTP options for sendmsg().
+ *
+ * cmsg_level cmsg_type cmsg_data[]
+ * ------------ ------------ -------------------
+ * IPPROTO_SCTP SCTP_PRINFO struct sctp_prinfo
+ */
+struct sctp_prinfo {
+ __u16 pr_policy;
+ __u32 pr_value;
+};
+
+/* 5.3.8 SCTP AUTH Information Structure (SCTP_AUTHINFO)
+ *
+ * This cmsghdr structure specifies SCTP options for sendmsg().
+ *
+ * cmsg_level cmsg_type cmsg_data[]
+ * ------------ ------------ -------------------
+ * IPPROTO_SCTP SCTP_AUTHINFO struct sctp_authinfo
+ */
+struct sctp_authinfo {
+ __u16 auth_keynumber;
+};
+
+/*
+ * sinfo_flags: 16 bits (unsigned integer)
+ *
+ * This field may contain any of the following flags and is composed of
+ * a bitwise OR of these values.
+ */
+enum sctp_sinfo_flags {
+ SCTP_UNORDERED = (1 << 0), /* Send/receive message unordered. */
+ SCTP_ADDR_OVER = (1 << 1), /* Override the primary destination. */
+ SCTP_ABORT = (1 << 2), /* Send an ABORT message to the peer. */
+ SCTP_SACK_IMMEDIATELY = (1 << 3), /* SACK should be sent without delay. */
+ /* 2 bits here have been used by SCTP_PR_SCTP_MASK */
+ SCTP_SENDALL = (1 << 6),
+ SCTP_PR_SCTP_ALL = (1 << 7),
+ SCTP_NOTIFICATION = MSG_NOTIFICATION, /* Next message is not user msg but notification. */
+ SCTP_EOF = MSG_FIN, /* Initiate graceful shutdown process. */
+};
+
+typedef union {
+ __u8 raw;
+ struct sctp_initmsg init;
+ struct sctp_sndrcvinfo sndrcv;
+} sctp_cmsg_data_t;
+
+/* These are cmsg_types. */
+typedef enum sctp_cmsg_type {
+ SCTP_INIT, /* 5.2.1 SCTP Initiation Structure */
+#define SCTP_INIT SCTP_INIT
+ SCTP_SNDRCV, /* 5.2.2 SCTP Header Information Structure */
+#define SCTP_SNDRCV SCTP_SNDRCV
+ SCTP_SNDINFO, /* 5.3.4 SCTP Send Information Structure */
+#define SCTP_SNDINFO SCTP_SNDINFO
+ SCTP_RCVINFO, /* 5.3.5 SCTP Receive Information Structure */
+#define SCTP_RCVINFO SCTP_RCVINFO
+ SCTP_NXTINFO, /* 5.3.6 SCTP Next Receive Information Structure */
+#define SCTP_NXTINFO SCTP_NXTINFO
+ SCTP_PRINFO, /* 5.3.7 SCTP PR-SCTP Information Structure */
+#define SCTP_PRINFO SCTP_PRINFO
+ SCTP_AUTHINFO, /* 5.3.8 SCTP AUTH Information Structure */
+#define SCTP_AUTHINFO SCTP_AUTHINFO
+ SCTP_DSTADDRV4, /* 5.3.9 SCTP Destination IPv4 Address Structure */
+#define SCTP_DSTADDRV4 SCTP_DSTADDRV4
+ SCTP_DSTADDRV6, /* 5.3.10 SCTP Destination IPv6 Address Structure */
+#define SCTP_DSTADDRV6 SCTP_DSTADDRV6
+} sctp_cmsg_t;
+
+/*
+ * 5.3.1.1 SCTP_ASSOC_CHANGE
+ *
+ * Communication notifications inform the ULP that an SCTP association
+ * has either begun or ended. The identifier for a new association is
+ * provided by this notificaion. The notification information has the
+ * following format:
+ *
+ */
+struct sctp_assoc_change {
+ __u16 sac_type;
+ __u16 sac_flags;
+ __u32 sac_length;
+ __u16 sac_state;
+ __u16 sac_error;
+ __u16 sac_outbound_streams;
+ __u16 sac_inbound_streams;
+ sctp_assoc_t sac_assoc_id;
+ __u8 sac_info[];
+};
+
+/*
+ * sac_state: 32 bits (signed integer)
+ *
+ * This field holds one of a number of values that communicate the
+ * event that happened to the association. They include:
+ *
+ * Note: The following state names deviate from the API draft as
+ * the names clash too easily with other kernel symbols.
+ */
+enum sctp_sac_state {
+ SCTP_COMM_UP,
+ SCTP_COMM_LOST,
+ SCTP_RESTART,
+ SCTP_SHUTDOWN_COMP,
+ SCTP_CANT_STR_ASSOC,
+};
+
+/*
+ * 5.3.1.2 SCTP_PEER_ADDR_CHANGE
+ *
+ * When a destination address on a multi-homed peer encounters a change
+ * an interface details event is sent. The information has the
+ * following structure:
+ */
+struct sctp_paddr_change {
+ __u16 spc_type;
+ __u16 spc_flags;
+ __u32 spc_length;
+ struct sockaddr_storage spc_aaddr;
+ int spc_state;
+ int spc_error;
+ sctp_assoc_t spc_assoc_id;
+} __attribute__((packed, aligned(4)));
+
+/*
+ * spc_state: 32 bits (signed integer)
+ *
+ * This field holds one of a number of values that communicate the
+ * event that happened to the address. They include:
+ */
+enum sctp_spc_state {
+ SCTP_ADDR_AVAILABLE,
+ SCTP_ADDR_UNREACHABLE,
+ SCTP_ADDR_REMOVED,
+ SCTP_ADDR_ADDED,
+ SCTP_ADDR_MADE_PRIM,
+ SCTP_ADDR_CONFIRMED,
+ SCTP_ADDR_POTENTIALLY_FAILED,
+#define SCTP_ADDR_PF SCTP_ADDR_POTENTIALLY_FAILED
+};
+
+
+/*
+ * 5.3.1.3 SCTP_REMOTE_ERROR
+ *
+ * A remote peer may send an Operational Error message to its peer.
+ * This message indicates a variety of error conditions on an
+ * association. The entire error TLV as it appears on the wire is
+ * included in a SCTP_REMOTE_ERROR event. Please refer to the SCTP
+ * specification [SCTP] and any extensions for a list of possible
+ * error formats. SCTP error TLVs have the format:
+ */
+struct sctp_remote_error {
+ __u16 sre_type;
+ __u16 sre_flags;
+ __u32 sre_length;
+ __be16 sre_error;
+ sctp_assoc_t sre_assoc_id;
+ __u8 sre_data[];
+};
+
+
+/*
+ * 5.3.1.4 SCTP_SEND_FAILED
+ *
+ * If SCTP cannot deliver a message it may return the message as a
+ * notification.
+ */
+struct sctp_send_failed {
+ __u16 ssf_type;
+ __u16 ssf_flags;
+ __u32 ssf_length;
+ __u32 ssf_error;
+ struct sctp_sndrcvinfo ssf_info;
+ sctp_assoc_t ssf_assoc_id;
+ __u8 ssf_data[];
+};
+
+struct sctp_send_failed_event {
+ __u16 ssf_type;
+ __u16 ssf_flags;
+ __u32 ssf_length;
+ __u32 ssf_error;
+ struct sctp_sndinfo ssfe_info;
+ sctp_assoc_t ssf_assoc_id;
+ __u8 ssf_data[];
+};
+
+/*
+ * ssf_flags: 16 bits (unsigned integer)
+ *
+ * The flag value will take one of the following values
+ *
+ * SCTP_DATA_UNSENT - Indicates that the data was never put on
+ * the wire.
+ *
+ * SCTP_DATA_SENT - Indicates that the data was put on the wire.
+ * Note that this does not necessarily mean that the
+ * data was (or was not) successfully delivered.
+ */
+enum sctp_ssf_flags {
+ SCTP_DATA_UNSENT,
+ SCTP_DATA_SENT,
+};
+
+/*
+ * 5.3.1.5 SCTP_SHUTDOWN_EVENT
+ *
+ * When a peer sends a SHUTDOWN, SCTP delivers this notification to
+ * inform the application that it should cease sending data.
+ */
+struct sctp_shutdown_event {
+ __u16 sse_type;
+ __u16 sse_flags;
+ __u32 sse_length;
+ sctp_assoc_t sse_assoc_id;
+};
+
+/*
+ * 5.3.1.6 SCTP_ADAPTATION_INDICATION
+ *
+ * When a peer sends a Adaptation Layer Indication parameter , SCTP
+ * delivers this notification to inform the application
+ * that of the peers requested adaptation layer.
+ */
+struct sctp_adaptation_event {
+ __u16 sai_type;
+ __u16 sai_flags;
+ __u32 sai_length;
+ __u32 sai_adaptation_ind;
+ sctp_assoc_t sai_assoc_id;
+};
+
+/*
+ * 5.3.1.7 SCTP_PARTIAL_DELIVERY_EVENT
+ *
+ * When a receiver is engaged in a partial delivery of a
+ * message this notification will be used to indicate
+ * various events.
+ */
+struct sctp_pdapi_event {
+ __u16 pdapi_type;
+ __u16 pdapi_flags;
+ __u32 pdapi_length;
+ __u32 pdapi_indication;
+ sctp_assoc_t pdapi_assoc_id;
+ __u32 pdapi_stream;
+ __u32 pdapi_seq;
+};
+
+enum { SCTP_PARTIAL_DELIVERY_ABORTED=0, };
+
+/*
+ * 5.3.1.8. SCTP_AUTHENTICATION_EVENT
+ *
+ * When a receiver is using authentication this message will provide
+ * notifications regarding new keys being made active as well as errors.
+ */
+struct sctp_authkey_event {
+ __u16 auth_type;
+ __u16 auth_flags;
+ __u32 auth_length;
+ __u16 auth_keynumber;
+ __u16 auth_altkeynumber;
+ __u32 auth_indication;
+ sctp_assoc_t auth_assoc_id;
+};
+
+enum {
+ SCTP_AUTH_NEW_KEY,
+#define SCTP_AUTH_NEWKEY SCTP_AUTH_NEW_KEY /* compatible with before */
+ SCTP_AUTH_FREE_KEY,
+ SCTP_AUTH_NO_AUTH,
+};
+
+/*
+ * 6.1.9. SCTP_SENDER_DRY_EVENT
+ *
+ * When the SCTP stack has no more user data to send or retransmit, this
+ * notification is given to the user. Also, at the time when a user app
+ * subscribes to this event, if there is no data to be sent or
+ * retransmit, the stack will immediately send up this notification.
+ */
+struct sctp_sender_dry_event {
+ __u16 sender_dry_type;
+ __u16 sender_dry_flags;
+ __u32 sender_dry_length;
+ sctp_assoc_t sender_dry_assoc_id;
+};
+
+#define SCTP_STREAM_RESET_INCOMING_SSN 0x0001
+#define SCTP_STREAM_RESET_OUTGOING_SSN 0x0002
+#define SCTP_STREAM_RESET_DENIED 0x0004
+#define SCTP_STREAM_RESET_FAILED 0x0008
+struct sctp_stream_reset_event {
+ __u16 strreset_type;
+ __u16 strreset_flags;
+ __u32 strreset_length;
+ sctp_assoc_t strreset_assoc_id;
+ __u16 strreset_stream_list[];
+};
+
+#define SCTP_ASSOC_RESET_DENIED 0x0004
+#define SCTP_ASSOC_RESET_FAILED 0x0008
+struct sctp_assoc_reset_event {
+ __u16 assocreset_type;
+ __u16 assocreset_flags;
+ __u32 assocreset_length;
+ sctp_assoc_t assocreset_assoc_id;
+ __u32 assocreset_local_tsn;
+ __u32 assocreset_remote_tsn;
+};
+
+#define SCTP_ASSOC_CHANGE_DENIED 0x0004
+#define SCTP_ASSOC_CHANGE_FAILED 0x0008
+#define SCTP_STREAM_CHANGE_DENIED SCTP_ASSOC_CHANGE_DENIED
+#define SCTP_STREAM_CHANGE_FAILED SCTP_ASSOC_CHANGE_FAILED
+struct sctp_stream_change_event {
+ __u16 strchange_type;
+ __u16 strchange_flags;
+ __u32 strchange_length;
+ sctp_assoc_t strchange_assoc_id;
+ __u16 strchange_instrms;
+ __u16 strchange_outstrms;
+};
+
+/*
+ * Described in Section 7.3
+ * Ancillary Data and Notification Interest Options
+ */
+struct sctp_event_subscribe {
+ __u8 sctp_data_io_event;
+ __u8 sctp_association_event;
+ __u8 sctp_address_event;
+ __u8 sctp_send_failure_event;
+ __u8 sctp_peer_error_event;
+ __u8 sctp_shutdown_event;
+ __u8 sctp_partial_delivery_event;
+ __u8 sctp_adaptation_layer_event;
+ __u8 sctp_authentication_event;
+ __u8 sctp_sender_dry_event;
+ __u8 sctp_stream_reset_event;
+ __u8 sctp_assoc_reset_event;
+ __u8 sctp_stream_change_event;
+ __u8 sctp_send_failure_event_event;
+};
+
+/*
+ * 5.3.1 SCTP Notification Structure
+ *
+ * The notification structure is defined as the union of all
+ * notification types.
+ *
+ */
+union sctp_notification {
+ struct {
+ __u16 sn_type; /* Notification type. */
+ __u16 sn_flags;
+ __u32 sn_length;
+ } sn_header;
+ struct sctp_assoc_change sn_assoc_change;
+ struct sctp_paddr_change sn_paddr_change;
+ struct sctp_remote_error sn_remote_error;
+ struct sctp_send_failed sn_send_failed;
+ struct sctp_shutdown_event sn_shutdown_event;
+ struct sctp_adaptation_event sn_adaptation_event;
+ struct sctp_pdapi_event sn_pdapi_event;
+ struct sctp_authkey_event sn_authkey_event;
+ struct sctp_sender_dry_event sn_sender_dry_event;
+ struct sctp_stream_reset_event sn_strreset_event;
+ struct sctp_assoc_reset_event sn_assocreset_event;
+ struct sctp_stream_change_event sn_strchange_event;
+ struct sctp_send_failed_event sn_send_failed_event;
+};
+
+/* Section 5.3.1
+ * All standard values for sn_type flags are greater than 2^15.
+ * Values from 2^15 and down are reserved.
+ */
+
+enum sctp_sn_type {
+ SCTP_SN_TYPE_BASE = (1<<15),
+ SCTP_DATA_IO_EVENT = SCTP_SN_TYPE_BASE,
+#define SCTP_DATA_IO_EVENT SCTP_DATA_IO_EVENT
+ SCTP_ASSOC_CHANGE,
+#define SCTP_ASSOC_CHANGE SCTP_ASSOC_CHANGE
+ SCTP_PEER_ADDR_CHANGE,
+#define SCTP_PEER_ADDR_CHANGE SCTP_PEER_ADDR_CHANGE
+ SCTP_SEND_FAILED,
+#define SCTP_SEND_FAILED SCTP_SEND_FAILED
+ SCTP_REMOTE_ERROR,
+#define SCTP_REMOTE_ERROR SCTP_REMOTE_ERROR
+ SCTP_SHUTDOWN_EVENT,
+#define SCTP_SHUTDOWN_EVENT SCTP_SHUTDOWN_EVENT
+ SCTP_PARTIAL_DELIVERY_EVENT,
+#define SCTP_PARTIAL_DELIVERY_EVENT SCTP_PARTIAL_DELIVERY_EVENT
+ SCTP_ADAPTATION_INDICATION,
+#define SCTP_ADAPTATION_INDICATION SCTP_ADAPTATION_INDICATION
+ SCTP_AUTHENTICATION_EVENT,
+#define SCTP_AUTHENTICATION_INDICATION SCTP_AUTHENTICATION_EVENT
+ SCTP_SENDER_DRY_EVENT,
+#define SCTP_SENDER_DRY_EVENT SCTP_SENDER_DRY_EVENT
+ SCTP_STREAM_RESET_EVENT,
+#define SCTP_STREAM_RESET_EVENT SCTP_STREAM_RESET_EVENT
+ SCTP_ASSOC_RESET_EVENT,
+#define SCTP_ASSOC_RESET_EVENT SCTP_ASSOC_RESET_EVENT
+ SCTP_STREAM_CHANGE_EVENT,
+#define SCTP_STREAM_CHANGE_EVENT SCTP_STREAM_CHANGE_EVENT
+ SCTP_SEND_FAILED_EVENT,
+#define SCTP_SEND_FAILED_EVENT SCTP_SEND_FAILED_EVENT
+ SCTP_SN_TYPE_MAX = SCTP_SEND_FAILED_EVENT,
+#define SCTP_SN_TYPE_MAX SCTP_SN_TYPE_MAX
+};
+
+/* Notification error codes used to fill up the error fields in some
+ * notifications.
+ * SCTP_PEER_ADDRESS_CHAGE : spc_error
+ * SCTP_ASSOC_CHANGE : sac_error
+ * These names should be potentially included in the draft 04 of the SCTP
+ * sockets API specification.
+ */
+typedef enum sctp_sn_error {
+ SCTP_FAILED_THRESHOLD,
+ SCTP_RECEIVED_SACK,
+ SCTP_HEARTBEAT_SUCCESS,
+ SCTP_RESPONSE_TO_USER_REQ,
+ SCTP_INTERNAL_ERROR,
+ SCTP_SHUTDOWN_GUARD_EXPIRES,
+ SCTP_PEER_FAULTY,
+} sctp_sn_error_t;
+
+/*
+ * 7.1.1 Retransmission Timeout Parameters (SCTP_RTOINFO)
+ *
+ * The protocol parameters used to initialize and bound retransmission
+ * timeout (RTO) are tunable. See [SCTP] for more information on how
+ * these parameters are used in RTO calculation.
+ */
+struct sctp_rtoinfo {
+ sctp_assoc_t srto_assoc_id;
+ __u32 srto_initial;
+ __u32 srto_max;
+ __u32 srto_min;
+};
+
+/*
+ * 7.1.2 Association Parameters (SCTP_ASSOCINFO)
+ *
+ * This option is used to both examine and set various association and
+ * endpoint parameters.
+ */
+struct sctp_assocparams {
+ sctp_assoc_t sasoc_assoc_id;
+ __u16 sasoc_asocmaxrxt;
+ __u16 sasoc_number_peer_destinations;
+ __u32 sasoc_peer_rwnd;
+ __u32 sasoc_local_rwnd;
+ __u32 sasoc_cookie_life;
+};
+
+/*
+ * 7.1.9 Set Peer Primary Address (SCTP_SET_PEER_PRIMARY_ADDR)
+ *
+ * Requests that the peer mark the enclosed address as the association
+ * primary. The enclosed address must be one of the association's
+ * locally bound addresses. The following structure is used to make a
+ * set primary request:
+ */
+struct sctp_setpeerprim {
+ sctp_assoc_t sspp_assoc_id;
+ struct sockaddr_storage sspp_addr;
+} __attribute__((packed, aligned(4)));
+
+/*
+ * 7.1.10 Set Primary Address (SCTP_PRIMARY_ADDR)
+ *
+ * Requests that the local SCTP stack use the enclosed peer address as
+ * the association primary. The enclosed address must be one of the
+ * association peer's addresses. The following structure is used to
+ * make a set peer primary request:
+ */
+struct sctp_prim {
+ sctp_assoc_t ssp_assoc_id;
+ struct sockaddr_storage ssp_addr;
+} __attribute__((packed, aligned(4)));
+
+/* For backward compatibility use, define the old name too */
+#define sctp_setprim sctp_prim
+
+/*
+ * 7.1.11 Set Adaptation Layer Indicator (SCTP_ADAPTATION_LAYER)
+ *
+ * Requests that the local endpoint set the specified Adaptation Layer
+ * Indication parameter for all future INIT and INIT-ACK exchanges.
+ */
+struct sctp_setadaptation {
+ __u32 ssb_adaptation_ind;
+};
+
+/*
+ * 7.1.13 Peer Address Parameters (SCTP_PEER_ADDR_PARAMS)
+ *
+ * Applications can enable or disable heartbeats for any peer address
+ * of an association, modify an address's heartbeat interval, force a
+ * heartbeat to be sent immediately, and adjust the address's maximum
+ * number of retransmissions sent before an address is considered
+ * unreachable. The following structure is used to access and modify an
+ * address's parameters:
+ */
+enum sctp_spp_flags {
+ SPP_HB_ENABLE = 1<<0, /*Enable heartbeats*/
+ SPP_HB_DISABLE = 1<<1, /*Disable heartbeats*/
+ SPP_HB = SPP_HB_ENABLE | SPP_HB_DISABLE,
+ SPP_HB_DEMAND = 1<<2, /*Send heartbeat immediately*/
+ SPP_PMTUD_ENABLE = 1<<3, /*Enable PMTU discovery*/
+ SPP_PMTUD_DISABLE = 1<<4, /*Disable PMTU discovery*/
+ SPP_PMTUD = SPP_PMTUD_ENABLE | SPP_PMTUD_DISABLE,
+ SPP_SACKDELAY_ENABLE = 1<<5, /*Enable SACK*/
+ SPP_SACKDELAY_DISABLE = 1<<6, /*Disable SACK*/
+ SPP_SACKDELAY = SPP_SACKDELAY_ENABLE | SPP_SACKDELAY_DISABLE,
+ SPP_HB_TIME_IS_ZERO = 1<<7, /* Set HB delay to 0 */
+ SPP_IPV6_FLOWLABEL = 1<<8,
+ SPP_DSCP = 1<<9,
+};
+
+struct sctp_paddrparams {
+ sctp_assoc_t spp_assoc_id;
+ struct sockaddr_storage spp_address;
+ __u32 spp_hbinterval;
+ __u16 spp_pathmaxrxt;
+ __u32 spp_pathmtu;
+ __u32 spp_sackdelay;
+ __u32 spp_flags;
+ __u32 spp_ipv6_flowlabel;
+ __u8 spp_dscp;
+} __attribute__((packed, aligned(4)));
+
+/*
+ * 7.1.18. Add a chunk that must be authenticated (SCTP_AUTH_CHUNK)
+ *
+ * This set option adds a chunk type that the user is requesting to be
+ * received only in an authenticated way. Changes to the list of chunks
+ * will only effect future associations on the socket.
+ */
+struct sctp_authchunk {
+ __u8 sauth_chunk;
+};
+
+/*
+ * 7.1.19. Get or set the list of supported HMAC Identifiers (SCTP_HMAC_IDENT)
+ *
+ * This option gets or sets the list of HMAC algorithms that the local
+ * endpoint requires the peer to use.
+ */
+/* This here is only used by user space as is. It might not be a good idea
+ * to export/reveal the whole structure with reserved fields etc.
+ */
+enum {
+ SCTP_AUTH_HMAC_ID_SHA1 = 1,
+ SCTP_AUTH_HMAC_ID_SHA256 = 3,
+};
+
+struct sctp_hmacalgo {
+ __u32 shmac_num_idents;
+ __u16 shmac_idents[];
+};
+
+/* Sadly, user and kernel space have different names for
+ * this structure member, so this is to not break anything.
+ */
+#define shmac_number_of_idents shmac_num_idents
+
+/*
+ * 7.1.20. Set a shared key (SCTP_AUTH_KEY)
+ *
+ * This option will set a shared secret key which is used to build an
+ * association shared key.
+ */
+struct sctp_authkey {
+ sctp_assoc_t sca_assoc_id;
+ __u16 sca_keynumber;
+ __u16 sca_keylength;
+ __u8 sca_key[];
+};
+
+/*
+ * 7.1.21. Get or set the active shared key (SCTP_AUTH_ACTIVE_KEY)
+ *
+ * This option will get or set the active shared key to be used to build
+ * the association shared key.
+ */
+
+struct sctp_authkeyid {
+ sctp_assoc_t scact_assoc_id;
+ __u16 scact_keynumber;
+};
+
+
+/*
+ * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK)
+ *
+ * This option will effect the way delayed acks are performed. This
+ * option allows you to get or set the delayed ack time, in
+ * milliseconds. It also allows changing the delayed ack frequency.
+ * Changing the frequency to 1 disables the delayed sack algorithm. If
+ * the assoc_id is 0, then this sets or gets the endpoints default
+ * values. If the assoc_id field is non-zero, then the set or get
+ * effects the specified association for the one to many model (the
+ * assoc_id field is ignored by the one to one model). Note that if
+ * sack_delay or sack_freq are 0 when setting this option, then the
+ * current values will remain unchanged.
+ */
+struct sctp_sack_info {
+ sctp_assoc_t sack_assoc_id;
+ uint32_t sack_delay;
+ uint32_t sack_freq;
+};
+
+struct sctp_assoc_value {
+ sctp_assoc_t assoc_id;
+ uint32_t assoc_value;
+};
+
+struct sctp_stream_value {
+ sctp_assoc_t assoc_id;
+ uint16_t stream_id;
+ uint16_t stream_value;
+};
+
+/*
+ * 7.2.2 Peer Address Information
+ *
+ * Applications can retrieve information about a specific peer address
+ * of an association, including its reachability state, congestion
+ * window, and retransmission timer values. This information is
+ * read-only. The following structure is used to access this
+ * information:
+ */
+struct sctp_paddrinfo {
+ sctp_assoc_t spinfo_assoc_id;
+ struct sockaddr_storage spinfo_address;
+ __s32 spinfo_state;
+ __u32 spinfo_cwnd;
+ __u32 spinfo_srtt;
+ __u32 spinfo_rto;
+ __u32 spinfo_mtu;
+} __attribute__((packed, aligned(4)));
+
+/* Peer addresses's state. */
+/* UNKNOWN: Peer address passed by the upper layer in sendmsg or connect[x]
+ * calls.
+ * UNCONFIRMED: Peer address received in INIT/INIT-ACK address parameters.
+ * Not yet confirmed by a heartbeat and not available for data
+ * transfers.
+ * ACTIVE : Peer address confirmed, active and available for data transfers.
+ * INACTIVE: Peer address inactive and not available for data transfers.
+ */
+enum sctp_spinfo_state {
+ SCTP_INACTIVE,
+ SCTP_PF,
+#define SCTP_POTENTIALLY_FAILED SCTP_PF
+ SCTP_ACTIVE,
+ SCTP_UNCONFIRMED,
+ SCTP_UNKNOWN = 0xffff /* Value used for transport state unknown */
+};
+
+/*
+ * 7.2.1 Association Status (SCTP_STATUS)
+ *
+ * Applications can retrieve current status information about an
+ * association, including association state, peer receiver window size,
+ * number of unacked data chunks, and number of data chunks pending
+ * receipt. This information is read-only. The following structure is
+ * used to access this information:
+ */
+struct sctp_status {
+ sctp_assoc_t sstat_assoc_id;
+ __s32 sstat_state;
+ __u32 sstat_rwnd;
+ __u16 sstat_unackdata;
+ __u16 sstat_penddata;
+ __u16 sstat_instrms;
+ __u16 sstat_outstrms;
+ __u32 sstat_fragmentation_point;
+ struct sctp_paddrinfo sstat_primary;
+};
+
+/*
+ * 7.2.3. Get the list of chunks the peer requires to be authenticated
+ * (SCTP_PEER_AUTH_CHUNKS)
+ *
+ * This option gets a list of chunks for a specified association that
+ * the peer requires to be received authenticated only.
+ */
+struct sctp_authchunks {
+ sctp_assoc_t gauth_assoc_id;
+ __u32 gauth_number_of_chunks;
+ uint8_t gauth_chunks[];
+};
+
+/* The broken spelling has been released already in lksctp-tools header,
+ * so don't break anyone, now that it's fixed.
+ */
+#define guth_number_of_chunks gauth_number_of_chunks
+
+/* Association states. */
+enum sctp_sstat_state {
+ SCTP_EMPTY = 0,
+ SCTP_CLOSED = 1,
+ SCTP_COOKIE_WAIT = 2,
+ SCTP_COOKIE_ECHOED = 3,
+ SCTP_ESTABLISHED = 4,
+ SCTP_SHUTDOWN_PENDING = 5,
+ SCTP_SHUTDOWN_SENT = 6,
+ SCTP_SHUTDOWN_RECEIVED = 7,
+ SCTP_SHUTDOWN_ACK_SENT = 8,
+};
+
+/*
+ * 8.2.6. Get the Current Identifiers of Associations
+ * (SCTP_GET_ASSOC_ID_LIST)
+ *
+ * This option gets the current list of SCTP association identifiers of
+ * the SCTP associations handled by a one-to-many style socket.
+ */
+struct sctp_assoc_ids {
+ __u32 gaids_number_of_ids;
+ sctp_assoc_t gaids_assoc_id[];
+};
+
+/*
+ * 8.3, 8.5 get all peer/local addresses in an association.
+ * This parameter struct is used by SCTP_GET_PEER_ADDRS and
+ * SCTP_GET_LOCAL_ADDRS socket options used internally to implement
+ * sctp_getpaddrs() and sctp_getladdrs() API.
+ */
+struct sctp_getaddrs_old {
+ sctp_assoc_t assoc_id;
+ int addr_num;
+ struct sockaddr *addrs;
+};
+
+struct sctp_getaddrs {
+ sctp_assoc_t assoc_id; /*input*/
+ __u32 addr_num; /*output*/
+ __u8 addrs[]; /*output, variable size*/
+};
+
+/* A socket user request obtained via SCTP_GET_ASSOC_STATS that retrieves
+ * association stats. All stats are counts except sas_maxrto and
+ * sas_obs_rto_ipaddr. maxrto is the max observed rto + transport since
+ * the last call. Will return 0 when RTO was not update since last call
+ */
+struct sctp_assoc_stats {
+ sctp_assoc_t sas_assoc_id; /* Input */
+ /* Transport of observed max RTO */
+ struct sockaddr_storage sas_obs_rto_ipaddr;
+ __u64 sas_maxrto; /* Maximum Observed RTO for period */
+ __u64 sas_isacks; /* SACKs received */
+ __u64 sas_osacks; /* SACKs sent */
+ __u64 sas_opackets; /* Packets sent */
+ __u64 sas_ipackets; /* Packets received */
+ __u64 sas_rtxchunks; /* Retransmitted Chunks */
+ __u64 sas_outofseqtsns;/* TSN received > next expected */
+ __u64 sas_idupchunks; /* Dups received (ordered+unordered) */
+ __u64 sas_gapcnt; /* Gap Acknowledgements Received */
+ __u64 sas_ouodchunks; /* Unordered data chunks sent */
+ __u64 sas_iuodchunks; /* Unordered data chunks received */
+ __u64 sas_oodchunks; /* Ordered data chunks sent */
+ __u64 sas_iodchunks; /* Ordered data chunks received */
+ __u64 sas_octrlchunks; /* Control chunks sent */
+ __u64 sas_ictrlchunks; /* Control chunks received */
+};
+
+/*
+ * 8.1 sctp_bindx()
+ *
+ * The flags parameter is formed from the bitwise OR of zero or more of the
+ * following currently defined flags:
+ */
+#define SCTP_BINDX_ADD_ADDR 0x01
+#define SCTP_BINDX_REM_ADDR 0x02
+
+/* This is the structure that is passed as an argument(optval) to
+ * getsockopt(SCTP_SOCKOPT_PEELOFF).
+ */
+typedef struct {
+ sctp_assoc_t associd;
+ int sd;
+} sctp_peeloff_arg_t;
+
+typedef struct {
+ sctp_peeloff_arg_t p_arg;
+ unsigned flags;
+} sctp_peeloff_flags_arg_t;
+
+/*
+ * Peer Address Thresholds socket option
+ */
+struct sctp_paddrthlds {
+ sctp_assoc_t spt_assoc_id;
+ struct sockaddr_storage spt_address;
+ __u16 spt_pathmaxrxt;
+ __u16 spt_pathpfthld;
+};
+
+/* Use a new structure with spt_pathcpthld for back compatibility */
+struct sctp_paddrthlds_v2 {
+ sctp_assoc_t spt_assoc_id;
+ struct sockaddr_storage spt_address;
+ __u16 spt_pathmaxrxt;
+ __u16 spt_pathpfthld;
+ __u16 spt_pathcpthld;
+};
+
+/*
+ * Socket Option for Getting the Association/Stream-Specific PR-SCTP Status
+ */
+struct sctp_prstatus {
+ sctp_assoc_t sprstat_assoc_id;
+ __u16 sprstat_sid;
+ __u16 sprstat_policy;
+ __u64 sprstat_abandoned_unsent;
+ __u64 sprstat_abandoned_sent;
+};
+
+struct sctp_default_prinfo {
+ sctp_assoc_t pr_assoc_id;
+ __u32 pr_value;
+ __u16 pr_policy;
+};
+
+struct sctp_info {
+ __u32 sctpi_tag;
+ __u32 sctpi_state;
+ __u32 sctpi_rwnd;
+ __u16 sctpi_unackdata;
+ __u16 sctpi_penddata;
+ __u16 sctpi_instrms;
+ __u16 sctpi_outstrms;
+ __u32 sctpi_fragmentation_point;
+ __u32 sctpi_inqueue;
+ __u32 sctpi_outqueue;
+ __u32 sctpi_overall_error;
+ __u32 sctpi_max_burst;
+ __u32 sctpi_maxseg;
+ __u32 sctpi_peer_rwnd;
+ __u32 sctpi_peer_tag;
+ __u8 sctpi_peer_capable;
+ __u8 sctpi_peer_sack;
+ __u16 __reserved1;
+
+ /* assoc status info */
+ __u64 sctpi_isacks;
+ __u64 sctpi_osacks;
+ __u64 sctpi_opackets;
+ __u64 sctpi_ipackets;
+ __u64 sctpi_rtxchunks;
+ __u64 sctpi_outofseqtsns;
+ __u64 sctpi_idupchunks;
+ __u64 sctpi_gapcnt;
+ __u64 sctpi_ouodchunks;
+ __u64 sctpi_iuodchunks;
+ __u64 sctpi_oodchunks;
+ __u64 sctpi_iodchunks;
+ __u64 sctpi_octrlchunks;
+ __u64 sctpi_ictrlchunks;
+
+ /* primary transport info */
+ struct sockaddr_storage sctpi_p_address;
+ __s32 sctpi_p_state;
+ __u32 sctpi_p_cwnd;
+ __u32 sctpi_p_srtt;
+ __u32 sctpi_p_rto;
+ __u32 sctpi_p_hbinterval;
+ __u32 sctpi_p_pathmaxrxt;
+ __u32 sctpi_p_sackdelay;
+ __u32 sctpi_p_sackfreq;
+ __u32 sctpi_p_ssthresh;
+ __u32 sctpi_p_partial_bytes_acked;
+ __u32 sctpi_p_flight_size;
+ __u16 sctpi_p_error;
+ __u16 __reserved2;
+
+ /* sctp sock info */
+ __u32 sctpi_s_autoclose;
+ __u32 sctpi_s_adaptation_ind;
+ __u32 sctpi_s_pd_point;
+ __u8 sctpi_s_nodelay;
+ __u8 sctpi_s_disable_fragments;
+ __u8 sctpi_s_v4mapped;
+ __u8 sctpi_s_frag_interleave;
+ __u32 sctpi_s_type;
+ __u32 __reserved3;
+};
+
+struct sctp_reset_streams {
+ sctp_assoc_t srs_assoc_id;
+ uint16_t srs_flags;
+ uint16_t srs_number_streams; /* 0 == ALL */
+ uint16_t srs_stream_list[]; /* list if srs_num_streams is not 0 */
+};
+
+struct sctp_add_streams {
+ sctp_assoc_t sas_assoc_id;
+ uint16_t sas_instrms;
+ uint16_t sas_outstrms;
+};
+
+struct sctp_event {
+ sctp_assoc_t se_assoc_id;
+ uint16_t se_type;
+ uint8_t se_on;
+};
+
+struct sctp_udpencaps {
+ sctp_assoc_t sue_assoc_id;
+ struct sockaddr_storage sue_address;
+ uint16_t sue_port;
+};
+
+/* SCTP Stream schedulers */
+enum sctp_sched_type {
+ SCTP_SS_FCFS,
+ SCTP_SS_DEFAULT = SCTP_SS_FCFS,
+ SCTP_SS_PRIO,
+ SCTP_SS_RR,
+ SCTP_SS_FC,
+ SCTP_SS_WFQ,
+ SCTP_SS_MAX = SCTP_SS_WFQ
+};
+
+/* Probe Interval socket option */
+struct sctp_probeinterval {
+ sctp_assoc_t spi_assoc_id;
+ struct sockaddr_storage spi_address;
+ __u32 spi_interval;
+};
+
+#endif /* _SCTP_H */
diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h
new file mode 100644
index 0000000..e888b00
--- /dev/null
+++ b/include/uapi/linux/seg6.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_SEG6_H
+#define _LINUX_SEG6_H
+
+#include <linux/types.h>
+#include <linux/in6.h> /* For struct in6_addr. */
+
+/*
+ * SRH
+ */
+struct ipv6_sr_hdr {
+ __u8 nexthdr;
+ __u8 hdrlen;
+ __u8 type;
+ __u8 segments_left;
+ __u8 first_segment; /* Represents the last_entry field of SRH */
+ __u8 flags;
+ __u16 tag;
+
+ struct in6_addr segments[];
+};
+
+#define SR6_FLAG1_PROTECTED (1 << 6)
+#define SR6_FLAG1_OAM (1 << 5)
+#define SR6_FLAG1_ALERT (1 << 4)
+#define SR6_FLAG1_HMAC (1 << 3)
+
+#define SR6_TLV_INGRESS 1
+#define SR6_TLV_EGRESS 2
+#define SR6_TLV_OPAQUE 3
+#define SR6_TLV_PADDING 4
+#define SR6_TLV_HMAC 5
+
+#define sr_has_hmac(srh) ((srh)->flags & SR6_FLAG1_HMAC)
+
+struct sr6_tlv {
+ __u8 type;
+ __u8 len;
+ __u8 data[0];
+};
+
+#endif
diff --git a/include/uapi/linux/seg6_genl.h b/include/uapi/linux/seg6_genl.h
new file mode 100644
index 0000000..0c23052
--- /dev/null
+++ b/include/uapi/linux/seg6_genl.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_SEG6_GENL_H
+#define _LINUX_SEG6_GENL_H
+
+#define SEG6_GENL_NAME "SEG6"
+#define SEG6_GENL_VERSION 0x1
+
+enum {
+ SEG6_ATTR_UNSPEC,
+ SEG6_ATTR_DST,
+ SEG6_ATTR_DSTLEN,
+ SEG6_ATTR_HMACKEYID,
+ SEG6_ATTR_SECRET,
+ SEG6_ATTR_SECRETLEN,
+ SEG6_ATTR_ALGID,
+ SEG6_ATTR_HMACINFO,
+ __SEG6_ATTR_MAX,
+};
+
+#define SEG6_ATTR_MAX (__SEG6_ATTR_MAX - 1)
+
+enum {
+ SEG6_CMD_UNSPEC,
+ SEG6_CMD_SETHMAC,
+ SEG6_CMD_DUMPHMAC,
+ SEG6_CMD_SET_TUNSRC,
+ SEG6_CMD_GET_TUNSRC,
+ __SEG6_CMD_MAX,
+};
+
+#define SEG6_CMD_MAX (__SEG6_CMD_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/seg6_hmac.h b/include/uapi/linux/seg6_hmac.h
new file mode 100644
index 0000000..3fb3412
--- /dev/null
+++ b/include/uapi/linux/seg6_hmac.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_SEG6_HMAC_H
+#define _LINUX_SEG6_HMAC_H
+
+#include <linux/types.h>
+#include <linux/seg6.h>
+
+#define SEG6_HMAC_SECRET_LEN 64
+#define SEG6_HMAC_FIELD_LEN 32
+
+struct sr6_tlv_hmac {
+ struct sr6_tlv tlvhdr;
+ __u16 reserved;
+ __be32 hmackeyid;
+ __u8 hmac[SEG6_HMAC_FIELD_LEN];
+};
+
+enum {
+ SEG6_HMAC_ALGO_SHA1 = 1,
+ SEG6_HMAC_ALGO_SHA256 = 2,
+};
+
+#endif
diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h
new file mode 100644
index 0000000..e1929d2
--- /dev/null
+++ b/include/uapi/linux/seg6_iptunnel.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_SEG6_IPTUNNEL_H
+#define _LINUX_SEG6_IPTUNNEL_H
+
+#include <linux/seg6.h> /* For struct ipv6_sr_hdr. */
+
+enum {
+ SEG6_IPTUNNEL_UNSPEC,
+ SEG6_IPTUNNEL_SRH,
+ __SEG6_IPTUNNEL_MAX,
+};
+#define SEG6_IPTUNNEL_MAX (__SEG6_IPTUNNEL_MAX - 1)
+
+struct seg6_iptunnel_encap {
+ int mode;
+ struct ipv6_sr_hdr srh[];
+};
+
+#define SEG6_IPTUN_ENCAP_SIZE(x) ((sizeof(*x)) + (((x)->srh->hdrlen + 1) << 3))
+
+enum {
+ SEG6_IPTUN_MODE_INLINE,
+ SEG6_IPTUN_MODE_ENCAP,
+ SEG6_IPTUN_MODE_L2ENCAP,
+ SEG6_IPTUN_MODE_ENCAP_RED,
+ SEG6_IPTUN_MODE_L2ENCAP_RED,
+};
+
+#endif
diff --git a/include/uapi/linux/seg6_local.h b/include/uapi/linux/seg6_local.h
new file mode 100644
index 0000000..6e71d97
--- /dev/null
+++ b/include/uapi/linux/seg6_local.h
@@ -0,0 +1,137 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_SEG6_LOCAL_H
+#define _LINUX_SEG6_LOCAL_H
+
+#include <linux/seg6.h>
+
+enum {
+ SEG6_LOCAL_UNSPEC,
+ SEG6_LOCAL_ACTION,
+ SEG6_LOCAL_SRH,
+ SEG6_LOCAL_TABLE,
+ SEG6_LOCAL_NH4,
+ SEG6_LOCAL_NH6,
+ SEG6_LOCAL_IIF,
+ SEG6_LOCAL_OIF,
+ SEG6_LOCAL_BPF,
+ SEG6_LOCAL_VRFTABLE,
+ SEG6_LOCAL_COUNTERS,
+ SEG6_LOCAL_FLAVORS,
+ __SEG6_LOCAL_MAX,
+};
+#define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1)
+
+enum {
+ SEG6_LOCAL_ACTION_UNSPEC = 0,
+ /* node segment */
+ SEG6_LOCAL_ACTION_END = 1,
+ /* adjacency segment (IPv6 cross-connect) */
+ SEG6_LOCAL_ACTION_END_X = 2,
+ /* lookup of next seg NH in table */
+ SEG6_LOCAL_ACTION_END_T = 3,
+ /* decap and L2 cross-connect */
+ SEG6_LOCAL_ACTION_END_DX2 = 4,
+ /* decap and IPv6 cross-connect */
+ SEG6_LOCAL_ACTION_END_DX6 = 5,
+ /* decap and IPv4 cross-connect */
+ SEG6_LOCAL_ACTION_END_DX4 = 6,
+ /* decap and lookup of DA in v6 table */
+ SEG6_LOCAL_ACTION_END_DT6 = 7,
+ /* decap and lookup of DA in v4 table */
+ SEG6_LOCAL_ACTION_END_DT4 = 8,
+ /* binding segment with insertion */
+ SEG6_LOCAL_ACTION_END_B6 = 9,
+ /* binding segment with encapsulation */
+ SEG6_LOCAL_ACTION_END_B6_ENCAP = 10,
+ /* binding segment with MPLS encap */
+ SEG6_LOCAL_ACTION_END_BM = 11,
+ /* lookup last seg in table */
+ SEG6_LOCAL_ACTION_END_S = 12,
+ /* forward to SR-unaware VNF with static proxy */
+ SEG6_LOCAL_ACTION_END_AS = 13,
+ /* forward to SR-unaware VNF with masquerading */
+ SEG6_LOCAL_ACTION_END_AM = 14,
+ /* custom BPF action */
+ SEG6_LOCAL_ACTION_END_BPF = 15,
+ /* decap and lookup of DA in v4 or v6 table */
+ SEG6_LOCAL_ACTION_END_DT46 = 16,
+
+ __SEG6_LOCAL_ACTION_MAX,
+};
+
+#define SEG6_LOCAL_ACTION_MAX (__SEG6_LOCAL_ACTION_MAX - 1)
+
+enum {
+ SEG6_LOCAL_BPF_PROG_UNSPEC,
+ SEG6_LOCAL_BPF_PROG,
+ SEG6_LOCAL_BPF_PROG_NAME,
+ __SEG6_LOCAL_BPF_PROG_MAX,
+};
+
+#define SEG6_LOCAL_BPF_PROG_MAX (__SEG6_LOCAL_BPF_PROG_MAX - 1)
+
+/* SRv6 Behavior counters are encoded as netlink attributes guaranteeing the
+ * correct alignment.
+ * Each counter is identified by a different attribute type (i.e.
+ * SEG6_LOCAL_CNT_PACKETS).
+ *
+ * - SEG6_LOCAL_CNT_PACKETS: identifies a counter that counts the number of
+ * packets that have been CORRECTLY processed by an SRv6 Behavior instance
+ * (i.e., packets that generate errors or are dropped are NOT counted).
+ *
+ * - SEG6_LOCAL_CNT_BYTES: identifies a counter that counts the total amount
+ * of traffic in bytes of all packets that have been CORRECTLY processed by
+ * an SRv6 Behavior instance (i.e., packets that generate errors or are
+ * dropped are NOT counted).
+ *
+ * - SEG6_LOCAL_CNT_ERRORS: identifies a counter that counts the number of
+ * packets that have NOT been properly processed by an SRv6 Behavior instance
+ * (i.e., packets that generate errors or are dropped).
+ */
+enum {
+ SEG6_LOCAL_CNT_UNSPEC,
+ SEG6_LOCAL_CNT_PAD, /* pad for 64 bits values */
+ SEG6_LOCAL_CNT_PACKETS,
+ SEG6_LOCAL_CNT_BYTES,
+ SEG6_LOCAL_CNT_ERRORS,
+ __SEG6_LOCAL_CNT_MAX,
+};
+
+#define SEG6_LOCAL_CNT_MAX (__SEG6_LOCAL_CNT_MAX - 1)
+
+/* SRv6 End* Flavor attributes */
+enum {
+ SEG6_LOCAL_FLV_UNSPEC,
+ SEG6_LOCAL_FLV_OPERATION,
+ SEG6_LOCAL_FLV_LCBLOCK_BITS,
+ SEG6_LOCAL_FLV_LCNODE_FN_BITS,
+ __SEG6_LOCAL_FLV_MAX,
+};
+
+#define SEG6_LOCAL_FLV_MAX (__SEG6_LOCAL_FLV_MAX - 1)
+
+/* Designed flavor operations for SRv6 End* Behavior */
+enum {
+ SEG6_LOCAL_FLV_OP_UNSPEC,
+ SEG6_LOCAL_FLV_OP_PSP,
+ SEG6_LOCAL_FLV_OP_USP,
+ SEG6_LOCAL_FLV_OP_USD,
+ SEG6_LOCAL_FLV_OP_NEXT_CSID,
+ __SEG6_LOCAL_FLV_OP_MAX
+};
+
+#define SEG6_LOCAL_FLV_OP_MAX (__SEG6_LOCAL_FLV_OP_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
new file mode 100644
index 0000000..a0819c6
--- /dev/null
+++ b/include/uapi/linux/snmp.h
@@ -0,0 +1,362 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Definitions for MIBs
+ *
+ * Author: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
+ */
+
+#ifndef _LINUX_SNMP_H
+#define _LINUX_SNMP_H
+
+/* ipstats mib definitions */
+/*
+ * RFC 1213: MIB-II
+ * RFC 2011 (updates 1213): SNMPv2-MIB-IP
+ * RFC 2863: Interfaces Group MIB
+ * RFC 2465: IPv6 MIB: General Group
+ * draft-ietf-ipv6-rfc2011-update-10.txt: MIB for IP: IP Statistics Tables
+ */
+enum
+{
+ IPSTATS_MIB_NUM = 0,
+/* frequently written fields in fast path, kept in same cache line */
+ IPSTATS_MIB_INPKTS, /* InReceives */
+ IPSTATS_MIB_INOCTETS, /* InOctets */
+ IPSTATS_MIB_INDELIVERS, /* InDelivers */
+ IPSTATS_MIB_OUTFORWDATAGRAMS, /* OutForwDatagrams */
+ IPSTATS_MIB_OUTREQUESTS, /* OutRequests */
+ IPSTATS_MIB_OUTOCTETS, /* OutOctets */
+/* other fields */
+ IPSTATS_MIB_INHDRERRORS, /* InHdrErrors */
+ IPSTATS_MIB_INTOOBIGERRORS, /* InTooBigErrors */
+ IPSTATS_MIB_INNOROUTES, /* InNoRoutes */
+ IPSTATS_MIB_INADDRERRORS, /* InAddrErrors */
+ IPSTATS_MIB_INUNKNOWNPROTOS, /* InUnknownProtos */
+ IPSTATS_MIB_INTRUNCATEDPKTS, /* InTruncatedPkts */
+ IPSTATS_MIB_INDISCARDS, /* InDiscards */
+ IPSTATS_MIB_OUTDISCARDS, /* OutDiscards */
+ IPSTATS_MIB_OUTNOROUTES, /* OutNoRoutes */
+ IPSTATS_MIB_REASMTIMEOUT, /* ReasmTimeout */
+ IPSTATS_MIB_REASMREQDS, /* ReasmReqds */
+ IPSTATS_MIB_REASMOKS, /* ReasmOKs */
+ IPSTATS_MIB_REASMFAILS, /* ReasmFails */
+ IPSTATS_MIB_FRAGOKS, /* FragOKs */
+ IPSTATS_MIB_FRAGFAILS, /* FragFails */
+ IPSTATS_MIB_FRAGCREATES, /* FragCreates */
+ IPSTATS_MIB_INMCASTPKTS, /* InMcastPkts */
+ IPSTATS_MIB_OUTMCASTPKTS, /* OutMcastPkts */
+ IPSTATS_MIB_INBCASTPKTS, /* InBcastPkts */
+ IPSTATS_MIB_OUTBCASTPKTS, /* OutBcastPkts */
+ IPSTATS_MIB_INMCASTOCTETS, /* InMcastOctets */
+ IPSTATS_MIB_OUTMCASTOCTETS, /* OutMcastOctets */
+ IPSTATS_MIB_INBCASTOCTETS, /* InBcastOctets */
+ IPSTATS_MIB_OUTBCASTOCTETS, /* OutBcastOctets */
+ IPSTATS_MIB_CSUMERRORS, /* InCsumErrors */
+ IPSTATS_MIB_NOECTPKTS, /* InNoECTPkts */
+ IPSTATS_MIB_ECT1PKTS, /* InECT1Pkts */
+ IPSTATS_MIB_ECT0PKTS, /* InECT0Pkts */
+ IPSTATS_MIB_CEPKTS, /* InCEPkts */
+ IPSTATS_MIB_REASM_OVERLAPS, /* ReasmOverlaps */
+ IPSTATS_MIB_OUTPKTS, /* OutTransmits */
+ __IPSTATS_MIB_MAX
+};
+
+/* icmp mib definitions */
+/*
+ * RFC 1213: MIB-II ICMP Group
+ * RFC 2011 (updates 1213): SNMPv2 MIB for IP: ICMP group
+ */
+enum
+{
+ ICMP_MIB_NUM = 0,
+ ICMP_MIB_INMSGS, /* InMsgs */
+ ICMP_MIB_INERRORS, /* InErrors */
+ ICMP_MIB_INDESTUNREACHS, /* InDestUnreachs */
+ ICMP_MIB_INTIMEEXCDS, /* InTimeExcds */
+ ICMP_MIB_INPARMPROBS, /* InParmProbs */
+ ICMP_MIB_INSRCQUENCHS, /* InSrcQuenchs */
+ ICMP_MIB_INREDIRECTS, /* InRedirects */
+ ICMP_MIB_INECHOS, /* InEchos */
+ ICMP_MIB_INECHOREPS, /* InEchoReps */
+ ICMP_MIB_INTIMESTAMPS, /* InTimestamps */
+ ICMP_MIB_INTIMESTAMPREPS, /* InTimestampReps */
+ ICMP_MIB_INADDRMASKS, /* InAddrMasks */
+ ICMP_MIB_INADDRMASKREPS, /* InAddrMaskReps */
+ ICMP_MIB_OUTMSGS, /* OutMsgs */
+ ICMP_MIB_OUTERRORS, /* OutErrors */
+ ICMP_MIB_OUTDESTUNREACHS, /* OutDestUnreachs */
+ ICMP_MIB_OUTTIMEEXCDS, /* OutTimeExcds */
+ ICMP_MIB_OUTPARMPROBS, /* OutParmProbs */
+ ICMP_MIB_OUTSRCQUENCHS, /* OutSrcQuenchs */
+ ICMP_MIB_OUTREDIRECTS, /* OutRedirects */
+ ICMP_MIB_OUTECHOS, /* OutEchos */
+ ICMP_MIB_OUTECHOREPS, /* OutEchoReps */
+ ICMP_MIB_OUTTIMESTAMPS, /* OutTimestamps */
+ ICMP_MIB_OUTTIMESTAMPREPS, /* OutTimestampReps */
+ ICMP_MIB_OUTADDRMASKS, /* OutAddrMasks */
+ ICMP_MIB_OUTADDRMASKREPS, /* OutAddrMaskReps */
+ ICMP_MIB_CSUMERRORS, /* InCsumErrors */
+ ICMP_MIB_RATELIMITGLOBAL, /* OutRateLimitGlobal */
+ ICMP_MIB_RATELIMITHOST, /* OutRateLimitHost */
+ __ICMP_MIB_MAX
+};
+
+#define __ICMPMSG_MIB_MAX 512 /* Out+In for all 8-bit ICMP types */
+
+/* icmp6 mib definitions */
+/*
+ * RFC 2466: ICMPv6-MIB
+ */
+enum
+{
+ ICMP6_MIB_NUM = 0,
+ ICMP6_MIB_INMSGS, /* InMsgs */
+ ICMP6_MIB_INERRORS, /* InErrors */
+ ICMP6_MIB_OUTMSGS, /* OutMsgs */
+ ICMP6_MIB_OUTERRORS, /* OutErrors */
+ ICMP6_MIB_CSUMERRORS, /* InCsumErrors */
+ ICMP6_MIB_RATELIMITHOST, /* OutRateLimitHost */
+ __ICMP6_MIB_MAX
+};
+
+#define __ICMP6MSG_MIB_MAX 512 /* Out+In for all 8-bit ICMPv6 types */
+
+/* tcp mib definitions */
+/*
+ * RFC 1213: MIB-II TCP group
+ * RFC 2012 (updates 1213): SNMPv2-MIB-TCP
+ */
+enum
+{
+ TCP_MIB_NUM = 0,
+ TCP_MIB_RTOALGORITHM, /* RtoAlgorithm */
+ TCP_MIB_RTOMIN, /* RtoMin */
+ TCP_MIB_RTOMAX, /* RtoMax */
+ TCP_MIB_MAXCONN, /* MaxConn */
+ TCP_MIB_ACTIVEOPENS, /* ActiveOpens */
+ TCP_MIB_PASSIVEOPENS, /* PassiveOpens */
+ TCP_MIB_ATTEMPTFAILS, /* AttemptFails */
+ TCP_MIB_ESTABRESETS, /* EstabResets */
+ TCP_MIB_CURRESTAB, /* CurrEstab */
+ TCP_MIB_INSEGS, /* InSegs */
+ TCP_MIB_OUTSEGS, /* OutSegs */
+ TCP_MIB_RETRANSSEGS, /* RetransSegs */
+ TCP_MIB_INERRS, /* InErrs */
+ TCP_MIB_OUTRSTS, /* OutRsts */
+ TCP_MIB_CSUMERRORS, /* InCsumErrors */
+ __TCP_MIB_MAX
+};
+
+/* udp mib definitions */
+/*
+ * RFC 1213: MIB-II UDP group
+ * RFC 2013 (updates 1213): SNMPv2-MIB-UDP
+ */
+enum
+{
+ UDP_MIB_NUM = 0,
+ UDP_MIB_INDATAGRAMS, /* InDatagrams */
+ UDP_MIB_NOPORTS, /* NoPorts */
+ UDP_MIB_INERRORS, /* InErrors */
+ UDP_MIB_OUTDATAGRAMS, /* OutDatagrams */
+ UDP_MIB_RCVBUFERRORS, /* RcvbufErrors */
+ UDP_MIB_SNDBUFERRORS, /* SndbufErrors */
+ UDP_MIB_CSUMERRORS, /* InCsumErrors */
+ UDP_MIB_IGNOREDMULTI, /* IgnoredMulti */
+ UDP_MIB_MEMERRORS, /* MemErrors */
+ __UDP_MIB_MAX
+};
+
+/* linux mib definitions */
+enum
+{
+ LINUX_MIB_NUM = 0,
+ LINUX_MIB_SYNCOOKIESSENT, /* SyncookiesSent */
+ LINUX_MIB_SYNCOOKIESRECV, /* SyncookiesRecv */
+ LINUX_MIB_SYNCOOKIESFAILED, /* SyncookiesFailed */
+ LINUX_MIB_EMBRYONICRSTS, /* EmbryonicRsts */
+ LINUX_MIB_PRUNECALLED, /* PruneCalled */
+ LINUX_MIB_RCVPRUNED, /* RcvPruned */
+ LINUX_MIB_OFOPRUNED, /* OfoPruned */
+ LINUX_MIB_OUTOFWINDOWICMPS, /* OutOfWindowIcmps */
+ LINUX_MIB_LOCKDROPPEDICMPS, /* LockDroppedIcmps */
+ LINUX_MIB_ARPFILTER, /* ArpFilter */
+ LINUX_MIB_TIMEWAITED, /* TimeWaited */
+ LINUX_MIB_TIMEWAITRECYCLED, /* TimeWaitRecycled */
+ LINUX_MIB_TIMEWAITKILLED, /* TimeWaitKilled */
+ LINUX_MIB_PAWSACTIVEREJECTED, /* PAWSActiveRejected */
+ LINUX_MIB_PAWSESTABREJECTED, /* PAWSEstabRejected */
+ LINUX_MIB_DELAYEDACKS, /* DelayedACKs */
+ LINUX_MIB_DELAYEDACKLOCKED, /* DelayedACKLocked */
+ LINUX_MIB_DELAYEDACKLOST, /* DelayedACKLost */
+ LINUX_MIB_LISTENOVERFLOWS, /* ListenOverflows */
+ LINUX_MIB_LISTENDROPS, /* ListenDrops */
+ LINUX_MIB_TCPHPHITS, /* TCPHPHits */
+ LINUX_MIB_TCPPUREACKS, /* TCPPureAcks */
+ LINUX_MIB_TCPHPACKS, /* TCPHPAcks */
+ LINUX_MIB_TCPRENORECOVERY, /* TCPRenoRecovery */
+ LINUX_MIB_TCPSACKRECOVERY, /* TCPSackRecovery */
+ LINUX_MIB_TCPSACKRENEGING, /* TCPSACKReneging */
+ LINUX_MIB_TCPSACKREORDER, /* TCPSACKReorder */
+ LINUX_MIB_TCPRENOREORDER, /* TCPRenoReorder */
+ LINUX_MIB_TCPTSREORDER, /* TCPTSReorder */
+ LINUX_MIB_TCPFULLUNDO, /* TCPFullUndo */
+ LINUX_MIB_TCPPARTIALUNDO, /* TCPPartialUndo */
+ LINUX_MIB_TCPDSACKUNDO, /* TCPDSACKUndo */
+ LINUX_MIB_TCPLOSSUNDO, /* TCPLossUndo */
+ LINUX_MIB_TCPLOSTRETRANSMIT, /* TCPLostRetransmit */
+ LINUX_MIB_TCPRENOFAILURES, /* TCPRenoFailures */
+ LINUX_MIB_TCPSACKFAILURES, /* TCPSackFailures */
+ LINUX_MIB_TCPLOSSFAILURES, /* TCPLossFailures */
+ LINUX_MIB_TCPFASTRETRANS, /* TCPFastRetrans */
+ LINUX_MIB_TCPSLOWSTARTRETRANS, /* TCPSlowStartRetrans */
+ LINUX_MIB_TCPTIMEOUTS, /* TCPTimeouts */
+ LINUX_MIB_TCPLOSSPROBES, /* TCPLossProbes */
+ LINUX_MIB_TCPLOSSPROBERECOVERY, /* TCPLossProbeRecovery */
+ LINUX_MIB_TCPRENORECOVERYFAIL, /* TCPRenoRecoveryFail */
+ LINUX_MIB_TCPSACKRECOVERYFAIL, /* TCPSackRecoveryFail */
+ LINUX_MIB_TCPRCVCOLLAPSED, /* TCPRcvCollapsed */
+ LINUX_MIB_TCPDSACKOLDSENT, /* TCPDSACKOldSent */
+ LINUX_MIB_TCPDSACKOFOSENT, /* TCPDSACKOfoSent */
+ LINUX_MIB_TCPDSACKRECV, /* TCPDSACKRecv */
+ LINUX_MIB_TCPDSACKOFORECV, /* TCPDSACKOfoRecv */
+ LINUX_MIB_TCPABORTONDATA, /* TCPAbortOnData */
+ LINUX_MIB_TCPABORTONCLOSE, /* TCPAbortOnClose */
+ LINUX_MIB_TCPABORTONMEMORY, /* TCPAbortOnMemory */
+ LINUX_MIB_TCPABORTONTIMEOUT, /* TCPAbortOnTimeout */
+ LINUX_MIB_TCPABORTONLINGER, /* TCPAbortOnLinger */
+ LINUX_MIB_TCPABORTFAILED, /* TCPAbortFailed */
+ LINUX_MIB_TCPMEMORYPRESSURES, /* TCPMemoryPressures */
+ LINUX_MIB_TCPMEMORYPRESSURESCHRONO, /* TCPMemoryPressuresChrono */
+ LINUX_MIB_TCPSACKDISCARD, /* TCPSACKDiscard */
+ LINUX_MIB_TCPDSACKIGNOREDOLD, /* TCPSACKIgnoredOld */
+ LINUX_MIB_TCPDSACKIGNOREDNOUNDO, /* TCPSACKIgnoredNoUndo */
+ LINUX_MIB_TCPSPURIOUSRTOS, /* TCPSpuriousRTOs */
+ LINUX_MIB_TCPMD5NOTFOUND, /* TCPMD5NotFound */
+ LINUX_MIB_TCPMD5UNEXPECTED, /* TCPMD5Unexpected */
+ LINUX_MIB_TCPMD5FAILURE, /* TCPMD5Failure */
+ LINUX_MIB_SACKSHIFTED,
+ LINUX_MIB_SACKMERGED,
+ LINUX_MIB_SACKSHIFTFALLBACK,
+ LINUX_MIB_TCPBACKLOGDROP,
+ LINUX_MIB_PFMEMALLOCDROP,
+ LINUX_MIB_TCPMINTTLDROP, /* RFC 5082 */
+ LINUX_MIB_TCPDEFERACCEPTDROP,
+ LINUX_MIB_IPRPFILTER, /* IP Reverse Path Filter (rp_filter) */
+ LINUX_MIB_TCPTIMEWAITOVERFLOW, /* TCPTimeWaitOverflow */
+ LINUX_MIB_TCPREQQFULLDOCOOKIES, /* TCPReqQFullDoCookies */
+ LINUX_MIB_TCPREQQFULLDROP, /* TCPReqQFullDrop */
+ LINUX_MIB_TCPRETRANSFAIL, /* TCPRetransFail */
+ LINUX_MIB_TCPRCVCOALESCE, /* TCPRcvCoalesce */
+ LINUX_MIB_TCPBACKLOGCOALESCE, /* TCPBacklogCoalesce */
+ LINUX_MIB_TCPOFOQUEUE, /* TCPOFOQueue */
+ LINUX_MIB_TCPOFODROP, /* TCPOFODrop */
+ LINUX_MIB_TCPOFOMERGE, /* TCPOFOMerge */
+ LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */
+ LINUX_MIB_TCPSYNCHALLENGE, /* TCPSYNChallenge */
+ LINUX_MIB_TCPFASTOPENACTIVE, /* TCPFastOpenActive */
+ LINUX_MIB_TCPFASTOPENACTIVEFAIL, /* TCPFastOpenActiveFail */
+ LINUX_MIB_TCPFASTOPENPASSIVE, /* TCPFastOpenPassive*/
+ LINUX_MIB_TCPFASTOPENPASSIVEFAIL, /* TCPFastOpenPassiveFail */
+ LINUX_MIB_TCPFASTOPENLISTENOVERFLOW, /* TCPFastOpenListenOverflow */
+ LINUX_MIB_TCPFASTOPENCOOKIEREQD, /* TCPFastOpenCookieReqd */
+ LINUX_MIB_TCPFASTOPENBLACKHOLE, /* TCPFastOpenBlackholeDetect */
+ LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */
+ LINUX_MIB_BUSYPOLLRXPACKETS, /* BusyPollRxPackets */
+ LINUX_MIB_TCPAUTOCORKING, /* TCPAutoCorking */
+ LINUX_MIB_TCPFROMZEROWINDOWADV, /* TCPFromZeroWindowAdv */
+ LINUX_MIB_TCPTOZEROWINDOWADV, /* TCPToZeroWindowAdv */
+ LINUX_MIB_TCPWANTZEROWINDOWADV, /* TCPWantZeroWindowAdv */
+ LINUX_MIB_TCPSYNRETRANS, /* TCPSynRetrans */
+ LINUX_MIB_TCPORIGDATASENT, /* TCPOrigDataSent */
+ LINUX_MIB_TCPHYSTARTTRAINDETECT, /* TCPHystartTrainDetect */
+ LINUX_MIB_TCPHYSTARTTRAINCWND, /* TCPHystartTrainCwnd */
+ LINUX_MIB_TCPHYSTARTDELAYDETECT, /* TCPHystartDelayDetect */
+ LINUX_MIB_TCPHYSTARTDELAYCWND, /* TCPHystartDelayCwnd */
+ LINUX_MIB_TCPACKSKIPPEDSYNRECV, /* TCPACKSkippedSynRecv */
+ LINUX_MIB_TCPACKSKIPPEDPAWS, /* TCPACKSkippedPAWS */
+ LINUX_MIB_TCPACKSKIPPEDSEQ, /* TCPACKSkippedSeq */
+ LINUX_MIB_TCPACKSKIPPEDFINWAIT2, /* TCPACKSkippedFinWait2 */
+ LINUX_MIB_TCPACKSKIPPEDTIMEWAIT, /* TCPACKSkippedTimeWait */
+ LINUX_MIB_TCPACKSKIPPEDCHALLENGE, /* TCPACKSkippedChallenge */
+ LINUX_MIB_TCPWINPROBE, /* TCPWinProbe */
+ LINUX_MIB_TCPKEEPALIVE, /* TCPKeepAlive */
+ LINUX_MIB_TCPMTUPFAIL, /* TCPMTUPFail */
+ LINUX_MIB_TCPMTUPSUCCESS, /* TCPMTUPSuccess */
+ LINUX_MIB_TCPDELIVERED, /* TCPDelivered */
+ LINUX_MIB_TCPDELIVEREDCE, /* TCPDeliveredCE */
+ LINUX_MIB_TCPACKCOMPRESSED, /* TCPAckCompressed */
+ LINUX_MIB_TCPZEROWINDOWDROP, /* TCPZeroWindowDrop */
+ LINUX_MIB_TCPRCVQDROP, /* TCPRcvQDrop */
+ LINUX_MIB_TCPWQUEUETOOBIG, /* TCPWqueueTooBig */
+ LINUX_MIB_TCPFASTOPENPASSIVEALTKEY, /* TCPFastOpenPassiveAltKey */
+ LINUX_MIB_TCPTIMEOUTREHASH, /* TCPTimeoutRehash */
+ LINUX_MIB_TCPDUPLICATEDATAREHASH, /* TCPDuplicateDataRehash */
+ LINUX_MIB_TCPDSACKRECVSEGS, /* TCPDSACKRecvSegs */
+ LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */
+ LINUX_MIB_TCPMIGRATEREQSUCCESS, /* TCPMigrateReqSuccess */
+ LINUX_MIB_TCPMIGRATEREQFAILURE, /* TCPMigrateReqFailure */
+ LINUX_MIB_TCPPLBREHASH, /* TCPPLBRehash */
+ LINUX_MIB_TCPAOREQUIRED, /* TCPAORequired */
+ LINUX_MIB_TCPAOBAD, /* TCPAOBad */
+ LINUX_MIB_TCPAOKEYNOTFOUND, /* TCPAOKeyNotFound */
+ LINUX_MIB_TCPAOGOOD, /* TCPAOGood */
+ LINUX_MIB_TCPAODROPPEDICMPS, /* TCPAODroppedIcmps */
+ __LINUX_MIB_MAX
+};
+
+/* linux Xfrm mib definitions */
+enum
+{
+ LINUX_MIB_XFRMNUM = 0,
+ LINUX_MIB_XFRMINERROR, /* XfrmInError */
+ LINUX_MIB_XFRMINBUFFERERROR, /* XfrmInBufferError */
+ LINUX_MIB_XFRMINHDRERROR, /* XfrmInHdrError */
+ LINUX_MIB_XFRMINNOSTATES, /* XfrmInNoStates */
+ LINUX_MIB_XFRMINSTATEPROTOERROR, /* XfrmInStateProtoError */
+ LINUX_MIB_XFRMINSTATEMODEERROR, /* XfrmInStateModeError */
+ LINUX_MIB_XFRMINSTATESEQERROR, /* XfrmInStateSeqError */
+ LINUX_MIB_XFRMINSTATEEXPIRED, /* XfrmInStateExpired */
+ LINUX_MIB_XFRMINSTATEMISMATCH, /* XfrmInStateMismatch */
+ LINUX_MIB_XFRMINSTATEINVALID, /* XfrmInStateInvalid */
+ LINUX_MIB_XFRMINTMPLMISMATCH, /* XfrmInTmplMismatch */
+ LINUX_MIB_XFRMINNOPOLS, /* XfrmInNoPols */
+ LINUX_MIB_XFRMINPOLBLOCK, /* XfrmInPolBlock */
+ LINUX_MIB_XFRMINPOLERROR, /* XfrmInPolError */
+ LINUX_MIB_XFRMOUTERROR, /* XfrmOutError */
+ LINUX_MIB_XFRMOUTBUNDLEGENERROR, /* XfrmOutBundleGenError */
+ LINUX_MIB_XFRMOUTBUNDLECHECKERROR, /* XfrmOutBundleCheckError */
+ LINUX_MIB_XFRMOUTNOSTATES, /* XfrmOutNoStates */
+ LINUX_MIB_XFRMOUTSTATEPROTOERROR, /* XfrmOutStateProtoError */
+ LINUX_MIB_XFRMOUTSTATEMODEERROR, /* XfrmOutStateModeError */
+ LINUX_MIB_XFRMOUTSTATESEQERROR, /* XfrmOutStateSeqError */
+ LINUX_MIB_XFRMOUTSTATEEXPIRED, /* XfrmOutStateExpired */
+ LINUX_MIB_XFRMOUTPOLBLOCK, /* XfrmOutPolBlock */
+ LINUX_MIB_XFRMOUTPOLDEAD, /* XfrmOutPolDead */
+ LINUX_MIB_XFRMOUTPOLERROR, /* XfrmOutPolError */
+ LINUX_MIB_XFRMFWDHDRERROR, /* XfrmFwdHdrError*/
+ LINUX_MIB_XFRMOUTSTATEINVALID, /* XfrmOutStateInvalid */
+ LINUX_MIB_XFRMACQUIREERROR, /* XfrmAcquireError */
+ __LINUX_MIB_XFRMMAX
+};
+
+/* linux TLS mib definitions */
+enum
+{
+ LINUX_MIB_TLSNUM = 0,
+ LINUX_MIB_TLSCURRTXSW, /* TlsCurrTxSw */
+ LINUX_MIB_TLSCURRRXSW, /* TlsCurrRxSw */
+ LINUX_MIB_TLSCURRTXDEVICE, /* TlsCurrTxDevice */
+ LINUX_MIB_TLSCURRRXDEVICE, /* TlsCurrRxDevice */
+ LINUX_MIB_TLSTXSW, /* TlsTxSw */
+ LINUX_MIB_TLSRXSW, /* TlsRxSw */
+ LINUX_MIB_TLSTXDEVICE, /* TlsTxDevice */
+ LINUX_MIB_TLSRXDEVICE, /* TlsRxDevice */
+ LINUX_MIB_TLSDECRYPTERROR, /* TlsDecryptError */
+ LINUX_MIB_TLSRXDEVICERESYNC, /* TlsRxDeviceResync */
+ LINUX_MIB_TLSDECRYPTRETRY, /* TlsDecryptRetry */
+ LINUX_MIB_TLSRXNOPADVIOL, /* TlsRxNoPadViolation */
+ __LINUX_MIB_TLSMAX
+};
+
+#endif /* _LINUX_SNMP_H */
diff --git a/include/uapi/linux/sock_diag.h b/include/uapi/linux/sock_diag.h
new file mode 100644
index 0000000..35c0ce6
--- /dev/null
+++ b/include/uapi/linux/sock_diag.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __SOCK_DIAG_H__
+#define __SOCK_DIAG_H__
+
+#include <linux/types.h>
+
+#define SOCK_DIAG_BY_FAMILY 20
+#define SOCK_DESTROY 21
+
+struct sock_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+};
+
+enum {
+ SK_MEMINFO_RMEM_ALLOC,
+ SK_MEMINFO_RCVBUF,
+ SK_MEMINFO_WMEM_ALLOC,
+ SK_MEMINFO_SNDBUF,
+ SK_MEMINFO_FWD_ALLOC,
+ SK_MEMINFO_WMEM_QUEUED,
+ SK_MEMINFO_OPTMEM,
+ SK_MEMINFO_BACKLOG,
+ SK_MEMINFO_DROPS,
+
+ SK_MEMINFO_VARS,
+};
+
+enum sknetlink_groups {
+ SKNLGRP_NONE,
+ SKNLGRP_INET_TCP_DESTROY,
+ SKNLGRP_INET_UDP_DESTROY,
+ SKNLGRP_INET6_TCP_DESTROY,
+ SKNLGRP_INET6_UDP_DESTROY,
+ __SKNLGRP_MAX,
+};
+#define SKNLGRP_MAX (__SKNLGRP_MAX - 1)
+
+enum {
+ SK_DIAG_BPF_STORAGE_REQ_NONE,
+ SK_DIAG_BPF_STORAGE_REQ_MAP_FD,
+ __SK_DIAG_BPF_STORAGE_REQ_MAX,
+};
+
+#define SK_DIAG_BPF_STORAGE_REQ_MAX (__SK_DIAG_BPF_STORAGE_REQ_MAX - 1)
+
+enum {
+ SK_DIAG_BPF_STORAGE_REP_NONE,
+ SK_DIAG_BPF_STORAGE,
+ __SK_DIAG_BPF_STORAGE_REP_MAX,
+};
+
+#define SK_DIAB_BPF_STORAGE_REP_MAX (__SK_DIAG_BPF_STORAGE_REP_MAX - 1)
+
+enum {
+ SK_DIAG_BPF_STORAGE_NONE,
+ SK_DIAG_BPF_STORAGE_PAD,
+ SK_DIAG_BPF_STORAGE_MAP_ID,
+ SK_DIAG_BPF_STORAGE_MAP_VALUE,
+ __SK_DIAG_BPF_STORAGE_MAX,
+};
+
+#define SK_DIAG_BPF_STORAGE_MAX (__SK_DIAG_BPF_STORAGE_MAX - 1)
+
+#endif /* __SOCK_DIAG_H__ */
diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h
new file mode 100644
index 0000000..89c227f
--- /dev/null
+++ b/include/uapi/linux/socket.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_SOCKET_H
+#define _LINUX_SOCKET_H
+
+/*
+ * Desired design of maximum size and alignment (see RFC2553)
+ */
+#define _K_SS_MAXSIZE 128 /* Implementation specific max size */
+
+typedef unsigned short __kernel_sa_family_t;
+
+/*
+ * The definition uses anonymous union and struct in order to control the
+ * default alignment.
+ */
+struct __kernel_sockaddr_storage {
+ union {
+ struct {
+ __kernel_sa_family_t ss_family; /* address family */
+ /* Following field(s) are implementation specific */
+ char __data[_K_SS_MAXSIZE - sizeof(unsigned short)];
+ /* space to achieve desired size, */
+ /* _SS_MAXSIZE value minus size of ss_family */
+ };
+ void *__align; /* implementation specific desired alignment */
+ };
+};
+
+#define SOCK_SNDBUF_LOCK 1
+#define SOCK_RCVBUF_LOCK 2
+
+#define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK)
+
+#define SOCK_TXREHASH_DEFAULT 255
+#define SOCK_TXREHASH_DISABLED 0
+#define SOCK_TXREHASH_ENABLED 1
+
+#endif /* _LINUX_SOCKET_H */
diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h
new file mode 100644
index 0000000..7d1bccb
--- /dev/null
+++ b/include/uapi/linux/sockios.h
@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions of the socket-level I/O control calls.
+ *
+ * Version: @(#)sockios.h 1.0.2 03/09/93
+ *
+ * Authors: Ross Biro
+ * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_SOCKIOS_H
+#define _LINUX_SOCKIOS_H
+
+#include <asm/bitsperlong.h>
+#include <asm/sockios.h>
+
+/* Linux-specific socket ioctls */
+#define SIOCINQ FIONREAD
+#define SIOCOUTQ TIOCOUTQ /* output queue size (not sent + not acked) */
+
+#define SOCK_IOC_TYPE 0x89
+
+/*
+ * the timeval/timespec data structure layout is defined by libc,
+ * so we need to cover both possible versions on 32-bit.
+ */
+/* Get stamp (timeval) */
+#define SIOCGSTAMP_NEW _IOR(SOCK_IOC_TYPE, 0x06, long long[2])
+/* Get stamp (timespec) */
+#define SIOCGSTAMPNS_NEW _IOR(SOCK_IOC_TYPE, 0x07, long long[2])
+
+#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
+/* on 64-bit and x32, avoid the ?: operator */
+#define SIOCGSTAMP SIOCGSTAMP_OLD
+#define SIOCGSTAMPNS SIOCGSTAMPNS_OLD
+#else
+#define SIOCGSTAMP ((sizeof(struct timeval)) == 8 ? \
+ SIOCGSTAMP_OLD : SIOCGSTAMP_NEW)
+#define SIOCGSTAMPNS ((sizeof(struct timespec)) == 8 ? \
+ SIOCGSTAMPNS_OLD : SIOCGSTAMPNS_NEW)
+#endif
+
+/* Routing table calls. */
+#define SIOCADDRT 0x890B /* add routing table entry */
+#define SIOCDELRT 0x890C /* delete routing table entry */
+#define SIOCRTMSG 0x890D /* unused */
+
+/* Socket configuration controls. */
+#define SIOCGIFNAME 0x8910 /* get iface name */
+#define SIOCSIFLINK 0x8911 /* set iface channel */
+#define SIOCGIFCONF 0x8912 /* get iface list */
+#define SIOCGIFFLAGS 0x8913 /* get flags */
+#define SIOCSIFFLAGS 0x8914 /* set flags */
+#define SIOCGIFADDR 0x8915 /* get PA address */
+#define SIOCSIFADDR 0x8916 /* set PA address */
+#define SIOCGIFDSTADDR 0x8917 /* get remote PA address */
+#define SIOCSIFDSTADDR 0x8918 /* set remote PA address */
+#define SIOCGIFBRDADDR 0x8919 /* get broadcast PA address */
+#define SIOCSIFBRDADDR 0x891a /* set broadcast PA address */
+#define SIOCGIFNETMASK 0x891b /* get network PA mask */
+#define SIOCSIFNETMASK 0x891c /* set network PA mask */
+#define SIOCGIFMETRIC 0x891d /* get metric */
+#define SIOCSIFMETRIC 0x891e /* set metric */
+#define SIOCGIFMEM 0x891f /* get memory address (BSD) */
+#define SIOCSIFMEM 0x8920 /* set memory address (BSD) */
+#define SIOCGIFMTU 0x8921 /* get MTU size */
+#define SIOCSIFMTU 0x8922 /* set MTU size */
+#define SIOCSIFNAME 0x8923 /* set interface name */
+#define SIOCSIFHWADDR 0x8924 /* set hardware address */
+#define SIOCGIFENCAP 0x8925 /* get/set encapsulations */
+#define SIOCSIFENCAP 0x8926
+#define SIOCGIFHWADDR 0x8927 /* Get hardware address */
+#define SIOCGIFSLAVE 0x8929 /* Driver slaving support */
+#define SIOCSIFSLAVE 0x8930
+#define SIOCADDMULTI 0x8931 /* Multicast address lists */
+#define SIOCDELMULTI 0x8932
+#define SIOCGIFINDEX 0x8933 /* name -> if_index mapping */
+#define SIOGIFINDEX SIOCGIFINDEX /* misprint compatibility :-) */
+#define SIOCSIFPFLAGS 0x8934 /* set/get extended flags set */
+#define SIOCGIFPFLAGS 0x8935
+#define SIOCDIFADDR 0x8936 /* delete PA address */
+#define SIOCSIFHWBROADCAST 0x8937 /* set hardware broadcast addr */
+#define SIOCGIFCOUNT 0x8938 /* get number of devices */
+
+#define SIOCGIFBR 0x8940 /* Bridging support */
+#define SIOCSIFBR 0x8941 /* Set bridging options */
+
+#define SIOCGIFTXQLEN 0x8942 /* Get the tx queue length */
+#define SIOCSIFTXQLEN 0x8943 /* Set the tx queue length */
+
+/* SIOCGIFDIVERT was: 0x8944 Frame diversion support */
+/* SIOCSIFDIVERT was: 0x8945 Set frame diversion options */
+
+#define SIOCETHTOOL 0x8946 /* Ethtool interface */
+
+#define SIOCGMIIPHY 0x8947 /* Get address of MII PHY in use. */
+#define SIOCGMIIREG 0x8948 /* Read MII PHY register. */
+#define SIOCSMIIREG 0x8949 /* Write MII PHY register. */
+
+#define SIOCWANDEV 0x894A /* get/set netdev parameters */
+
+#define SIOCOUTQNSD 0x894B /* output queue size (not sent only) */
+#define SIOCGSKNS 0x894C /* get socket network namespace */
+
+/* ARP cache control calls. */
+ /* 0x8950 - 0x8952 * obsolete calls, don't re-use */
+#define SIOCDARP 0x8953 /* delete ARP table entry */
+#define SIOCGARP 0x8954 /* get ARP table entry */
+#define SIOCSARP 0x8955 /* set ARP table entry */
+
+/* RARP cache control calls. */
+#define SIOCDRARP 0x8960 /* delete RARP table entry */
+#define SIOCGRARP 0x8961 /* get RARP table entry */
+#define SIOCSRARP 0x8962 /* set RARP table entry */
+
+/* Driver configuration calls */
+
+#define SIOCGIFMAP 0x8970 /* Get device parameters */
+#define SIOCSIFMAP 0x8971 /* Set device parameters */
+
+/* DLCI configuration calls */
+
+#define SIOCADDDLCI 0x8980 /* Create new DLCI device */
+#define SIOCDELDLCI 0x8981 /* Delete DLCI device */
+
+#define SIOCGIFVLAN 0x8982 /* 802.1Q VLAN support */
+#define SIOCSIFVLAN 0x8983 /* Set 802.1Q VLAN options */
+
+/* bonding calls */
+
+#define SIOCBONDENSLAVE 0x8990 /* enslave a device to the bond */
+#define SIOCBONDRELEASE 0x8991 /* release a slave from the bond*/
+#define SIOCBONDSETHWADDR 0x8992 /* set the hw addr of the bond */
+#define SIOCBONDSLAVEINFOQUERY 0x8993 /* rtn info about slave state */
+#define SIOCBONDINFOQUERY 0x8994 /* rtn info about bond state */
+#define SIOCBONDCHANGEACTIVE 0x8995 /* update to a new active slave */
+
+/* bridge calls */
+#define SIOCBRADDBR 0x89a0 /* create new bridge device */
+#define SIOCBRDELBR 0x89a1 /* remove bridge device */
+#define SIOCBRADDIF 0x89a2 /* add interface to bridge */
+#define SIOCBRDELIF 0x89a3 /* remove interface from bridge */
+
+/* hardware time stamping: parameters in linux/net_tstamp.h */
+#define SIOCSHWTSTAMP 0x89b0 /* set and get config */
+#define SIOCGHWTSTAMP 0x89b1 /* get config */
+
+/* Device private ioctl calls */
+
+/*
+ * These 16 ioctls are available to devices via the do_ioctl() device
+ * vector. Each device should include this file and redefine these names
+ * as their own. Because these are device dependent it is a good idea
+ * _NOT_ to issue them to random objects and hope.
+ *
+ * THESE IOCTLS ARE _DEPRECATED_ AND WILL DISAPPEAR IN 2.5.X -DaveM
+ */
+
+#define SIOCDEVPRIVATE 0x89F0 /* to 89FF */
+
+/*
+ * These 16 ioctl calls are protocol private
+ */
+
+#define SIOCPROTOPRIVATE 0x89E0 /* to 89EF */
+#endif /* _LINUX_SOCKIOS_H */
diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
new file mode 100644
index 0000000..bf9749d
--- /dev/null
+++ b/include/uapi/linux/stddef.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_STDDEF_H
+#define _LINUX_STDDEF_H
+
+
+
+#ifndef __always_inline
+#define __always_inline __inline__
+#endif
+
+/**
+ * __struct_group() - Create a mirrored named and anonyomous struct
+ *
+ * @TAG: The tag name for the named sub-struct (usually empty)
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @ATTRS: Any struct attributes (usually empty)
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical layout
+ * and size: one anonymous and one named. The former's members can be used
+ * normally without sub-struct naming, and the latter can be used to
+ * reason about the start, end, and size of the group of struct members.
+ * The named struct can also be explicitly tagged for layer reuse, as well
+ * as both having struct attributes appended.
+ */
+#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
+ union { \
+ struct { MEMBERS } ATTRS; \
+ struct TAG { MEMBERS } ATTRS NAME; \
+ } ATTRS
+
+#ifdef __cplusplus
+/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */
+#define __DECLARE_FLEX_ARRAY(T, member) \
+ T member[0]
+#else
+/**
+ * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
+ *
+ * @TYPE: The type of each flexible array element
+ * @NAME: The name of the flexible array member
+ *
+ * In order to have a flexible array member in a union or alone in a
+ * struct, it needs to be wrapped in an anonymous struct with at least 1
+ * named member, but that member can be empty.
+ */
+#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \
+ struct { \
+ struct { } __empty_ ## NAME; \
+ TYPE NAME[]; \
+ }
+#endif
+
+#ifndef __counted_by
+#define __counted_by(m)
+#endif
+
+#endif /* _LINUX_STDDEF_H */
diff --git a/include/uapi/linux/sysinfo.h b/include/uapi/linux/sysinfo.h
new file mode 100644
index 0000000..435d5c2
--- /dev/null
+++ b/include/uapi/linux/sysinfo.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_SYSINFO_H
+#define _LINUX_SYSINFO_H
+
+#include <linux/types.h>
+
+#define SI_LOAD_SHIFT 16
+struct sysinfo {
+ __kernel_long_t uptime; /* Seconds since boot */
+ __kernel_ulong_t loads[3]; /* 1, 5, and 15 minute load averages */
+ __kernel_ulong_t totalram; /* Total usable main memory size */
+ __kernel_ulong_t freeram; /* Available memory size */
+ __kernel_ulong_t sharedram; /* Amount of shared memory */
+ __kernel_ulong_t bufferram; /* Memory used by buffers */
+ __kernel_ulong_t totalswap; /* Total swap space size */
+ __kernel_ulong_t freeswap; /* swap space still available */
+ __u16 procs; /* Number of current processes */
+ __u16 pad; /* Explicit padding for m68k */
+ __kernel_ulong_t totalhigh; /* Total high memory size */
+ __kernel_ulong_t freehigh; /* Available high memory size */
+ __u32 mem_unit; /* Memory unit size in bytes */
+ char _f[20-2*sizeof(__kernel_ulong_t)-sizeof(__u32)]; /* Padding: libc5 uses this.. */
+};
+
+#endif /* _LINUX_SYSINFO_H */
diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 0000000..fe6c8f8
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+struct tc_act_bpf {
+ tc_gen;
+};
+
+enum {
+ TCA_ACT_BPF_UNSPEC,
+ TCA_ACT_BPF_TM,
+ TCA_ACT_BPF_PARMS,
+ TCA_ACT_BPF_OPS_LEN,
+ TCA_ACT_BPF_OPS,
+ TCA_ACT_BPF_FD,
+ TCA_ACT_BPF_NAME,
+ TCA_ACT_BPF_PAD,
+ TCA_ACT_BPF_TAG,
+ TCA_ACT_BPF_ID,
+ __TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_connmark.h b/include/uapi/linux/tc_act/tc_connmark.h
new file mode 100644
index 0000000..9f8f6f7
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_connmark.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UAPI_TC_CONNMARK_H
+#define __UAPI_TC_CONNMARK_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+struct tc_connmark {
+ tc_gen;
+ __u16 zone;
+};
+
+enum {
+ TCA_CONNMARK_UNSPEC,
+ TCA_CONNMARK_PARMS,
+ TCA_CONNMARK_TM,
+ TCA_CONNMARK_PAD,
+ __TCA_CONNMARK_MAX
+};
+#define TCA_CONNMARK_MAX (__TCA_CONNMARK_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_csum.h b/include/uapi/linux/tc_act/tc_csum.h
new file mode 100644
index 0000000..94b2044
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_csum.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_CSUM_H
+#define __LINUX_TC_CSUM_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+ TCA_CSUM_UNSPEC,
+ TCA_CSUM_PARMS,
+ TCA_CSUM_TM,
+ TCA_CSUM_PAD,
+ __TCA_CSUM_MAX
+};
+#define TCA_CSUM_MAX (__TCA_CSUM_MAX - 1)
+
+enum {
+ TCA_CSUM_UPDATE_FLAG_IPV4HDR = 1,
+ TCA_CSUM_UPDATE_FLAG_ICMP = 2,
+ TCA_CSUM_UPDATE_FLAG_IGMP = 4,
+ TCA_CSUM_UPDATE_FLAG_TCP = 8,
+ TCA_CSUM_UPDATE_FLAG_UDP = 16,
+ TCA_CSUM_UPDATE_FLAG_UDPLITE = 32,
+ TCA_CSUM_UPDATE_FLAG_SCTP = 64,
+};
+
+struct tc_csum {
+ tc_gen;
+
+ __u32 update_flags;
+};
+
+#endif /* __LINUX_TC_CSUM_H */
diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h
new file mode 100644
index 0000000..6c5200f
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_ct.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UAPI_TC_CT_H
+#define __UAPI_TC_CT_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+ TCA_CT_UNSPEC,
+ TCA_CT_PARMS,
+ TCA_CT_TM,
+ TCA_CT_ACTION, /* u16 */
+ TCA_CT_ZONE, /* u16 */
+ TCA_CT_MARK, /* u32 */
+ TCA_CT_MARK_MASK, /* u32 */
+ TCA_CT_LABELS, /* u128 */
+ TCA_CT_LABELS_MASK, /* u128 */
+ TCA_CT_NAT_IPV4_MIN, /* be32 */
+ TCA_CT_NAT_IPV4_MAX, /* be32 */
+ TCA_CT_NAT_IPV6_MIN, /* struct in6_addr */
+ TCA_CT_NAT_IPV6_MAX, /* struct in6_addr */
+ TCA_CT_NAT_PORT_MIN, /* be16 */
+ TCA_CT_NAT_PORT_MAX, /* be16 */
+ TCA_CT_PAD,
+ TCA_CT_HELPER_NAME, /* string */
+ TCA_CT_HELPER_FAMILY, /* u8 */
+ TCA_CT_HELPER_PROTO, /* u8 */
+ __TCA_CT_MAX
+};
+
+#define TCA_CT_MAX (__TCA_CT_MAX - 1)
+
+#define TCA_CT_ACT_COMMIT (1 << 0)
+#define TCA_CT_ACT_FORCE (1 << 1)
+#define TCA_CT_ACT_CLEAR (1 << 2)
+#define TCA_CT_ACT_NAT (1 << 3)
+#define TCA_CT_ACT_NAT_SRC (1 << 4)
+#define TCA_CT_ACT_NAT_DST (1 << 5)
+
+struct tc_ct {
+ tc_gen;
+};
+
+#endif /* __UAPI_TC_CT_H */
diff --git a/include/uapi/linux/tc_act/tc_ctinfo.h b/include/uapi/linux/tc_act/tc_ctinfo.h
new file mode 100644
index 0000000..f5f26d9
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_ctinfo.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UAPI_TC_CTINFO_H
+#define __UAPI_TC_CTINFO_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+struct tc_ctinfo {
+ tc_gen;
+};
+
+enum {
+ TCA_CTINFO_UNSPEC,
+ TCA_CTINFO_PAD,
+ TCA_CTINFO_TM,
+ TCA_CTINFO_ACT,
+ TCA_CTINFO_ZONE,
+ TCA_CTINFO_PARMS_DSCP_MASK,
+ TCA_CTINFO_PARMS_DSCP_STATEMASK,
+ TCA_CTINFO_PARMS_CPMARK_MASK,
+ TCA_CTINFO_STATS_DSCP_SET,
+ TCA_CTINFO_STATS_DSCP_ERROR,
+ TCA_CTINFO_STATS_CPMARK_SET,
+ __TCA_CTINFO_MAX
+};
+
+#define TCA_CTINFO_MAX (__TCA_CTINFO_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_defact.h b/include/uapi/linux/tc_act/tc_defact.h
new file mode 100644
index 0000000..e3ecd8b
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_defact.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_DEF_H
+#define __LINUX_TC_DEF_H
+
+#include <linux/pkt_cls.h>
+
+struct tc_defact {
+ tc_gen;
+};
+
+enum {
+ TCA_DEF_UNSPEC,
+ TCA_DEF_TM,
+ TCA_DEF_PARMS,
+ TCA_DEF_DATA,
+ TCA_DEF_PAD,
+ __TCA_DEF_MAX
+};
+#define TCA_DEF_MAX (__TCA_DEF_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_gact.h b/include/uapi/linux/tc_act/tc_gact.h
new file mode 100644
index 0000000..37e5392
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_gact.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_GACT_H
+#define __LINUX_TC_GACT_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+struct tc_gact {
+ tc_gen;
+
+};
+
+struct tc_gact_p {
+#define PGACT_NONE 0
+#define PGACT_NETRAND 1
+#define PGACT_DETERM 2
+#define MAX_RAND (PGACT_DETERM + 1 )
+ __u16 ptype;
+ __u16 pval;
+ int paction;
+};
+
+enum {
+ TCA_GACT_UNSPEC,
+ TCA_GACT_TM,
+ TCA_GACT_PARMS,
+ TCA_GACT_PROB,
+ TCA_GACT_PAD,
+ __TCA_GACT_MAX
+};
+#define TCA_GACT_MAX (__TCA_GACT_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_gate.h b/include/uapi/linux/tc_act/tc_gate.h
new file mode 100644
index 0000000..f214b3a
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_gate.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/* Copyright 2020 NXP */
+
+#ifndef __LINUX_TC_GATE_H
+#define __LINUX_TC_GATE_H
+
+#include <linux/pkt_cls.h>
+
+struct tc_gate {
+ tc_gen;
+};
+
+enum {
+ TCA_GATE_ENTRY_UNSPEC,
+ TCA_GATE_ENTRY_INDEX,
+ TCA_GATE_ENTRY_GATE,
+ TCA_GATE_ENTRY_INTERVAL,
+ TCA_GATE_ENTRY_IPV,
+ TCA_GATE_ENTRY_MAX_OCTETS,
+ __TCA_GATE_ENTRY_MAX,
+};
+#define TCA_GATE_ENTRY_MAX (__TCA_GATE_ENTRY_MAX - 1)
+
+enum {
+ TCA_GATE_ONE_ENTRY_UNSPEC,
+ TCA_GATE_ONE_ENTRY,
+ __TCA_GATE_ONE_ENTRY_MAX,
+};
+#define TCA_GATE_ONE_ENTRY_MAX (__TCA_GATE_ONE_ENTRY_MAX - 1)
+
+enum {
+ TCA_GATE_UNSPEC,
+ TCA_GATE_TM,
+ TCA_GATE_PARMS,
+ TCA_GATE_PAD,
+ TCA_GATE_PRIORITY,
+ TCA_GATE_ENTRY_LIST,
+ TCA_GATE_BASE_TIME,
+ TCA_GATE_CYCLE_TIME,
+ TCA_GATE_CYCLE_TIME_EXT,
+ TCA_GATE_FLAGS,
+ TCA_GATE_CLOCKID,
+ __TCA_GATE_MAX,
+};
+#define TCA_GATE_MAX (__TCA_GATE_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h
new file mode 100644
index 0000000..8c401f1
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_ife.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UAPI_TC_IFE_H
+#define __UAPI_TC_IFE_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+#include <linux/ife.h>
+
+/* Flag bits for now just encoding/decoding; mutually exclusive */
+#define IFE_ENCODE 1
+#define IFE_DECODE 0
+
+struct tc_ife {
+ tc_gen;
+ __u16 flags;
+};
+
+/*XXX: We need to encode the total number of bytes consumed */
+enum {
+ TCA_IFE_UNSPEC,
+ TCA_IFE_PARMS,
+ TCA_IFE_TM,
+ TCA_IFE_DMAC,
+ TCA_IFE_SMAC,
+ TCA_IFE_TYPE,
+ TCA_IFE_METALST,
+ TCA_IFE_PAD,
+ __TCA_IFE_MAX
+};
+#define TCA_IFE_MAX (__TCA_IFE_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h
new file mode 100644
index 0000000..c61e76f
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_mirred.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_MIR_H
+#define __LINUX_TC_MIR_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TCA_EGRESS_REDIR 1 /* packet redirect to EGRESS*/
+#define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */
+#define TCA_INGRESS_REDIR 3 /* packet redirect to INGRESS*/
+#define TCA_INGRESS_MIRROR 4 /* mirror packet to INGRESS */
+
+struct tc_mirred {
+ tc_gen;
+ int eaction; /* one of IN/EGRESS_MIRROR/REDIR */
+ __u32 ifindex; /* ifindex of egress port */
+};
+
+enum {
+ TCA_MIRRED_UNSPEC,
+ TCA_MIRRED_TM,
+ TCA_MIRRED_PARMS,
+ TCA_MIRRED_PAD,
+ TCA_MIRRED_BLOCKID,
+ __TCA_MIRRED_MAX
+};
+#define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_mpls.h b/include/uapi/linux/tc_act/tc_mpls.h
new file mode 100644
index 0000000..9e4e8f5
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_mpls.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#ifndef __LINUX_TC_MPLS_H
+#define __LINUX_TC_MPLS_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_MPLS_ACT_POP 1
+#define TCA_MPLS_ACT_PUSH 2
+#define TCA_MPLS_ACT_MODIFY 3
+#define TCA_MPLS_ACT_DEC_TTL 4
+#define TCA_MPLS_ACT_MAC_PUSH 5
+
+struct tc_mpls {
+ tc_gen; /* generic TC action fields. */
+ int m_action; /* action of type TCA_MPLS_ACT_*. */
+};
+
+enum {
+ TCA_MPLS_UNSPEC,
+ TCA_MPLS_TM, /* struct tcf_t; time values associated with action. */
+ TCA_MPLS_PARMS, /* struct tc_mpls; action type and general TC fields. */
+ TCA_MPLS_PAD,
+ TCA_MPLS_PROTO, /* be16; eth_type of pushed or next (for pop) header. */
+ TCA_MPLS_LABEL, /* u32; MPLS label. Lower 20 bits are used. */
+ TCA_MPLS_TC, /* u8; MPLS TC field. Lower 3 bits are used. */
+ TCA_MPLS_TTL, /* u8; MPLS TTL field. Must not be 0. */
+ TCA_MPLS_BOS, /* u8; MPLS BOS field. Either 1 or 0. */
+ __TCA_MPLS_MAX,
+};
+#define TCA_MPLS_MAX (__TCA_MPLS_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_nat.h b/include/uapi/linux/tc_act/tc_nat.h
new file mode 100644
index 0000000..21399c2
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_nat.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_NAT_H
+#define __LINUX_TC_NAT_H
+
+#include <linux/pkt_cls.h>
+#include <linux/types.h>
+
+enum {
+ TCA_NAT_UNSPEC,
+ TCA_NAT_PARMS,
+ TCA_NAT_TM,
+ TCA_NAT_PAD,
+ __TCA_NAT_MAX
+};
+#define TCA_NAT_MAX (__TCA_NAT_MAX - 1)
+
+#define TCA_NAT_FLAG_EGRESS 1
+
+struct tc_nat {
+ tc_gen;
+ __be32 old_addr;
+ __be32 new_addr;
+ __be32 mask;
+ __u32 flags;
+};
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h
new file mode 100644
index 0000000..f3e61b0
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_pedit.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_PED_H
+#define __LINUX_TC_PED_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+ TCA_PEDIT_UNSPEC,
+ TCA_PEDIT_TM,
+ TCA_PEDIT_PARMS,
+ TCA_PEDIT_PAD,
+ TCA_PEDIT_PARMS_EX,
+ TCA_PEDIT_KEYS_EX,
+ TCA_PEDIT_KEY_EX,
+ __TCA_PEDIT_MAX
+};
+
+#define TCA_PEDIT_MAX (__TCA_PEDIT_MAX - 1)
+
+enum {
+ TCA_PEDIT_KEY_EX_HTYPE = 1,
+ TCA_PEDIT_KEY_EX_CMD = 2,
+ __TCA_PEDIT_KEY_EX_MAX
+};
+
+#define TCA_PEDIT_KEY_EX_MAX (__TCA_PEDIT_KEY_EX_MAX - 1)
+
+ /* TCA_PEDIT_KEY_EX_HDR_TYPE_NETWROK is a special case for legacy users. It
+ * means no specific header type - offset is relative to the network layer
+ */
+enum pedit_header_type {
+ TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK = 0,
+ TCA_PEDIT_KEY_EX_HDR_TYPE_ETH = 1,
+ TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 = 2,
+ TCA_PEDIT_KEY_EX_HDR_TYPE_IP6 = 3,
+ TCA_PEDIT_KEY_EX_HDR_TYPE_TCP = 4,
+ TCA_PEDIT_KEY_EX_HDR_TYPE_UDP = 5,
+ __PEDIT_HDR_TYPE_MAX,
+};
+
+#define TCA_PEDIT_HDR_TYPE_MAX (__PEDIT_HDR_TYPE_MAX - 1)
+
+enum pedit_cmd {
+ TCA_PEDIT_KEY_EX_CMD_SET = 0,
+ TCA_PEDIT_KEY_EX_CMD_ADD = 1,
+ __PEDIT_CMD_MAX,
+};
+
+#define TCA_PEDIT_CMD_MAX (__PEDIT_CMD_MAX - 1)
+
+struct tc_pedit_key {
+ __u32 mask; /* AND */
+ __u32 val; /*XOR */
+ __u32 off; /*offset */
+ __u32 at;
+ __u32 offmask;
+ __u32 shift;
+};
+
+struct tc_pedit_sel {
+ tc_gen;
+ unsigned char nkeys;
+ unsigned char flags;
+ struct tc_pedit_key keys[0];
+};
+
+#define tc_pedit tc_pedit_sel
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_sample.h b/include/uapi/linux/tc_act/tc_sample.h
new file mode 100644
index 0000000..fee1bcc
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_sample.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_SAMPLE_H
+#define __LINUX_TC_SAMPLE_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+#include <linux/if_ether.h>
+
+struct tc_sample {
+ tc_gen;
+};
+
+enum {
+ TCA_SAMPLE_UNSPEC,
+ TCA_SAMPLE_TM,
+ TCA_SAMPLE_PARMS,
+ TCA_SAMPLE_RATE,
+ TCA_SAMPLE_TRUNC_SIZE,
+ TCA_SAMPLE_PSAMPLE_GROUP,
+ TCA_SAMPLE_PAD,
+ __TCA_SAMPLE_MAX
+};
+#define TCA_SAMPLE_MAX (__TCA_SAMPLE_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h
new file mode 100644
index 0000000..6403251
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_skbedit.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2008, Intel Corporation.
+ *
+ * Author: Alexander Duyck <alexander.h.duyck@intel.com>
+ */
+
+#ifndef __LINUX_TC_SKBEDIT_H
+#define __LINUX_TC_SKBEDIT_H
+
+#include <linux/pkt_cls.h>
+
+#define SKBEDIT_F_PRIORITY 0x1
+#define SKBEDIT_F_QUEUE_MAPPING 0x2
+#define SKBEDIT_F_MARK 0x4
+#define SKBEDIT_F_PTYPE 0x8
+#define SKBEDIT_F_MASK 0x10
+#define SKBEDIT_F_INHERITDSFIELD 0x20
+#define SKBEDIT_F_TXQ_SKBHASH 0x40
+
+struct tc_skbedit {
+ tc_gen;
+};
+
+enum {
+ TCA_SKBEDIT_UNSPEC,
+ TCA_SKBEDIT_TM,
+ TCA_SKBEDIT_PARMS,
+ TCA_SKBEDIT_PRIORITY,
+ TCA_SKBEDIT_QUEUE_MAPPING,
+ TCA_SKBEDIT_MARK,
+ TCA_SKBEDIT_PAD,
+ TCA_SKBEDIT_PTYPE,
+ TCA_SKBEDIT_MASK,
+ TCA_SKBEDIT_FLAGS,
+ TCA_SKBEDIT_QUEUE_MAPPING_MAX,
+ __TCA_SKBEDIT_MAX
+};
+#define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_skbmod.h b/include/uapi/linux/tc_act/tc_skbmod.h
new file mode 100644
index 0000000..ac62c9a
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_skbmod.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2016, Jamal Hadi Salim
+ */
+
+#ifndef __LINUX_TC_SKBMOD_H
+#define __LINUX_TC_SKBMOD_H
+
+#include <linux/pkt_cls.h>
+
+#define SKBMOD_F_DMAC 0x1
+#define SKBMOD_F_SMAC 0x2
+#define SKBMOD_F_ETYPE 0x4
+#define SKBMOD_F_SWAPMAC 0x8
+#define SKBMOD_F_ECN 0x10
+
+struct tc_skbmod {
+ tc_gen;
+ __u64 flags;
+};
+
+enum {
+ TCA_SKBMOD_UNSPEC,
+ TCA_SKBMOD_TM,
+ TCA_SKBMOD_PARMS,
+ TCA_SKBMOD_DMAC,
+ TCA_SKBMOD_SMAC,
+ TCA_SKBMOD_ETYPE,
+ TCA_SKBMOD_PAD,
+ __TCA_SKBMOD_MAX
+};
+#define TCA_SKBMOD_MAX (__TCA_SKBMOD_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
new file mode 100644
index 0000000..37c6f61
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2016, Amir Vadai <amir@vadai.me>
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ */
+
+#ifndef __LINUX_TC_TUNNEL_KEY_H
+#define __LINUX_TC_TUNNEL_KEY_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_TUNNEL_KEY_ACT_SET 1
+#define TCA_TUNNEL_KEY_ACT_RELEASE 2
+
+struct tc_tunnel_key {
+ tc_gen;
+ int t_action;
+};
+
+enum {
+ TCA_TUNNEL_KEY_UNSPEC,
+ TCA_TUNNEL_KEY_TM,
+ TCA_TUNNEL_KEY_PARMS,
+ TCA_TUNNEL_KEY_ENC_IPV4_SRC, /* be32 */
+ TCA_TUNNEL_KEY_ENC_IPV4_DST, /* be32 */
+ TCA_TUNNEL_KEY_ENC_IPV6_SRC, /* struct in6_addr */
+ TCA_TUNNEL_KEY_ENC_IPV6_DST, /* struct in6_addr */
+ TCA_TUNNEL_KEY_ENC_KEY_ID, /* be64 */
+ TCA_TUNNEL_KEY_PAD,
+ TCA_TUNNEL_KEY_ENC_DST_PORT, /* be16 */
+ TCA_TUNNEL_KEY_NO_CSUM, /* u8 */
+ TCA_TUNNEL_KEY_ENC_OPTS, /* Nested TCA_TUNNEL_KEY_ENC_OPTS_
+ * attributes
+ */
+ TCA_TUNNEL_KEY_ENC_TOS, /* u8 */
+ TCA_TUNNEL_KEY_ENC_TTL, /* u8 */
+ TCA_TUNNEL_KEY_NO_FRAG, /* flag */
+ __TCA_TUNNEL_KEY_MAX,
+};
+
+#define TCA_TUNNEL_KEY_MAX (__TCA_TUNNEL_KEY_MAX - 1)
+
+enum {
+ TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC,
+ TCA_TUNNEL_KEY_ENC_OPTS_GENEVE, /* Nested
+ * TCA_TUNNEL_KEY_ENC_OPTS_
+ * attributes
+ */
+ TCA_TUNNEL_KEY_ENC_OPTS_VXLAN, /* Nested
+ * TCA_TUNNEL_KEY_ENC_OPTS_
+ * attributes
+ */
+ TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN, /* Nested
+ * TCA_TUNNEL_KEY_ENC_OPTS_
+ * attributes
+ */
+ __TCA_TUNNEL_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPTS_MAX (__TCA_TUNNEL_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+ TCA_TUNNEL_KEY_ENC_OPT_GENEVE_UNSPEC,
+ TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, /* be16 */
+ TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */
+ TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */
+
+ __TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX \
+ (__TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+ TCA_TUNNEL_KEY_ENC_OPT_VXLAN_UNSPEC,
+ TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP, /* u32 */
+ __TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX \
+ (__TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX - 1)
+
+enum {
+ TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_UNSPEC,
+ TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER, /* u8 */
+ TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX, /* be32 */
+ TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR, /* u8 */
+ TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID, /* u8 */
+ __TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX \
+ (__TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h
new file mode 100644
index 0000000..3e1f8e5
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_vlan.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ */
+
+#ifndef __LINUX_TC_VLAN_H
+#define __LINUX_TC_VLAN_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_VLAN_ACT_POP 1
+#define TCA_VLAN_ACT_PUSH 2
+#define TCA_VLAN_ACT_MODIFY 3
+#define TCA_VLAN_ACT_POP_ETH 4
+#define TCA_VLAN_ACT_PUSH_ETH 5
+
+struct tc_vlan {
+ tc_gen;
+ int v_action;
+};
+
+enum {
+ TCA_VLAN_UNSPEC,
+ TCA_VLAN_TM,
+ TCA_VLAN_PARMS,
+ TCA_VLAN_PUSH_VLAN_ID,
+ TCA_VLAN_PUSH_VLAN_PROTOCOL,
+ TCA_VLAN_PAD,
+ TCA_VLAN_PUSH_VLAN_PRIORITY,
+ TCA_VLAN_PUSH_ETH_DST,
+ TCA_VLAN_PUSH_ETH_SRC,
+ __TCA_VLAN_MAX,
+};
+#define TCA_VLAN_MAX (__TCA_VLAN_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_ematch/tc_em_cmp.h b/include/uapi/linux/tc_ematch/tc_em_cmp.h
new file mode 100644
index 0000000..2549d9d
--- /dev/null
+++ b/include/uapi/linux/tc_ematch/tc_em_cmp.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_EM_CMP_H
+#define __LINUX_TC_EM_CMP_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+struct tcf_em_cmp {
+ __u32 val;
+ __u32 mask;
+ __u16 off;
+ __u8 align:4;
+ __u8 flags:4;
+ __u8 layer:4;
+ __u8 opnd:4;
+};
+
+enum {
+ TCF_EM_ALIGN_U8 = 1,
+ TCF_EM_ALIGN_U16 = 2,
+ TCF_EM_ALIGN_U32 = 4
+};
+
+#define TCF_EM_CMP_TRANS 1
+
+#endif
diff --git a/include/uapi/linux/tc_ematch/tc_em_ipt.h b/include/uapi/linux/tc_ematch/tc_em_ipt.h
new file mode 100644
index 0000000..49a6553
--- /dev/null
+++ b/include/uapi/linux/tc_ematch/tc_em_ipt.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_EM_IPT_H
+#define __LINUX_TC_EM_IPT_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+ TCA_EM_IPT_UNSPEC,
+ TCA_EM_IPT_HOOK,
+ TCA_EM_IPT_MATCH_NAME,
+ TCA_EM_IPT_MATCH_REVISION,
+ TCA_EM_IPT_NFPROTO,
+ TCA_EM_IPT_MATCH_DATA,
+ __TCA_EM_IPT_MAX
+};
+
+#define TCA_EM_IPT_MAX (__TCA_EM_IPT_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tc_ematch/tc_em_meta.h b/include/uapi/linux/tc_ematch/tc_em_meta.h
new file mode 100644
index 0000000..cf30b5b
--- /dev/null
+++ b/include/uapi/linux/tc_ematch/tc_em_meta.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_EM_META_H
+#define __LINUX_TC_EM_META_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+enum {
+ TCA_EM_META_UNSPEC,
+ TCA_EM_META_HDR,
+ TCA_EM_META_LVALUE,
+ TCA_EM_META_RVALUE,
+ __TCA_EM_META_MAX
+};
+#define TCA_EM_META_MAX (__TCA_EM_META_MAX - 1)
+
+struct tcf_meta_val {
+ __u16 kind;
+ __u8 shift;
+ __u8 op;
+};
+
+#define TCF_META_TYPE_MASK (0xf << 12)
+#define TCF_META_TYPE(kind) (((kind) & TCF_META_TYPE_MASK) >> 12)
+#define TCF_META_ID_MASK 0x7ff
+#define TCF_META_ID(kind) ((kind) & TCF_META_ID_MASK)
+
+enum {
+ TCF_META_TYPE_VAR,
+ TCF_META_TYPE_INT,
+ __TCF_META_TYPE_MAX
+};
+#define TCF_META_TYPE_MAX (__TCF_META_TYPE_MAX - 1)
+
+enum {
+ TCF_META_ID_VALUE,
+ TCF_META_ID_RANDOM,
+ TCF_META_ID_LOADAVG_0,
+ TCF_META_ID_LOADAVG_1,
+ TCF_META_ID_LOADAVG_2,
+ TCF_META_ID_DEV,
+ TCF_META_ID_PRIORITY,
+ TCF_META_ID_PROTOCOL,
+ TCF_META_ID_PKTTYPE,
+ TCF_META_ID_PKTLEN,
+ TCF_META_ID_DATALEN,
+ TCF_META_ID_MACLEN,
+ TCF_META_ID_NFMARK,
+ TCF_META_ID_TCINDEX,
+ TCF_META_ID_RTCLASSID,
+ TCF_META_ID_RTIIF,
+ TCF_META_ID_SK_FAMILY,
+ TCF_META_ID_SK_STATE,
+ TCF_META_ID_SK_REUSE,
+ TCF_META_ID_SK_BOUND_IF,
+ TCF_META_ID_SK_REFCNT,
+ TCF_META_ID_SK_SHUTDOWN,
+ TCF_META_ID_SK_PROTO,
+ TCF_META_ID_SK_TYPE,
+ TCF_META_ID_SK_RCVBUF,
+ TCF_META_ID_SK_RMEM_ALLOC,
+ TCF_META_ID_SK_WMEM_ALLOC,
+ TCF_META_ID_SK_OMEM_ALLOC,
+ TCF_META_ID_SK_WMEM_QUEUED,
+ TCF_META_ID_SK_RCV_QLEN,
+ TCF_META_ID_SK_SND_QLEN,
+ TCF_META_ID_SK_ERR_QLEN,
+ TCF_META_ID_SK_FORWARD_ALLOCS,
+ TCF_META_ID_SK_SNDBUF,
+ TCF_META_ID_SK_ALLOCS,
+ __TCF_META_ID_SK_ROUTE_CAPS, /* unimplemented but in ABI already */
+ TCF_META_ID_SK_HASH,
+ TCF_META_ID_SK_LINGERTIME,
+ TCF_META_ID_SK_ACK_BACKLOG,
+ TCF_META_ID_SK_MAX_ACK_BACKLOG,
+ TCF_META_ID_SK_PRIO,
+ TCF_META_ID_SK_RCVLOWAT,
+ TCF_META_ID_SK_RCVTIMEO,
+ TCF_META_ID_SK_SNDTIMEO,
+ TCF_META_ID_SK_SENDMSG_OFF,
+ TCF_META_ID_SK_WRITE_PENDING,
+ TCF_META_ID_VLAN_TAG,
+ TCF_META_ID_RXHASH,
+ __TCF_META_ID_MAX
+};
+#define TCF_META_ID_MAX (__TCF_META_ID_MAX - 1)
+
+struct tcf_meta_hdr {
+ struct tcf_meta_val left;
+ struct tcf_meta_val right;
+};
+
+#endif
diff --git a/include/uapi/linux/tc_ematch/tc_em_nbyte.h b/include/uapi/linux/tc_ematch/tc_em_nbyte.h
new file mode 100644
index 0000000..c76333f
--- /dev/null
+++ b/include/uapi/linux/tc_ematch/tc_em_nbyte.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_TC_EM_NBYTE_H
+#define __LINUX_TC_EM_NBYTE_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+struct tcf_em_nbyte {
+ __u16 off;
+ __u16 len:12;
+ __u8 layer:4;
+};
+
+#endif
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
new file mode 100644
index 0000000..a1b9fb3
--- /dev/null
+++ b/include/uapi/linux/tcp.h
@@ -0,0 +1,486 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions for the TCP protocol.
+ *
+ * Version: @(#)tcp.h 1.0.2 04/28/93
+ *
+ * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_TCP_H
+#define _LINUX_TCP_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <linux/socket.h>
+
+struct tcphdr {
+ __be16 source;
+ __be16 dest;
+ __be32 seq;
+ __be32 ack_seq;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u16 res1:4,
+ doff:4,
+ fin:1,
+ syn:1,
+ rst:1,
+ psh:1,
+ ack:1,
+ urg:1,
+ ece:1,
+ cwr:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u16 doff:4,
+ res1:4,
+ cwr:1,
+ ece:1,
+ urg:1,
+ ack:1,
+ psh:1,
+ rst:1,
+ syn:1,
+ fin:1;
+#else
+#error "Adjust your <asm/byteorder.h> defines"
+#endif
+ __be16 window;
+ __sum16 check;
+ __be16 urg_ptr;
+};
+
+/*
+ * The union cast uses a gcc extension to avoid aliasing problems
+ * (union is compatible to any of its members)
+ * This means this part of the code is -fstrict-aliasing safe now.
+ */
+union tcp_word_hdr {
+ struct tcphdr hdr;
+ __be32 words[5];
+};
+
+#define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3])
+
+enum {
+ TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000),
+ TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000),
+ TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000),
+ TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000),
+ TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000),
+ TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000),
+ TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000),
+ TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000),
+ TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000),
+ TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000)
+};
+
+/*
+ * TCP general constants
+ */
+#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */
+#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */
+
+/* TCP socket options */
+#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */
+#define TCP_MAXSEG 2 /* Limit MSS */
+#define TCP_CORK 3 /* Never send partially complete segments */
+#define TCP_KEEPIDLE 4 /* Start keeplives after this period */
+#define TCP_KEEPINTVL 5 /* Interval between keepalives */
+#define TCP_KEEPCNT 6 /* Number of keepalives before death */
+#define TCP_SYNCNT 7 /* Number of SYN retransmits */
+#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */
+#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */
+#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */
+#define TCP_INFO 11 /* Information about this connection. */
+#define TCP_QUICKACK 12 /* Block/reenable quick acks */
+#define TCP_CONGESTION 13 /* Congestion control algorithm */
+#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */
+#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/
+#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */
+#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */
+#define TCP_REPAIR 19 /* TCP sock is under repair right now */
+#define TCP_REPAIR_QUEUE 20
+#define TCP_QUEUE_SEQ 21
+#define TCP_REPAIR_OPTIONS 22
+#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */
+#define TCP_TIMESTAMP 24
+#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */
+#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */
+#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */
+#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */
+#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */
+#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */
+#define TCP_ULP 31 /* Attach a ULP to a TCP connection */
+#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */
+#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */
+#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */
+#define TCP_ZEROCOPY_RECEIVE 35
+#define TCP_INQ 36 /* Notify bytes available to read as a cmsg on read */
+
+#define TCP_CM_INQ TCP_INQ
+
+#define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */
+
+#define TCP_AO_ADD_KEY 38 /* Add/Set MKT */
+#define TCP_AO_DEL_KEY 39 /* Delete MKT */
+#define TCP_AO_INFO 40 /* Set/list TCP-AO per-socket options */
+#define TCP_AO_GET_KEYS 41 /* List MKT(s) */
+#define TCP_AO_REPAIR 42 /* Get/Set SNEs and ISNs */
+
+#define TCP_REPAIR_ON 1
+#define TCP_REPAIR_OFF 0
+#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */
+
+struct tcp_repair_opt {
+ __u32 opt_code;
+ __u32 opt_val;
+};
+
+struct tcp_repair_window {
+ __u32 snd_wl1;
+ __u32 snd_wnd;
+ __u32 max_window;
+
+ __u32 rcv_wnd;
+ __u32 rcv_wup;
+};
+
+enum {
+ TCP_NO_QUEUE,
+ TCP_RECV_QUEUE,
+ TCP_SEND_QUEUE,
+ TCP_QUEUES_NR,
+};
+
+/* why fastopen failed from client perspective */
+enum tcp_fastopen_client_fail {
+ TFO_STATUS_UNSPEC, /* catch-all */
+ TFO_COOKIE_UNAVAILABLE, /* if not in TFO_CLIENT_NO_COOKIE mode */
+ TFO_DATA_NOT_ACKED, /* SYN-ACK did not ack SYN data */
+ TFO_SYN_RETRANSMITTED, /* SYN-ACK did not ack SYN data after timeout */
+};
+
+/* for TCP_INFO socket option */
+#define TCPI_OPT_TIMESTAMPS 1
+#define TCPI_OPT_SACK 2
+#define TCPI_OPT_WSCALE 4
+#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */
+#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */
+#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */
+#define TCPI_OPT_USEC_TS 64 /* usec timestamps */
+
+/*
+ * Sender's congestion state indicating normal or abnormal situations
+ * in the last round of packets sent. The state is driven by the ACK
+ * information and timer events.
+ */
+enum tcp_ca_state {
+ /*
+ * Nothing bad has been observed recently.
+ * No apparent reordering, packet loss, or ECN marks.
+ */
+ TCP_CA_Open = 0,
+#define TCPF_CA_Open (1<<TCP_CA_Open)
+ /*
+ * The sender enters disordered state when it has received DUPACKs or
+ * SACKs in the last round of packets sent. This could be due to packet
+ * loss or reordering but needs further information to confirm packets
+ * have been lost.
+ */
+ TCP_CA_Disorder = 1,
+#define TCPF_CA_Disorder (1<<TCP_CA_Disorder)
+ /*
+ * The sender enters Congestion Window Reduction (CWR) state when it
+ * has received ACKs with ECN-ECE marks, or has experienced congestion
+ * or packet discard on the sender host (e.g. qdisc).
+ */
+ TCP_CA_CWR = 2,
+#define TCPF_CA_CWR (1<<TCP_CA_CWR)
+ /*
+ * The sender is in fast recovery and retransmitting lost packets,
+ * typically triggered by ACK events.
+ */
+ TCP_CA_Recovery = 3,
+#define TCPF_CA_Recovery (1<<TCP_CA_Recovery)
+ /*
+ * The sender is in loss recovery triggered by retransmission timeout.
+ */
+ TCP_CA_Loss = 4
+#define TCPF_CA_Loss (1<<TCP_CA_Loss)
+};
+
+struct tcp_info {
+ __u8 tcpi_state;
+ __u8 tcpi_ca_state;
+ __u8 tcpi_retransmits;
+ __u8 tcpi_probes;
+ __u8 tcpi_backoff;
+ __u8 tcpi_options;
+ __u8 tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;
+ __u8 tcpi_delivery_rate_app_limited:1, tcpi_fastopen_client_fail:2;
+
+ __u32 tcpi_rto;
+ __u32 tcpi_ato;
+ __u32 tcpi_snd_mss;
+ __u32 tcpi_rcv_mss;
+
+ __u32 tcpi_unacked;
+ __u32 tcpi_sacked;
+ __u32 tcpi_lost;
+ __u32 tcpi_retrans;
+ __u32 tcpi_fackets;
+
+ /* Times. */
+ __u32 tcpi_last_data_sent;
+ __u32 tcpi_last_ack_sent; /* Not remembered, sorry. */
+ __u32 tcpi_last_data_recv;
+ __u32 tcpi_last_ack_recv;
+
+ /* Metrics. */
+ __u32 tcpi_pmtu;
+ __u32 tcpi_rcv_ssthresh;
+ __u32 tcpi_rtt;
+ __u32 tcpi_rttvar;
+ __u32 tcpi_snd_ssthresh;
+ __u32 tcpi_snd_cwnd;
+ __u32 tcpi_advmss;
+ __u32 tcpi_reordering;
+
+ __u32 tcpi_rcv_rtt;
+ __u32 tcpi_rcv_space;
+
+ __u32 tcpi_total_retrans;
+
+ __u64 tcpi_pacing_rate;
+ __u64 tcpi_max_pacing_rate;
+ __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */
+ __u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
+ __u32 tcpi_segs_out; /* RFC4898 tcpEStatsPerfSegsOut */
+ __u32 tcpi_segs_in; /* RFC4898 tcpEStatsPerfSegsIn */
+
+ __u32 tcpi_notsent_bytes;
+ __u32 tcpi_min_rtt;
+ __u32 tcpi_data_segs_in; /* RFC4898 tcpEStatsDataSegsIn */
+ __u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */
+
+ __u64 tcpi_delivery_rate;
+
+ __u64 tcpi_busy_time; /* Time (usec) busy sending data */
+ __u64 tcpi_rwnd_limited; /* Time (usec) limited by receive window */
+ __u64 tcpi_sndbuf_limited; /* Time (usec) limited by send buffer */
+
+ __u32 tcpi_delivered;
+ __u32 tcpi_delivered_ce;
+
+ __u64 tcpi_bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
+ __u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */
+ __u32 tcpi_dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups */
+ __u32 tcpi_reord_seen; /* reordering events seen */
+
+ __u32 tcpi_rcv_ooopack; /* Out-of-order packets received */
+
+ __u32 tcpi_snd_wnd; /* peer's advertised receive window after
+ * scaling (bytes)
+ */
+ __u32 tcpi_rcv_wnd; /* local advertised receive window after
+ * scaling (bytes)
+ */
+
+ __u32 tcpi_rehash; /* PLB or timeout triggered rehash attempts */
+
+ __u16 tcpi_total_rto; /* Total number of RTO timeouts, including
+ * SYN/SYN-ACK and recurring timeouts.
+ */
+ __u16 tcpi_total_rto_recoveries; /* Total number of RTO
+ * recoveries, including any
+ * unfinished recovery.
+ */
+ __u32 tcpi_total_rto_time; /* Total time spent in RTO recoveries
+ * in milliseconds, including any
+ * unfinished recovery.
+ */
+};
+
+/* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
+enum {
+ TCP_NLA_PAD,
+ TCP_NLA_BUSY, /* Time (usec) busy sending data */
+ TCP_NLA_RWND_LIMITED, /* Time (usec) limited by receive window */
+ TCP_NLA_SNDBUF_LIMITED, /* Time (usec) limited by send buffer */
+ TCP_NLA_DATA_SEGS_OUT, /* Data pkts sent including retransmission */
+ TCP_NLA_TOTAL_RETRANS, /* Data pkts retransmitted */
+ TCP_NLA_PACING_RATE, /* Pacing rate in bytes per second */
+ TCP_NLA_DELIVERY_RATE, /* Delivery rate in bytes per second */
+ TCP_NLA_SND_CWND, /* Sending congestion window */
+ TCP_NLA_REORDERING, /* Reordering metric */
+ TCP_NLA_MIN_RTT, /* minimum RTT */
+ TCP_NLA_RECUR_RETRANS, /* Recurring retransmits for the current pkt */
+ TCP_NLA_DELIVERY_RATE_APP_LMT, /* delivery rate application limited ? */
+ TCP_NLA_SNDQ_SIZE, /* Data (bytes) pending in send queue */
+ TCP_NLA_CA_STATE, /* ca_state of socket */
+ TCP_NLA_SND_SSTHRESH, /* Slow start size threshold */
+ TCP_NLA_DELIVERED, /* Data pkts delivered incl. out-of-order */
+ TCP_NLA_DELIVERED_CE, /* Like above but only ones w/ CE marks */
+ TCP_NLA_BYTES_SENT, /* Data bytes sent including retransmission */
+ TCP_NLA_BYTES_RETRANS, /* Data bytes retransmitted */
+ TCP_NLA_DSACK_DUPS, /* DSACK blocks received */
+ TCP_NLA_REORD_SEEN, /* reordering events seen */
+ TCP_NLA_SRTT, /* smoothed RTT in usecs */
+ TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */
+ TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */
+ TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */
+ TCP_NLA_TTL, /* TTL or hop limit of a packet received */
+ TCP_NLA_REHASH, /* PLB and timeout triggered rehash attempts */
+};
+
+/* for TCP_MD5SIG socket option */
+#define TCP_MD5SIG_MAXKEYLEN 80
+
+/* tcp_md5sig extension flags for TCP_MD5SIG_EXT */
+#define TCP_MD5SIG_FLAG_PREFIX 0x1 /* address prefix length */
+#define TCP_MD5SIG_FLAG_IFINDEX 0x2 /* ifindex set */
+
+struct tcp_md5sig {
+ struct __kernel_sockaddr_storage tcpm_addr; /* address associated */
+ __u8 tcpm_flags; /* extension flags */
+ __u8 tcpm_prefixlen; /* address prefix */
+ __u16 tcpm_keylen; /* key length */
+ int tcpm_ifindex; /* device index for scope */
+ __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
+};
+
+/* INET_DIAG_MD5SIG */
+struct tcp_diag_md5sig {
+ __u8 tcpm_family;
+ __u8 tcpm_prefixlen;
+ __u16 tcpm_keylen;
+ __be32 tcpm_addr[4];
+ __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN];
+};
+
+#define TCP_AO_MAXKEYLEN 80
+
+#define TCP_AO_KEYF_IFINDEX (1 << 0) /* L3 ifindex for VRF */
+#define TCP_AO_KEYF_EXCLUDE_OPT (1 << 1) /* "Indicates whether TCP
+ * options other than TCP-AO
+ * are included in the MAC
+ * calculation"
+ */
+
+struct tcp_ao_add { /* setsockopt(TCP_AO_ADD_KEY) */
+ struct __kernel_sockaddr_storage addr; /* peer's address for the key */
+ char alg_name[64]; /* crypto hash algorithm to use */
+ __s32 ifindex; /* L3 dev index for VRF */
+ __u32 set_current :1, /* set key as Current_key at once */
+ set_rnext :1, /* request it from peer with RNext_key */
+ reserved :30; /* must be 0 */
+ __u16 reserved2; /* padding, must be 0 */
+ __u8 prefix; /* peer's address prefix */
+ __u8 sndid; /* SendID for outgoing segments */
+ __u8 rcvid; /* RecvID to match for incoming seg */
+ __u8 maclen; /* length of authentication code (hash) */
+ __u8 keyflags; /* see TCP_AO_KEYF_ */
+ __u8 keylen; /* length of ::key */
+ __u8 key[TCP_AO_MAXKEYLEN];
+} __attribute__((aligned(8)));
+
+struct tcp_ao_del { /* setsockopt(TCP_AO_DEL_KEY) */
+ struct __kernel_sockaddr_storage addr; /* peer's address for the key */
+ __s32 ifindex; /* L3 dev index for VRF */
+ __u32 set_current :1, /* corresponding ::current_key */
+ set_rnext :1, /* corresponding ::rnext */
+ del_async :1, /* only valid for listen sockets */
+ reserved :29; /* must be 0 */
+ __u16 reserved2; /* padding, must be 0 */
+ __u8 prefix; /* peer's address prefix */
+ __u8 sndid; /* SendID for outgoing segments */
+ __u8 rcvid; /* RecvID to match for incoming seg */
+ __u8 current_key; /* KeyID to set as Current_key */
+ __u8 rnext; /* KeyID to set as Rnext_key */
+ __u8 keyflags; /* see TCP_AO_KEYF_ */
+} __attribute__((aligned(8)));
+
+struct tcp_ao_info_opt { /* setsockopt(TCP_AO_INFO), getsockopt(TCP_AO_INFO) */
+ /* Here 'in' is for setsockopt(), 'out' is for getsockopt() */
+ __u32 set_current :1, /* in/out: corresponding ::current_key */
+ set_rnext :1, /* in/out: corresponding ::rnext */
+ ao_required :1, /* in/out: don't accept non-AO connects */
+ set_counters :1, /* in: set/clear ::pkt_* counters */
+ accept_icmps :1, /* in/out: accept incoming ICMPs */
+ reserved :27; /* must be 0 */
+ __u16 reserved2; /* padding, must be 0 */
+ __u8 current_key; /* in/out: KeyID of Current_key */
+ __u8 rnext; /* in/out: keyid of RNext_key */
+ __u64 pkt_good; /* in/out: verified segments */
+ __u64 pkt_bad; /* in/out: failed verification */
+ __u64 pkt_key_not_found; /* in/out: could not find a key to verify */
+ __u64 pkt_ao_required; /* in/out: segments missing TCP-AO sign */
+ __u64 pkt_dropped_icmp; /* in/out: ICMPs that were ignored */
+} __attribute__((aligned(8)));
+
+struct tcp_ao_getsockopt { /* getsockopt(TCP_AO_GET_KEYS) */
+ struct __kernel_sockaddr_storage addr; /* in/out: dump keys for peer
+ * with this address/prefix
+ */
+ char alg_name[64]; /* out: crypto hash algorithm */
+ __u8 key[TCP_AO_MAXKEYLEN];
+ __u32 nkeys; /* in: size of the userspace buffer
+ * @optval, measured in @optlen - the
+ * sizeof(struct tcp_ao_getsockopt)
+ * out: number of keys that matched
+ */
+ __u16 is_current :1, /* in: match and dump Current_key,
+ * out: the dumped key is Current_key
+ */
+
+ is_rnext :1, /* in: match and dump RNext_key,
+ * out: the dumped key is RNext_key
+ */
+ get_all :1, /* in: dump all keys */
+ reserved :13; /* padding, must be 0 */
+ __u8 sndid; /* in/out: dump keys with SendID */
+ __u8 rcvid; /* in/out: dump keys with RecvID */
+ __u8 prefix; /* in/out: dump keys with address/prefix */
+ __u8 maclen; /* out: key's length of authentication
+ * code (hash)
+ */
+ __u8 keyflags; /* in/out: see TCP_AO_KEYF_ */
+ __u8 keylen; /* out: length of ::key */
+ __s32 ifindex; /* in/out: L3 dev index for VRF */
+ __u64 pkt_good; /* out: verified segments */
+ __u64 pkt_bad; /* out: segments that failed verification */
+} __attribute__((aligned(8)));
+
+struct tcp_ao_repair { /* {s,g}etsockopt(TCP_AO_REPAIR) */
+ __be32 snt_isn;
+ __be32 rcv_isn;
+ __u32 snd_sne;
+ __u32 rcv_sne;
+} __attribute__((aligned(8)));
+
+/* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */
+
+#define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1
+struct tcp_zerocopy_receive {
+ __u64 address; /* in: address of mapping */
+ __u32 length; /* in/out: number of bytes to map/mapped */
+ __u32 recv_skip_hint; /* out: amount of bytes to skip */
+ __u32 inq; /* out: amount of bytes in read queue */
+ __s32 err; /* out: socket error */
+ __u64 copybuf_address; /* in: copybuf address (small reads) */
+ __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */
+ __u32 flags; /* in: flags */
+ __u64 msg_control; /* ancillary data */
+ __u64 msg_controllen;
+ __u32 msg_flags;
+ __u32 reserved; /* set to 0 for now */
+};
+#endif /* _LINUX_TCP_H */
diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h
new file mode 100644
index 0000000..7cb4a17
--- /dev/null
+++ b/include/uapi/linux/tcp_metrics.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* tcp_metrics.h - TCP Metrics Interface */
+
+#ifndef _LINUX_TCP_METRICS_H
+#define _LINUX_TCP_METRICS_H
+
+#include <linux/types.h>
+
+/* NETLINK_GENERIC related info
+ */
+#define TCP_METRICS_GENL_NAME "tcp_metrics"
+#define TCP_METRICS_GENL_VERSION 0x1
+
+enum tcp_metric_index {
+ TCP_METRIC_RTT, /* in ms units */
+ TCP_METRIC_RTTVAR, /* in ms units */
+ TCP_METRIC_SSTHRESH,
+ TCP_METRIC_CWND,
+ TCP_METRIC_REORDERING,
+
+ TCP_METRIC_RTT_US, /* in usec units */
+ TCP_METRIC_RTTVAR_US, /* in usec units */
+
+ /* Always last. */
+ __TCP_METRIC_MAX,
+};
+
+#define TCP_METRIC_MAX (__TCP_METRIC_MAX - 1)
+
+enum {
+ TCP_METRICS_ATTR_UNSPEC,
+ TCP_METRICS_ATTR_ADDR_IPV4, /* u32 */
+ TCP_METRICS_ATTR_ADDR_IPV6, /* binary */
+ TCP_METRICS_ATTR_AGE, /* msecs */
+ TCP_METRICS_ATTR_TW_TSVAL, /* u32, raw, rcv tsval */
+ TCP_METRICS_ATTR_TW_TS_STAMP, /* s32, sec age */
+ TCP_METRICS_ATTR_VALS, /* nested +1, u32 */
+ TCP_METRICS_ATTR_FOPEN_MSS, /* u16 */
+ TCP_METRICS_ATTR_FOPEN_SYN_DROPS, /* u16, count of drops */
+ TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS, /* msecs age */
+ TCP_METRICS_ATTR_FOPEN_COOKIE, /* binary */
+ TCP_METRICS_ATTR_SADDR_IPV4, /* u32 */
+ TCP_METRICS_ATTR_SADDR_IPV6, /* binary */
+ TCP_METRICS_ATTR_PAD,
+
+ __TCP_METRICS_ATTR_MAX,
+};
+
+#define TCP_METRICS_ATTR_MAX (__TCP_METRICS_ATTR_MAX - 1)
+
+enum {
+ TCP_METRICS_CMD_UNSPEC,
+ TCP_METRICS_CMD_GET,
+ TCP_METRICS_CMD_DEL,
+
+ __TCP_METRICS_CMD_MAX,
+};
+
+#define TCP_METRICS_CMD_MAX (__TCP_METRICS_CMD_MAX - 1)
+
+#endif /* _LINUX_TCP_METRICS_H */
diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
new file mode 100644
index 0000000..f08cc36
--- /dev/null
+++ b/include/uapi/linux/tipc.h
@@ -0,0 +1,315 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/*
+ * include/uapi/linux/tipc.h: Header for TIPC socket interface
+ *
+ * Copyright (c) 2003-2006, 2015-2016 Ericsson AB
+ * Copyright (c) 2005, 2010-2011, Wind River Systems
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_TIPC_H_
+#define _LINUX_TIPC_H_
+
+#include <linux/types.h>
+#include <linux/sockios.h>
+
+/*
+ * TIPC addressing primitives
+ */
+
+struct tipc_socket_addr {
+ __u32 ref;
+ __u32 node;
+};
+
+struct tipc_service_addr {
+ __u32 type;
+ __u32 instance;
+};
+
+struct tipc_service_range {
+ __u32 type;
+ __u32 lower;
+ __u32 upper;
+};
+
+/*
+ * Application-accessible service types
+ */
+
+#define TIPC_NODE_STATE 0 /* node state service type */
+#define TIPC_TOP_SRV 1 /* topology server service type */
+#define TIPC_LINK_STATE 2 /* link state service type */
+#define TIPC_RESERVED_TYPES 64 /* lowest user-allowed service type */
+
+/*
+ * Publication scopes when binding service / service range
+ */
+enum tipc_scope {
+ TIPC_CLUSTER_SCOPE = 2, /* 0 can also be used */
+ TIPC_NODE_SCOPE = 3
+};
+
+/*
+ * Limiting values for messages
+ */
+
+#define TIPC_MAX_USER_MSG_SIZE 66000U
+
+/*
+ * Message importance levels
+ */
+
+#define TIPC_LOW_IMPORTANCE 0
+#define TIPC_MEDIUM_IMPORTANCE 1
+#define TIPC_HIGH_IMPORTANCE 2
+#define TIPC_CRITICAL_IMPORTANCE 3
+
+/*
+ * Msg rejection/connection shutdown reasons
+ */
+
+#define TIPC_OK 0
+#define TIPC_ERR_NO_NAME 1
+#define TIPC_ERR_NO_PORT 2
+#define TIPC_ERR_NO_NODE 3
+#define TIPC_ERR_OVERLOAD 4
+#define TIPC_CONN_SHUTDOWN 5
+
+/*
+ * TIPC topology subscription service definitions
+ */
+
+#define TIPC_SUB_PORTS 0x01 /* filter: evt at each match */
+#define TIPC_SUB_SERVICE 0x02 /* filter: evt at first up/last down */
+#define TIPC_SUB_CANCEL 0x04 /* filter: cancel a subscription */
+
+#define TIPC_WAIT_FOREVER (~0) /* timeout for permanent subscription */
+
+struct tipc_subscr {
+ struct tipc_service_range seq; /* range of interest */
+ __u32 timeout; /* subscription duration (in ms) */
+ __u32 filter; /* bitmask of filter options */
+ char usr_handle[8]; /* available for subscriber use */
+};
+
+#define TIPC_PUBLISHED 1 /* publication event */
+#define TIPC_WITHDRAWN 2 /* withdrawal event */
+#define TIPC_SUBSCR_TIMEOUT 3 /* subscription timeout event */
+
+struct tipc_event {
+ __u32 event; /* event type */
+ __u32 found_lower; /* matching range */
+ __u32 found_upper; /* " " */
+ struct tipc_socket_addr port; /* associated socket */
+ struct tipc_subscr s; /* associated subscription */
+};
+
+/*
+ * Socket API
+ */
+
+#ifndef AF_TIPC
+#define AF_TIPC 30
+#endif
+
+#ifndef PF_TIPC
+#define PF_TIPC AF_TIPC
+#endif
+
+#ifndef SOL_TIPC
+#define SOL_TIPC 271
+#endif
+
+#define TIPC_ADDR_MCAST 1
+#define TIPC_SERVICE_RANGE 1
+#define TIPC_SERVICE_ADDR 2
+#define TIPC_SOCKET_ADDR 3
+
+struct sockaddr_tipc {
+ unsigned short family;
+ unsigned char addrtype;
+ signed char scope;
+ union {
+ struct tipc_socket_addr id;
+ struct tipc_service_range nameseq;
+ struct {
+ struct tipc_service_addr name;
+ __u32 domain;
+ } name;
+ } addr;
+};
+
+/*
+ * Ancillary data objects supported by recvmsg()
+ */
+
+#define TIPC_ERRINFO 1 /* error info */
+#define TIPC_RETDATA 2 /* returned data */
+#define TIPC_DESTNAME 3 /* destination name */
+
+/*
+ * TIPC-specific socket option names
+ */
+
+#define TIPC_IMPORTANCE 127 /* Default: TIPC_LOW_IMPORTANCE */
+#define TIPC_SRC_DROPPABLE 128 /* Default: based on socket type */
+#define TIPC_DEST_DROPPABLE 129 /* Default: based on socket type */
+#define TIPC_CONN_TIMEOUT 130 /* Default: 8000 (ms) */
+#define TIPC_NODE_RECVQ_DEPTH 131 /* Default: none (read only) */
+#define TIPC_SOCK_RECVQ_DEPTH 132 /* Default: none (read only) */
+#define TIPC_MCAST_BROADCAST 133 /* Default: TIPC selects. No arg */
+#define TIPC_MCAST_REPLICAST 134 /* Default: TIPC selects. No arg */
+#define TIPC_GROUP_JOIN 135 /* Takes struct tipc_group_req* */
+#define TIPC_GROUP_LEAVE 136 /* No argument */
+#define TIPC_SOCK_RECVQ_USED 137 /* Default: none (read only) */
+#define TIPC_NODELAY 138 /* Default: false */
+
+/*
+ * Flag values
+ */
+#define TIPC_GROUP_LOOPBACK 0x1 /* Receive copy of sent msg when match */
+#define TIPC_GROUP_MEMBER_EVTS 0x2 /* Receive membership events in socket */
+
+struct tipc_group_req {
+ __u32 type; /* group id */
+ __u32 instance; /* member id */
+ __u32 scope; /* cluster/node */
+ __u32 flags;
+};
+
+/*
+ * Maximum sizes of TIPC bearer-related names (including terminating NULL)
+ * The string formatting for each name element is:
+ * media: media
+ * interface: media:interface name
+ * link: node:interface-node:interface
+ */
+#define TIPC_NODEID_LEN 16
+#define TIPC_MAX_MEDIA_NAME 16
+#define TIPC_MAX_IF_NAME 16
+#define TIPC_MAX_BEARER_NAME 32
+#define TIPC_MAX_LINK_NAME 68
+
+#define SIOCGETLINKNAME SIOCPROTOPRIVATE
+#define SIOCGETNODEID (SIOCPROTOPRIVATE + 1)
+
+struct tipc_sioc_ln_req {
+ __u32 peer;
+ __u32 bearer_id;
+ char linkname[TIPC_MAX_LINK_NAME];
+};
+
+struct tipc_sioc_nodeid_req {
+ __u32 peer;
+ char node_id[TIPC_NODEID_LEN];
+};
+
+/*
+ * TIPC Crypto, AEAD
+ */
+#define TIPC_AEAD_ALG_NAME (32)
+
+struct tipc_aead_key {
+ char alg_name[TIPC_AEAD_ALG_NAME];
+ unsigned int keylen; /* in bytes */
+ char key[];
+};
+
+#define TIPC_AEAD_KEYLEN_MIN (16 + 4)
+#define TIPC_AEAD_KEYLEN_MAX (32 + 4)
+#define TIPC_AEAD_KEY_SIZE_MAX (sizeof(struct tipc_aead_key) + \
+ TIPC_AEAD_KEYLEN_MAX)
+
+static __inline__ int tipc_aead_key_size(struct tipc_aead_key *key)
+{
+ return sizeof(*key) + key->keylen;
+}
+
+#define TIPC_REKEYING_NOW (~0U)
+
+/* The macros and functions below are deprecated:
+ */
+
+#define TIPC_CFG_SRV 0
+#define TIPC_ZONE_SCOPE 1
+
+#define TIPC_ADDR_NAMESEQ 1
+#define TIPC_ADDR_NAME 2
+#define TIPC_ADDR_ID 3
+
+#define TIPC_NODE_BITS 12
+#define TIPC_CLUSTER_BITS 12
+#define TIPC_ZONE_BITS 8
+
+#define TIPC_NODE_OFFSET 0
+#define TIPC_CLUSTER_OFFSET TIPC_NODE_BITS
+#define TIPC_ZONE_OFFSET (TIPC_CLUSTER_OFFSET + TIPC_CLUSTER_BITS)
+
+#define TIPC_NODE_SIZE ((1UL << TIPC_NODE_BITS) - 1)
+#define TIPC_CLUSTER_SIZE ((1UL << TIPC_CLUSTER_BITS) - 1)
+#define TIPC_ZONE_SIZE ((1UL << TIPC_ZONE_BITS) - 1)
+
+#define TIPC_NODE_MASK (TIPC_NODE_SIZE << TIPC_NODE_OFFSET)
+#define TIPC_CLUSTER_MASK (TIPC_CLUSTER_SIZE << TIPC_CLUSTER_OFFSET)
+#define TIPC_ZONE_MASK (TIPC_ZONE_SIZE << TIPC_ZONE_OFFSET)
+
+#define TIPC_ZONE_CLUSTER_MASK (TIPC_ZONE_MASK | TIPC_CLUSTER_MASK)
+
+#define tipc_portid tipc_socket_addr
+#define tipc_name tipc_service_addr
+#define tipc_name_seq tipc_service_range
+
+static __inline__ __u32 tipc_addr(unsigned int zone,
+ unsigned int cluster,
+ unsigned int node)
+{
+ return (zone << TIPC_ZONE_OFFSET) |
+ (cluster << TIPC_CLUSTER_OFFSET) |
+ node;
+}
+
+static __inline__ unsigned int tipc_zone(__u32 addr)
+{
+ return addr >> TIPC_ZONE_OFFSET;
+}
+
+static __inline__ unsigned int tipc_cluster(__u32 addr)
+{
+ return (addr & TIPC_CLUSTER_MASK) >> TIPC_CLUSTER_OFFSET;
+}
+
+static __inline__ unsigned int tipc_node(__u32 addr)
+{
+ return addr & TIPC_NODE_MASK;
+}
+
+#endif
diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
new file mode 100644
index 0000000..d847dd6
--- /dev/null
+++ b/include/uapi/linux/tipc_netlink.h
@@ -0,0 +1,341 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/*
+ * Copyright (c) 2014, Ericsson AB
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_TIPC_NETLINK_H_
+#define _LINUX_TIPC_NETLINK_H_
+
+#define TIPC_GENL_V2_NAME "TIPCv2"
+#define TIPC_GENL_V2_VERSION 0x1
+
+/* Netlink commands */
+enum {
+ TIPC_NL_UNSPEC,
+ TIPC_NL_LEGACY,
+ TIPC_NL_BEARER_DISABLE,
+ TIPC_NL_BEARER_ENABLE,
+ TIPC_NL_BEARER_GET,
+ TIPC_NL_BEARER_SET,
+ TIPC_NL_SOCK_GET,
+ TIPC_NL_PUBL_GET,
+ TIPC_NL_LINK_GET,
+ TIPC_NL_LINK_SET,
+ TIPC_NL_LINK_RESET_STATS,
+ TIPC_NL_MEDIA_GET,
+ TIPC_NL_MEDIA_SET,
+ TIPC_NL_NODE_GET,
+ TIPC_NL_NET_GET,
+ TIPC_NL_NET_SET,
+ TIPC_NL_NAME_TABLE_GET,
+ TIPC_NL_MON_SET,
+ TIPC_NL_MON_GET,
+ TIPC_NL_MON_PEER_GET,
+ TIPC_NL_PEER_REMOVE,
+ TIPC_NL_BEARER_ADD,
+ TIPC_NL_UDP_GET_REMOTEIP,
+ TIPC_NL_KEY_SET,
+ TIPC_NL_KEY_FLUSH,
+ TIPC_NL_ADDR_LEGACY_GET,
+
+ __TIPC_NL_CMD_MAX,
+ TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1
+};
+
+/* Top level netlink attributes */
+enum {
+ TIPC_NLA_UNSPEC,
+ TIPC_NLA_BEARER, /* nest */
+ TIPC_NLA_SOCK, /* nest */
+ TIPC_NLA_PUBL, /* nest */
+ TIPC_NLA_LINK, /* nest */
+ TIPC_NLA_MEDIA, /* nest */
+ TIPC_NLA_NODE, /* nest */
+ TIPC_NLA_NET, /* nest */
+ TIPC_NLA_NAME_TABLE, /* nest */
+ TIPC_NLA_MON, /* nest */
+ TIPC_NLA_MON_PEER, /* nest */
+
+ __TIPC_NLA_MAX,
+ TIPC_NLA_MAX = __TIPC_NLA_MAX - 1
+};
+
+/* Bearer info */
+enum {
+ TIPC_NLA_BEARER_UNSPEC,
+ TIPC_NLA_BEARER_NAME, /* string */
+ TIPC_NLA_BEARER_PROP, /* nest */
+ TIPC_NLA_BEARER_DOMAIN, /* u32 */
+ TIPC_NLA_BEARER_UDP_OPTS, /* nest */
+
+ __TIPC_NLA_BEARER_MAX,
+ TIPC_NLA_BEARER_MAX = __TIPC_NLA_BEARER_MAX - 1
+};
+
+enum {
+ TIPC_NLA_UDP_UNSPEC,
+ TIPC_NLA_UDP_LOCAL, /* sockaddr_storage */
+ TIPC_NLA_UDP_REMOTE, /* sockaddr_storage */
+ TIPC_NLA_UDP_MULTI_REMOTEIP, /* flag */
+
+ __TIPC_NLA_UDP_MAX,
+ TIPC_NLA_UDP_MAX = __TIPC_NLA_UDP_MAX - 1
+};
+/* Socket info */
+enum {
+ TIPC_NLA_SOCK_UNSPEC,
+ TIPC_NLA_SOCK_ADDR, /* u32 */
+ TIPC_NLA_SOCK_REF, /* u32 */
+ TIPC_NLA_SOCK_CON, /* nest */
+ TIPC_NLA_SOCK_HAS_PUBL, /* flag */
+ TIPC_NLA_SOCK_STAT, /* nest */
+ TIPC_NLA_SOCK_TYPE, /* u32 */
+ TIPC_NLA_SOCK_INO, /* u32 */
+ TIPC_NLA_SOCK_UID, /* u32 */
+ TIPC_NLA_SOCK_TIPC_STATE, /* u32 */
+ TIPC_NLA_SOCK_COOKIE, /* u64 */
+ TIPC_NLA_SOCK_PAD, /* flag */
+ TIPC_NLA_SOCK_GROUP, /* nest */
+
+ __TIPC_NLA_SOCK_MAX,
+ TIPC_NLA_SOCK_MAX = __TIPC_NLA_SOCK_MAX - 1
+};
+
+/* Link info */
+enum {
+ TIPC_NLA_LINK_UNSPEC,
+ TIPC_NLA_LINK_NAME, /* string */
+ TIPC_NLA_LINK_DEST, /* u32 */
+ TIPC_NLA_LINK_MTU, /* u32 */
+ TIPC_NLA_LINK_BROADCAST, /* flag */
+ TIPC_NLA_LINK_UP, /* flag */
+ TIPC_NLA_LINK_ACTIVE, /* flag */
+ TIPC_NLA_LINK_PROP, /* nest */
+ TIPC_NLA_LINK_STATS, /* nest */
+ TIPC_NLA_LINK_RX, /* u32 */
+ TIPC_NLA_LINK_TX, /* u32 */
+
+ __TIPC_NLA_LINK_MAX,
+ TIPC_NLA_LINK_MAX = __TIPC_NLA_LINK_MAX - 1
+};
+
+/* Media info */
+enum {
+ TIPC_NLA_MEDIA_UNSPEC,
+ TIPC_NLA_MEDIA_NAME, /* string */
+ TIPC_NLA_MEDIA_PROP, /* nest */
+
+ __TIPC_NLA_MEDIA_MAX,
+ TIPC_NLA_MEDIA_MAX = __TIPC_NLA_MEDIA_MAX - 1
+};
+
+/* Node info */
+enum {
+ TIPC_NLA_NODE_UNSPEC,
+ TIPC_NLA_NODE_ADDR, /* u32 */
+ TIPC_NLA_NODE_UP, /* flag */
+ TIPC_NLA_NODE_ID, /* data */
+ TIPC_NLA_NODE_KEY, /* data */
+ TIPC_NLA_NODE_KEY_MASTER, /* flag */
+ TIPC_NLA_NODE_REKEYING, /* u32 */
+
+ __TIPC_NLA_NODE_MAX,
+ TIPC_NLA_NODE_MAX = __TIPC_NLA_NODE_MAX - 1
+};
+
+/* Net info */
+enum {
+ TIPC_NLA_NET_UNSPEC,
+ TIPC_NLA_NET_ID, /* u32 */
+ TIPC_NLA_NET_ADDR, /* u32 */
+ TIPC_NLA_NET_NODEID, /* u64 */
+ TIPC_NLA_NET_NODEID_W1, /* u64 */
+ TIPC_NLA_NET_ADDR_LEGACY, /* flag */
+
+ __TIPC_NLA_NET_MAX,
+ TIPC_NLA_NET_MAX = __TIPC_NLA_NET_MAX - 1
+};
+
+/* Name table info */
+enum {
+ TIPC_NLA_NAME_TABLE_UNSPEC,
+ TIPC_NLA_NAME_TABLE_PUBL, /* nest */
+
+ __TIPC_NLA_NAME_TABLE_MAX,
+ TIPC_NLA_NAME_TABLE_MAX = __TIPC_NLA_NAME_TABLE_MAX - 1
+};
+
+/* Monitor info */
+enum {
+ TIPC_NLA_MON_UNSPEC,
+ TIPC_NLA_MON_ACTIVATION_THRESHOLD, /* u32 */
+ TIPC_NLA_MON_REF, /* u32 */
+ TIPC_NLA_MON_ACTIVE, /* flag */
+ TIPC_NLA_MON_BEARER_NAME, /* string */
+ TIPC_NLA_MON_PEERCNT, /* u32 */
+ TIPC_NLA_MON_LISTGEN, /* u32 */
+
+ __TIPC_NLA_MON_MAX,
+ TIPC_NLA_MON_MAX = __TIPC_NLA_MON_MAX - 1
+};
+
+/* Publication info */
+enum {
+ TIPC_NLA_PUBL_UNSPEC,
+
+ TIPC_NLA_PUBL_TYPE, /* u32 */
+ TIPC_NLA_PUBL_LOWER, /* u32 */
+ TIPC_NLA_PUBL_UPPER, /* u32 */
+ TIPC_NLA_PUBL_SCOPE, /* u32 */
+ TIPC_NLA_PUBL_NODE, /* u32 */
+ TIPC_NLA_PUBL_REF, /* u32 */
+ TIPC_NLA_PUBL_KEY, /* u32 */
+
+ __TIPC_NLA_PUBL_MAX,
+ TIPC_NLA_PUBL_MAX = __TIPC_NLA_PUBL_MAX - 1
+};
+
+/* Monitor peer info */
+enum {
+ TIPC_NLA_MON_PEER_UNSPEC,
+
+ TIPC_NLA_MON_PEER_ADDR, /* u32 */
+ TIPC_NLA_MON_PEER_DOMGEN, /* u32 */
+ TIPC_NLA_MON_PEER_APPLIED, /* u32 */
+ TIPC_NLA_MON_PEER_UPMAP, /* u64 */
+ TIPC_NLA_MON_PEER_MEMBERS, /* tlv */
+ TIPC_NLA_MON_PEER_UP, /* flag */
+ TIPC_NLA_MON_PEER_HEAD, /* flag */
+ TIPC_NLA_MON_PEER_LOCAL, /* flag */
+ TIPC_NLA_MON_PEER_PAD, /* flag */
+
+ __TIPC_NLA_MON_PEER_MAX,
+ TIPC_NLA_MON_PEER_MAX = __TIPC_NLA_MON_PEER_MAX - 1
+};
+
+/* Nest, socket group info */
+enum {
+ TIPC_NLA_SOCK_GROUP_ID, /* u32 */
+ TIPC_NLA_SOCK_GROUP_OPEN, /* flag */
+ TIPC_NLA_SOCK_GROUP_NODE_SCOPE, /* flag */
+ TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE, /* flag */
+ TIPC_NLA_SOCK_GROUP_INSTANCE, /* u32 */
+ TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT, /* u32 */
+
+ __TIPC_NLA_SOCK_GROUP_MAX,
+ TIPC_NLA_SOCK_GROUP_MAX = __TIPC_NLA_SOCK_GROUP_MAX - 1
+};
+
+/* Nest, connection info */
+enum {
+ TIPC_NLA_CON_UNSPEC,
+
+ TIPC_NLA_CON_FLAG, /* flag */
+ TIPC_NLA_CON_NODE, /* u32 */
+ TIPC_NLA_CON_SOCK, /* u32 */
+ TIPC_NLA_CON_TYPE, /* u32 */
+ TIPC_NLA_CON_INST, /* u32 */
+
+ __TIPC_NLA_CON_MAX,
+ TIPC_NLA_CON_MAX = __TIPC_NLA_CON_MAX - 1
+};
+
+/* Nest, socket statistics info */
+enum {
+ TIPC_NLA_SOCK_STAT_RCVQ, /* u32 */
+ TIPC_NLA_SOCK_STAT_SENDQ, /* u32 */
+ TIPC_NLA_SOCK_STAT_LINK_CONG, /* flag */
+ TIPC_NLA_SOCK_STAT_CONN_CONG, /* flag */
+ TIPC_NLA_SOCK_STAT_DROP, /* u32 */
+
+ __TIPC_NLA_SOCK_STAT_MAX,
+ TIPC_NLA_SOCK_STAT_MAX = __TIPC_NLA_SOCK_STAT_MAX - 1
+};
+
+/* Nest, link propreties. Valid for link, media and bearer */
+enum {
+ TIPC_NLA_PROP_UNSPEC,
+
+ TIPC_NLA_PROP_PRIO, /* u32 */
+ TIPC_NLA_PROP_TOL, /* u32 */
+ TIPC_NLA_PROP_WIN, /* u32 */
+ TIPC_NLA_PROP_MTU, /* u32 */
+ TIPC_NLA_PROP_BROADCAST, /* u32 */
+ TIPC_NLA_PROP_BROADCAST_RATIO, /* u32 */
+
+ __TIPC_NLA_PROP_MAX,
+ TIPC_NLA_PROP_MAX = __TIPC_NLA_PROP_MAX - 1
+};
+
+/* Nest, statistics info */
+enum {
+ TIPC_NLA_STATS_UNSPEC,
+
+ TIPC_NLA_STATS_RX_INFO, /* u32 */
+ TIPC_NLA_STATS_RX_FRAGMENTS, /* u32 */
+ TIPC_NLA_STATS_RX_FRAGMENTED, /* u32 */
+ TIPC_NLA_STATS_RX_BUNDLES, /* u32 */
+ TIPC_NLA_STATS_RX_BUNDLED, /* u32 */
+ TIPC_NLA_STATS_TX_INFO, /* u32 */
+ TIPC_NLA_STATS_TX_FRAGMENTS, /* u32 */
+ TIPC_NLA_STATS_TX_FRAGMENTED, /* u32 */
+ TIPC_NLA_STATS_TX_BUNDLES, /* u32 */
+ TIPC_NLA_STATS_TX_BUNDLED, /* u32 */
+ TIPC_NLA_STATS_MSG_PROF_TOT, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_CNT, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_TOT, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P0, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P1, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P2, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P3, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P4, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P5, /* u32 */
+ TIPC_NLA_STATS_MSG_LEN_P6, /* u32 */
+ TIPC_NLA_STATS_RX_STATES, /* u32 */
+ TIPC_NLA_STATS_RX_PROBES, /* u32 */
+ TIPC_NLA_STATS_RX_NACKS, /* u32 */
+ TIPC_NLA_STATS_RX_DEFERRED, /* u32 */
+ TIPC_NLA_STATS_TX_STATES, /* u32 */
+ TIPC_NLA_STATS_TX_PROBES, /* u32 */
+ TIPC_NLA_STATS_TX_NACKS, /* u32 */
+ TIPC_NLA_STATS_TX_ACKS, /* u32 */
+ TIPC_NLA_STATS_RETRANSMITTED, /* u32 */
+ TIPC_NLA_STATS_DUPLICATES, /* u32 */
+ TIPC_NLA_STATS_LINK_CONGS, /* u32 */
+ TIPC_NLA_STATS_MAX_QUEUE, /* u32 */
+ TIPC_NLA_STATS_AVG_QUEUE, /* u32 */
+
+ __TIPC_NLA_STATS_MAX,
+ TIPC_NLA_STATS_MAX = __TIPC_NLA_STATS_MAX - 1
+};
+
+#endif
diff --git a/include/uapi/linux/tipc_sockets_diag.h b/include/uapi/linux/tipc_sockets_diag.h
new file mode 100644
index 0000000..21b766e
--- /dev/null
+++ b/include/uapi/linux/tipc_sockets_diag.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* AF_TIPC sock_diag interface for querying open sockets */
+
+#ifndef __TIPC_SOCKETS_DIAG_H__
+#define __TIPC_SOCKETS_DIAG_H__
+
+#include <linux/types.h>
+#include <linux/sock_diag.h>
+
+/* Request */
+struct tipc_sock_diag_req {
+ __u8 sdiag_family; /* must be AF_TIPC */
+ __u8 sdiag_protocol; /* must be 0 */
+ __u16 pad; /* must be 0 */
+ __u32 tidiag_states; /* query*/
+};
+#endif /* __TIPC_SOCKETS_DIAG_H__ */
diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h
new file mode 100644
index 0000000..dd7dea8
--- /dev/null
+++ b/include/uapi/linux/tls.h
@@ -0,0 +1,206 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/*
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _LINUX_TLS_H
+#define _LINUX_TLS_H
+
+#include <linux/types.h>
+
+/* TLS socket options */
+#define TLS_TX 1 /* Set transmit parameters */
+#define TLS_RX 2 /* Set receive parameters */
+#define TLS_TX_ZEROCOPY_RO 3 /* TX zerocopy (only sendfile now) */
+#define TLS_RX_EXPECT_NO_PAD 4 /* Attempt opportunistic zero-copy */
+
+/* Supported versions */
+#define TLS_VERSION_MINOR(ver) ((ver) & 0xFF)
+#define TLS_VERSION_MAJOR(ver) (((ver) >> 8) & 0xFF)
+
+#define TLS_VERSION_NUMBER(id) ((((id##_VERSION_MAJOR) & 0xFF) << 8) | \
+ ((id##_VERSION_MINOR) & 0xFF))
+
+#define TLS_1_2_VERSION_MAJOR 0x3
+#define TLS_1_2_VERSION_MINOR 0x3
+#define TLS_1_2_VERSION TLS_VERSION_NUMBER(TLS_1_2)
+
+#define TLS_1_3_VERSION_MAJOR 0x3
+#define TLS_1_3_VERSION_MINOR 0x4
+#define TLS_1_3_VERSION TLS_VERSION_NUMBER(TLS_1_3)
+
+/* Supported ciphers */
+#define TLS_CIPHER_AES_GCM_128 51
+#define TLS_CIPHER_AES_GCM_128_IV_SIZE 8
+#define TLS_CIPHER_AES_GCM_128_KEY_SIZE 16
+#define TLS_CIPHER_AES_GCM_128_SALT_SIZE 4
+#define TLS_CIPHER_AES_GCM_128_TAG_SIZE 16
+#define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE 8
+
+#define TLS_CIPHER_AES_GCM_256 52
+#define TLS_CIPHER_AES_GCM_256_IV_SIZE 8
+#define TLS_CIPHER_AES_GCM_256_KEY_SIZE 32
+#define TLS_CIPHER_AES_GCM_256_SALT_SIZE 4
+#define TLS_CIPHER_AES_GCM_256_TAG_SIZE 16
+#define TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE 8
+
+#define TLS_CIPHER_AES_CCM_128 53
+#define TLS_CIPHER_AES_CCM_128_IV_SIZE 8
+#define TLS_CIPHER_AES_CCM_128_KEY_SIZE 16
+#define TLS_CIPHER_AES_CCM_128_SALT_SIZE 4
+#define TLS_CIPHER_AES_CCM_128_TAG_SIZE 16
+#define TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE 8
+
+#define TLS_CIPHER_CHACHA20_POLY1305 54
+#define TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE 12
+#define TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE 32
+#define TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE 0
+#define TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE 16
+#define TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE 8
+
+#define TLS_CIPHER_SM4_GCM 55
+#define TLS_CIPHER_SM4_GCM_IV_SIZE 8
+#define TLS_CIPHER_SM4_GCM_KEY_SIZE 16
+#define TLS_CIPHER_SM4_GCM_SALT_SIZE 4
+#define TLS_CIPHER_SM4_GCM_TAG_SIZE 16
+#define TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE 8
+
+#define TLS_CIPHER_SM4_CCM 56
+#define TLS_CIPHER_SM4_CCM_IV_SIZE 8
+#define TLS_CIPHER_SM4_CCM_KEY_SIZE 16
+#define TLS_CIPHER_SM4_CCM_SALT_SIZE 4
+#define TLS_CIPHER_SM4_CCM_TAG_SIZE 16
+#define TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE 8
+
+#define TLS_CIPHER_ARIA_GCM_128 57
+#define TLS_CIPHER_ARIA_GCM_128_IV_SIZE 8
+#define TLS_CIPHER_ARIA_GCM_128_KEY_SIZE 16
+#define TLS_CIPHER_ARIA_GCM_128_SALT_SIZE 4
+#define TLS_CIPHER_ARIA_GCM_128_TAG_SIZE 16
+#define TLS_CIPHER_ARIA_GCM_128_REC_SEQ_SIZE 8
+
+#define TLS_CIPHER_ARIA_GCM_256 58
+#define TLS_CIPHER_ARIA_GCM_256_IV_SIZE 8
+#define TLS_CIPHER_ARIA_GCM_256_KEY_SIZE 32
+#define TLS_CIPHER_ARIA_GCM_256_SALT_SIZE 4
+#define TLS_CIPHER_ARIA_GCM_256_TAG_SIZE 16
+#define TLS_CIPHER_ARIA_GCM_256_REC_SEQ_SIZE 8
+
+#define TLS_SET_RECORD_TYPE 1
+#define TLS_GET_RECORD_TYPE 2
+
+struct tls_crypto_info {
+ __u16 version;
+ __u16 cipher_type;
+};
+
+struct tls12_crypto_info_aes_gcm_128 {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_AES_GCM_128_IV_SIZE];
+ unsigned char key[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_AES_GCM_128_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE];
+};
+
+struct tls12_crypto_info_aes_gcm_256 {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_AES_GCM_256_IV_SIZE];
+ unsigned char key[TLS_CIPHER_AES_GCM_256_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_AES_GCM_256_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE];
+};
+
+struct tls12_crypto_info_aes_ccm_128 {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_AES_CCM_128_IV_SIZE];
+ unsigned char key[TLS_CIPHER_AES_CCM_128_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_AES_CCM_128_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE];
+};
+
+struct tls12_crypto_info_chacha20_poly1305 {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE];
+ unsigned char key[TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE];
+};
+
+struct tls12_crypto_info_sm4_gcm {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_SM4_GCM_IV_SIZE];
+ unsigned char key[TLS_CIPHER_SM4_GCM_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_SM4_GCM_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE];
+};
+
+struct tls12_crypto_info_sm4_ccm {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_SM4_CCM_IV_SIZE];
+ unsigned char key[TLS_CIPHER_SM4_CCM_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_SM4_CCM_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE];
+};
+
+struct tls12_crypto_info_aria_gcm_128 {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_ARIA_GCM_128_IV_SIZE];
+ unsigned char key[TLS_CIPHER_ARIA_GCM_128_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_ARIA_GCM_128_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_ARIA_GCM_128_REC_SEQ_SIZE];
+};
+
+struct tls12_crypto_info_aria_gcm_256 {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_ARIA_GCM_256_IV_SIZE];
+ unsigned char key[TLS_CIPHER_ARIA_GCM_256_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_ARIA_GCM_256_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_ARIA_GCM_256_REC_SEQ_SIZE];
+};
+
+enum {
+ TLS_INFO_UNSPEC,
+ TLS_INFO_VERSION,
+ TLS_INFO_CIPHER,
+ TLS_INFO_TXCONF,
+ TLS_INFO_RXCONF,
+ TLS_INFO_ZC_RO_TX,
+ TLS_INFO_RX_NO_PAD,
+ __TLS_INFO_MAX,
+};
+#define TLS_INFO_MAX (__TLS_INFO_MAX - 1)
+
+#define TLS_CONF_BASE 1
+#define TLS_CONF_SW 2
+#define TLS_CONF_HW 3
+#define TLS_CONF_HW_RECORD 4
+
+#endif /* _LINUX_TLS_H */
diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h
new file mode 100644
index 0000000..e670013
--- /dev/null
+++ b/include/uapi/linux/types.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_TYPES_H
+#define _LINUX_TYPES_H
+
+#include <asm/types.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/posix_types.h>
+
+#ifdef __SIZEOF_INT128__
+typedef __signed__ __int128 __s128 __attribute__((aligned(16)));
+typedef unsigned __int128 __u128 __attribute__((aligned(16)));
+#endif
+
+/*
+ * Below are truly Linux-specific types that should never collide with
+ * any application/library that wants linux/types.h.
+ */
+
+/* sparse defines __CHECKER__; see Documentation/dev-tools/sparse.rst */
+#ifdef __CHECKER__
+#define __bitwise __attribute__((bitwise))
+#else
+#define __bitwise
+#endif
+
+/* The kernel doesn't use this legacy form, but user space does */
+#define __bitwise__ __bitwise
+
+typedef __u16 __bitwise __le16;
+typedef __u16 __bitwise __be16;
+typedef __u32 __bitwise __le32;
+typedef __u32 __bitwise __be32;
+typedef __u64 __bitwise __le64;
+typedef __u64 __bitwise __be64;
+
+typedef __u16 __bitwise __sum16;
+typedef __u32 __bitwise __wsum;
+
+/*
+ * aligned_u64 should be used in defining kernel<->userspace ABIs to avoid
+ * common 32/64-bit compat problems.
+ * 64-bit values align to 4-byte boundaries on x86_32 (and possibly other
+ * architectures) and to 8-byte boundaries on 64-bit architectures. The new
+ * aligned_64 type enforces 8-byte alignment so that structs containing
+ * aligned_64 values have the same alignment on 32-bit and 64-bit architectures.
+ * No conversions are necessary between 32-bit user-space and a 64-bit kernel.
+ */
+#define __aligned_u64 __u64 __attribute__((aligned(8)))
+#define __aligned_be64 __be64 __attribute__((aligned(8)))
+#define __aligned_le64 __le64 __attribute__((aligned(8)))
+
+typedef unsigned __bitwise __poll_t;
+
+#endif /* __ASSEMBLY__ */
+#endif /* _LINUX_TYPES_H */
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
new file mode 100644
index 0000000..d0a7223
--- /dev/null
+++ b/include/uapi/linux/udp.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * Definitions for the UDP protocol.
+ *
+ * Version: @(#)udp.h 1.0.2 04/28/93
+ *
+ * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_UDP_H
+#define _LINUX_UDP_H
+
+#include <linux/types.h>
+
+struct udphdr {
+ __be16 source;
+ __be16 dest;
+ __be16 len;
+ __sum16 check;
+};
+
+/* UDP socket options */
+#define UDP_CORK 1 /* Never send partially complete segments */
+#define UDP_ENCAP 100 /* Set the socket to accept encapsulated packets */
+#define UDP_NO_CHECK6_TX 101 /* Disable sending checksum for UDP6X */
+#define UDP_NO_CHECK6_RX 102 /* Disable accpeting checksum for UDP6 */
+#define UDP_SEGMENT 103 /* Set GSO segmentation size */
+#define UDP_GRO 104 /* This socket can receive UDP GRO packets */
+
+/* UDP encapsulation types */
+#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
+#define UDP_ENCAP_ESPINUDP 2 /* draft-ietf-ipsec-udp-encaps-06 */
+#define UDP_ENCAP_L2TPINUDP 3 /* rfc2661 */
+#define UDP_ENCAP_GTP0 4 /* GSM TS 09.60 */
+#define UDP_ENCAP_GTP1U 5 /* 3GPP TS 29.060 */
+#define UDP_ENCAP_RXRPC 6
+#define TCP_ENCAP_ESPINTCP 7 /* Yikes, this is really xfrm encap types. */
+
+#endif /* _LINUX_UDP_H */
diff --git a/include/uapi/linux/unix_diag.h b/include/uapi/linux/unix_diag.h
new file mode 100644
index 0000000..a198857
--- /dev/null
+++ b/include/uapi/linux/unix_diag.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __UNIX_DIAG_H__
+#define __UNIX_DIAG_H__
+
+#include <linux/types.h>
+
+struct unix_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u16 pad;
+ __u32 udiag_states;
+ __u32 udiag_ino;
+ __u32 udiag_show;
+ __u32 udiag_cookie[2];
+};
+
+#define UDIAG_SHOW_NAME 0x00000001 /* show name (not path) */
+#define UDIAG_SHOW_VFS 0x00000002 /* show VFS inode info */
+#define UDIAG_SHOW_PEER 0x00000004 /* show peer socket info */
+#define UDIAG_SHOW_ICONS 0x00000008 /* show pending connections */
+#define UDIAG_SHOW_RQLEN 0x00000010 /* show skb receive queue len */
+#define UDIAG_SHOW_MEMINFO 0x00000020 /* show memory info of a socket */
+#define UDIAG_SHOW_UID 0x00000040 /* show socket's UID */
+
+struct unix_diag_msg {
+ __u8 udiag_family;
+ __u8 udiag_type;
+ __u8 udiag_state;
+ __u8 pad;
+
+ __u32 udiag_ino;
+ __u32 udiag_cookie[2];
+};
+
+enum {
+ /* UNIX_DIAG_NONE, standard nl API requires this attribute! */
+ UNIX_DIAG_NAME,
+ UNIX_DIAG_VFS,
+ UNIX_DIAG_PEER,
+ UNIX_DIAG_ICONS,
+ UNIX_DIAG_RQLEN,
+ UNIX_DIAG_MEMINFO,
+ UNIX_DIAG_SHUTDOWN,
+ UNIX_DIAG_UID,
+
+ __UNIX_DIAG_MAX,
+};
+
+#define UNIX_DIAG_MAX (__UNIX_DIAG_MAX - 1)
+
+struct unix_diag_vfs {
+ __u32 udiag_vfs_ino;
+ __u32 udiag_vfs_dev;
+};
+
+struct unix_diag_rqlen {
+ __u32 udiag_rqueue;
+ __u32 udiag_wqueue;
+};
+
+#endif
diff --git a/include/uapi/linux/veth.h b/include/uapi/linux/veth.h
new file mode 100644
index 0000000..52b58e5
--- /dev/null
+++ b/include/uapi/linux/veth.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __NET_VETH_H_
+#define __NET_VETH_H_
+
+enum {
+ VETH_INFO_UNSPEC,
+ VETH_INFO_PEER,
+
+ __VETH_INFO_MAX
+#define VETH_INFO_MAX (__VETH_INFO_MAX - 1)
+};
+
+#endif
diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
new file mode 100644
index 0000000..3bf80a8
--- /dev/null
+++ b/include/uapi/linux/virtio_config.h
@@ -0,0 +1,121 @@
+#ifndef _LINUX_VIRTIO_CONFIG_H
+#define _LINUX_VIRTIO_CONFIG_H
+/* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
+ * anyone can use the definitions to implement compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
+
+/* Virtio devices use a standardized configuration space to define their
+ * features and pass configuration information, but each implementation can
+ * store and access that space differently. */
+#include <linux/types.h>
+
+/* Status byte for guest to report progress, and synchronize features. */
+/* We have seen device and processed generic fields (VIRTIO_CONFIG_F_VIRTIO) */
+#define VIRTIO_CONFIG_S_ACKNOWLEDGE 1
+/* We have found a driver for the device. */
+#define VIRTIO_CONFIG_S_DRIVER 2
+/* Driver has used its parts of the config, and is happy */
+#define VIRTIO_CONFIG_S_DRIVER_OK 4
+/* Driver has finished configuring features */
+#define VIRTIO_CONFIG_S_FEATURES_OK 8
+/* Device entered invalid state, driver must reset it */
+#define VIRTIO_CONFIG_S_NEEDS_RESET 0x40
+/* We've given up on this device. */
+#define VIRTIO_CONFIG_S_FAILED 0x80
+
+/*
+ * Virtio feature bits VIRTIO_TRANSPORT_F_START through
+ * VIRTIO_TRANSPORT_F_END are reserved for the transport
+ * being used (e.g. virtio_ring, virtio_pci etc.), the
+ * rest are per-device feature bits.
+ */
+#define VIRTIO_TRANSPORT_F_START 28
+#define VIRTIO_TRANSPORT_F_END 42
+
+#ifndef VIRTIO_CONFIG_NO_LEGACY
+/* Do we get callbacks when the ring is completely used, even if we've
+ * suppressed them? */
+#define VIRTIO_F_NOTIFY_ON_EMPTY 24
+
+/* Can the device handle any descriptor layout? */
+#define VIRTIO_F_ANY_LAYOUT 27
+#endif /* VIRTIO_CONFIG_NO_LEGACY */
+
+/* v1.0 compliant. */
+#define VIRTIO_F_VERSION_1 32
+
+/*
+ * If clear - device has the platform DMA (e.g. IOMMU) bypass quirk feature.
+ * If set - use platform DMA tools to access the memory.
+ *
+ * Note the reverse polarity (compared to most other features),
+ * this is for compatibility with legacy systems.
+ */
+#define VIRTIO_F_ACCESS_PLATFORM 33
+/* Legacy name for VIRTIO_F_ACCESS_PLATFORM (for compatibility with old userspace) */
+#define VIRTIO_F_IOMMU_PLATFORM VIRTIO_F_ACCESS_PLATFORM
+
+/* This feature indicates support for the packed virtqueue layout. */
+#define VIRTIO_F_RING_PACKED 34
+
+/*
+ * Inorder feature indicates that all buffers are used by the device
+ * in the same order in which they have been made available.
+ */
+#define VIRTIO_F_IN_ORDER 35
+
+/*
+ * This feature indicates that memory accesses by the driver and the
+ * device are ordered in a way described by the platform.
+ */
+#define VIRTIO_F_ORDER_PLATFORM 36
+
+/*
+ * Does the device support Single Root I/O Virtualization?
+ */
+#define VIRTIO_F_SR_IOV 37
+
+/*
+ * This feature indicates that the driver passes extra data (besides
+ * identifying the virtqueue) in its device notifications.
+ */
+#define VIRTIO_F_NOTIFICATION_DATA 38
+
+/* This feature indicates that the driver uses the data provided by the device
+ * as a virtqueue identifier in available buffer notifications.
+ */
+#define VIRTIO_F_NOTIF_CONFIG_DATA 39
+
+/*
+ * This feature indicates that the driver can reset a queue individually.
+ */
+#define VIRTIO_F_RING_RESET 40
+
+/*
+ * This feature indicates that the device support administration virtqueues.
+ */
+#define VIRTIO_F_ADMIN_VQ 41
+
+#endif /* _LINUX_VIRTIO_CONFIG_H */
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
new file mode 100644
index 0000000..7aa2eb7
--- /dev/null
+++ b/include/uapi/linux/virtio_ids.h
@@ -0,0 +1,84 @@
+#ifndef _LINUX_VIRTIO_IDS_H
+#define _LINUX_VIRTIO_IDS_H
+/*
+ * Virtio IDs
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
+
+#define VIRTIO_ID_NET 1 /* virtio net */
+#define VIRTIO_ID_BLOCK 2 /* virtio block */
+#define VIRTIO_ID_CONSOLE 3 /* virtio console */
+#define VIRTIO_ID_RNG 4 /* virtio rng */
+#define VIRTIO_ID_BALLOON 5 /* virtio balloon */
+#define VIRTIO_ID_IOMEM 6 /* virtio ioMemory */
+#define VIRTIO_ID_RPMSG 7 /* virtio remote processor messaging */
+#define VIRTIO_ID_SCSI 8 /* virtio scsi */
+#define VIRTIO_ID_9P 9 /* 9p virtio console */
+#define VIRTIO_ID_MAC80211_WLAN 10 /* virtio WLAN MAC */
+#define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */
+#define VIRTIO_ID_CAIF 12 /* Virtio caif */
+#define VIRTIO_ID_MEMORY_BALLOON 13 /* virtio memory balloon */
+#define VIRTIO_ID_GPU 16 /* virtio GPU */
+#define VIRTIO_ID_CLOCK 17 /* virtio clock/timer */
+#define VIRTIO_ID_INPUT 18 /* virtio input */
+#define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */
+#define VIRTIO_ID_CRYPTO 20 /* virtio crypto */
+#define VIRTIO_ID_SIGNAL_DIST 21 /* virtio signal distribution device */
+#define VIRTIO_ID_PSTORE 22 /* virtio pstore device */
+#define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */
+#define VIRTIO_ID_MEM 24 /* virtio mem */
+#define VIRTIO_ID_SOUND 25 /* virtio sound */
+#define VIRTIO_ID_FS 26 /* virtio filesystem */
+#define VIRTIO_ID_PMEM 27 /* virtio pmem */
+#define VIRTIO_ID_RPMB 28 /* virtio rpmb */
+#define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */
+#define VIRTIO_ID_VIDEO_ENCODER 30 /* virtio video encoder */
+#define VIRTIO_ID_VIDEO_DECODER 31 /* virtio video decoder */
+#define VIRTIO_ID_SCMI 32 /* virtio SCMI */
+#define VIRTIO_ID_NITRO_SEC_MOD 33 /* virtio nitro secure module*/
+#define VIRTIO_ID_I2C_ADAPTER 34 /* virtio i2c adapter */
+#define VIRTIO_ID_WATCHDOG 35 /* virtio watchdog */
+#define VIRTIO_ID_CAN 36 /* virtio can */
+#define VIRTIO_ID_DMABUF 37 /* virtio dmabuf */
+#define VIRTIO_ID_PARAM_SERV 38 /* virtio parameter server */
+#define VIRTIO_ID_AUDIO_POLICY 39 /* virtio audio policy */
+#define VIRTIO_ID_BT 40 /* virtio bluetooth */
+#define VIRTIO_ID_GPIO 41 /* virtio gpio */
+
+/*
+ * Virtio Transitional IDs
+ */
+
+#define VIRTIO_TRANS_ID_NET 0x1000 /* transitional virtio net */
+#define VIRTIO_TRANS_ID_BLOCK 0x1001 /* transitional virtio block */
+#define VIRTIO_TRANS_ID_BALLOON 0x1002 /* transitional virtio balloon */
+#define VIRTIO_TRANS_ID_CONSOLE 0x1003 /* transitional virtio console */
+#define VIRTIO_TRANS_ID_SCSI 0x1004 /* transitional virtio SCSI */
+#define VIRTIO_TRANS_ID_RNG 0x1005 /* transitional virtio rng */
+#define VIRTIO_TRANS_ID_9P 0x1009 /* transitional virtio 9p console */
+
+#endif /* _LINUX_VIRTIO_IDS_H */
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
new file mode 100644
index 0000000..5775077
--- /dev/null
+++ b/include/uapi/linux/virtio_net.h
@@ -0,0 +1,409 @@
+#ifndef _LINUX_VIRTIO_NET_H
+#define _LINUX_VIRTIO_NET_H
+/* This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
+#include <linux/types.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_types.h>
+#include <linux/if_ether.h>
+
+/* The feature bitmap for virtio net */
+#define VIRTIO_NET_F_CSUM 0 /* Host handles pkts w/ partial csum */
+#define VIRTIO_NET_F_GUEST_CSUM 1 /* Guest handles pkts w/ partial csum */
+#define VIRTIO_NET_F_CTRL_GUEST_OFFLOADS 2 /* Dynamic offload configuration. */
+#define VIRTIO_NET_F_MTU 3 /* Initial MTU advice */
+#define VIRTIO_NET_F_MAC 5 /* Host has given MAC address. */
+#define VIRTIO_NET_F_GUEST_TSO4 7 /* Guest can handle TSOv4 in. */
+#define VIRTIO_NET_F_GUEST_TSO6 8 /* Guest can handle TSOv6 in. */
+#define VIRTIO_NET_F_GUEST_ECN 9 /* Guest can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_GUEST_UFO 10 /* Guest can handle UFO in. */
+#define VIRTIO_NET_F_HOST_TSO4 11 /* Host can handle TSOv4 in. */
+#define VIRTIO_NET_F_HOST_TSO6 12 /* Host can handle TSOv6 in. */
+#define VIRTIO_NET_F_HOST_ECN 13 /* Host can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_HOST_UFO 14 /* Host can handle UFO in. */
+#define VIRTIO_NET_F_MRG_RXBUF 15 /* Host can merge receive buffers. */
+#define VIRTIO_NET_F_STATUS 16 /* virtio_net_config.status available */
+#define VIRTIO_NET_F_CTRL_VQ 17 /* Control channel available */
+#define VIRTIO_NET_F_CTRL_RX 18 /* Control channel RX mode support */
+#define VIRTIO_NET_F_CTRL_VLAN 19 /* Control channel VLAN filtering */
+#define VIRTIO_NET_F_CTRL_RX_EXTRA 20 /* Extra RX mode control support */
+#define VIRTIO_NET_F_GUEST_ANNOUNCE 21 /* Guest can announce device on the
+ * network */
+#define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow
+ * Steering */
+#define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */
+#define VIRTIO_NET_F_VQ_NOTF_COAL 52 /* Device supports virtqueue notification coalescing */
+#define VIRTIO_NET_F_NOTF_COAL 53 /* Device supports notifications coalescing */
+#define VIRTIO_NET_F_GUEST_USO4 54 /* Guest can handle USOv4 in. */
+#define VIRTIO_NET_F_GUEST_USO6 55 /* Guest can handle USOv6 in. */
+#define VIRTIO_NET_F_HOST_USO 56 /* Host can handle USO in. */
+#define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */
+#define VIRTIO_NET_F_GUEST_HDRLEN 59 /* Guest provides the exact hdr_len value. */
+#define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */
+#define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */
+#define VIRTIO_NET_F_STANDBY 62 /* Act as standby for another device
+ * with the same MAC.
+ */
+#define VIRTIO_NET_F_SPEED_DUPLEX 63 /* Device set linkspeed and duplex */
+
+#ifndef VIRTIO_NET_NO_LEGACY
+#define VIRTIO_NET_F_GSO 6 /* Host handles pkts w/ any GSO type */
+#endif /* VIRTIO_NET_NO_LEGACY */
+
+#define VIRTIO_NET_S_LINK_UP 1 /* Link is up */
+#define VIRTIO_NET_S_ANNOUNCE 2 /* Announcement is needed */
+
+/* supported/enabled hash types */
+#define VIRTIO_NET_RSS_HASH_TYPE_IPv4 (1 << 0)
+#define VIRTIO_NET_RSS_HASH_TYPE_TCPv4 (1 << 1)
+#define VIRTIO_NET_RSS_HASH_TYPE_UDPv4 (1 << 2)
+#define VIRTIO_NET_RSS_HASH_TYPE_IPv6 (1 << 3)
+#define VIRTIO_NET_RSS_HASH_TYPE_TCPv6 (1 << 4)
+#define VIRTIO_NET_RSS_HASH_TYPE_UDPv6 (1 << 5)
+#define VIRTIO_NET_RSS_HASH_TYPE_IP_EX (1 << 6)
+#define VIRTIO_NET_RSS_HASH_TYPE_TCP_EX (1 << 7)
+#define VIRTIO_NET_RSS_HASH_TYPE_UDP_EX (1 << 8)
+
+struct virtio_net_config {
+ /* The config defining mac address (if VIRTIO_NET_F_MAC) */
+ __u8 mac[ETH_ALEN];
+ /* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
+ __virtio16 status;
+ /* Maximum number of each of transmit and receive queues;
+ * see VIRTIO_NET_F_MQ and VIRTIO_NET_CTRL_MQ.
+ * Legal values are between 1 and 0x8000
+ */
+ __virtio16 max_virtqueue_pairs;
+ /* Default maximum transmit unit advice */
+ __virtio16 mtu;
+ /*
+ * speed, in units of 1Mb. All values 0 to INT_MAX are legal.
+ * Any other value stands for unknown.
+ */
+ __le32 speed;
+ /*
+ * 0x00 - half duplex
+ * 0x01 - full duplex
+ * Any other value stands for unknown.
+ */
+ __u8 duplex;
+ /* maximum size of RSS key */
+ __u8 rss_max_key_size;
+ /* maximum number of indirection table entries */
+ __le16 rss_max_indirection_table_length;
+ /* bitmask of supported VIRTIO_NET_RSS_HASH_ types */
+ __le32 supported_hash_types;
+} __attribute__((packed));
+
+/*
+ * This header comes first in the scatter-gather list. If you don't
+ * specify GSO or CSUM features, you can simply ignore the header.
+ *
+ * This is bitwise-equivalent to the legacy struct virtio_net_hdr_mrg_rxbuf,
+ * only flattened.
+ */
+struct virtio_net_hdr_v1 {
+#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 /* Use csum_start, csum_offset */
+#define VIRTIO_NET_HDR_F_DATA_VALID 2 /* Csum is valid */
+#define VIRTIO_NET_HDR_F_RSC_INFO 4 /* rsc info in csum_ fields */
+ __u8 flags;
+#define VIRTIO_NET_HDR_GSO_NONE 0 /* Not a GSO frame */
+#define VIRTIO_NET_HDR_GSO_TCPV4 1 /* GSO frame, IPv4 TCP (TSO) */
+#define VIRTIO_NET_HDR_GSO_UDP 3 /* GSO frame, IPv4 UDP (UFO) */
+#define VIRTIO_NET_HDR_GSO_TCPV6 4 /* GSO frame, IPv6 TCP */
+#define VIRTIO_NET_HDR_GSO_UDP_L4 5 /* GSO frame, IPv4& IPv6 UDP (USO) */
+#define VIRTIO_NET_HDR_GSO_ECN 0x80 /* TCP has ECN set */
+ __u8 gso_type;
+ __virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */
+ __virtio16 gso_size; /* Bytes to append to hdr_len per frame */
+ union {
+ struct {
+ __virtio16 csum_start;
+ __virtio16 csum_offset;
+ };
+ /* Checksum calculation */
+ struct {
+ /* Position to start checksumming from */
+ __virtio16 start;
+ /* Offset after that to place checksum */
+ __virtio16 offset;
+ } csum;
+ /* Receive Segment Coalescing */
+ struct {
+ /* Number of coalesced segments */
+ __le16 segments;
+ /* Number of duplicated acks */
+ __le16 dup_acks;
+ } rsc;
+ };
+ __virtio16 num_buffers; /* Number of merged rx buffers */
+};
+
+struct virtio_net_hdr_v1_hash {
+ struct virtio_net_hdr_v1 hdr;
+ __le32 hash_value;
+#define VIRTIO_NET_HASH_REPORT_NONE 0
+#define VIRTIO_NET_HASH_REPORT_IPv4 1
+#define VIRTIO_NET_HASH_REPORT_TCPv4 2
+#define VIRTIO_NET_HASH_REPORT_UDPv4 3
+#define VIRTIO_NET_HASH_REPORT_IPv6 4
+#define VIRTIO_NET_HASH_REPORT_TCPv6 5
+#define VIRTIO_NET_HASH_REPORT_UDPv6 6
+#define VIRTIO_NET_HASH_REPORT_IPv6_EX 7
+#define VIRTIO_NET_HASH_REPORT_TCPv6_EX 8
+#define VIRTIO_NET_HASH_REPORT_UDPv6_EX 9
+ __le16 hash_report;
+ __le16 padding;
+};
+
+#ifndef VIRTIO_NET_NO_LEGACY
+/* This header comes first in the scatter-gather list.
+ * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated, it must
+ * be the first element of the scatter-gather list. If you don't
+ * specify GSO or CSUM features, you can simply ignore the header. */
+struct virtio_net_hdr {
+ /* See VIRTIO_NET_HDR_F_* */
+ __u8 flags;
+ /* See VIRTIO_NET_HDR_GSO_* */
+ __u8 gso_type;
+ __virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */
+ __virtio16 gso_size; /* Bytes to append to hdr_len per frame */
+ __virtio16 csum_start; /* Position to start checksumming from */
+ __virtio16 csum_offset; /* Offset after that to place checksum */
+};
+
+/* This is the version of the header to use when the MRG_RXBUF
+ * feature has been negotiated. */
+struct virtio_net_hdr_mrg_rxbuf {
+ struct virtio_net_hdr hdr;
+ __virtio16 num_buffers; /* Number of merged rx buffers */
+};
+#endif /* ...VIRTIO_NET_NO_LEGACY */
+
+/*
+ * Control virtqueue data structures
+ *
+ * The control virtqueue expects a header in the first sg entry
+ * and an ack/status response in the last entry. Data for the
+ * command goes in between.
+ */
+struct virtio_net_ctrl_hdr {
+ __u8 class;
+ __u8 cmd;
+} __attribute__((packed));
+
+typedef __u8 virtio_net_ctrl_ack;
+
+#define VIRTIO_NET_OK 0
+#define VIRTIO_NET_ERR 1
+
+/*
+ * Control the RX mode, ie. promisucous, allmulti, etc...
+ * All commands require an "out" sg entry containing a 1 byte
+ * state value, zero = disable, non-zero = enable. Commands
+ * 0 and 1 are supported with the VIRTIO_NET_F_CTRL_RX feature.
+ * Commands 2-5 are added with VIRTIO_NET_F_CTRL_RX_EXTRA.
+ */
+#define VIRTIO_NET_CTRL_RX 0
+ #define VIRTIO_NET_CTRL_RX_PROMISC 0
+ #define VIRTIO_NET_CTRL_RX_ALLMULTI 1
+ #define VIRTIO_NET_CTRL_RX_ALLUNI 2
+ #define VIRTIO_NET_CTRL_RX_NOMULTI 3
+ #define VIRTIO_NET_CTRL_RX_NOUNI 4
+ #define VIRTIO_NET_CTRL_RX_NOBCAST 5
+
+/*
+ * Control the MAC
+ *
+ * The MAC filter table is managed by the hypervisor, the guest should
+ * assume the size is infinite. Filtering should be considered
+ * non-perfect, ie. based on hypervisor resources, the guest may
+ * received packets from sources not specified in the filter list.
+ *
+ * In addition to the class/cmd header, the TABLE_SET command requires
+ * two out scatterlists. Each contains a 4 byte count of entries followed
+ * by a concatenated byte stream of the ETH_ALEN MAC addresses. The
+ * first sg list contains unicast addresses, the second is for multicast.
+ * This functionality is present if the VIRTIO_NET_F_CTRL_RX feature
+ * is available.
+ *
+ * The ADDR_SET command requests one out scatterlist, it contains a
+ * 6 bytes MAC address. This functionality is present if the
+ * VIRTIO_NET_F_CTRL_MAC_ADDR feature is available.
+ */
+struct virtio_net_ctrl_mac {
+ __virtio32 entries;
+ __u8 macs[][ETH_ALEN];
+} __attribute__((packed));
+
+#define VIRTIO_NET_CTRL_MAC 1
+ #define VIRTIO_NET_CTRL_MAC_TABLE_SET 0
+ #define VIRTIO_NET_CTRL_MAC_ADDR_SET 1
+
+/*
+ * Control VLAN filtering
+ *
+ * The VLAN filter table is controlled via a simple ADD/DEL interface.
+ * VLAN IDs not added may be filterd by the hypervisor. Del is the
+ * opposite of add. Both commands expect an out entry containing a 2
+ * byte VLAN ID. VLAN filterting is available with the
+ * VIRTIO_NET_F_CTRL_VLAN feature bit.
+ */
+#define VIRTIO_NET_CTRL_VLAN 2
+ #define VIRTIO_NET_CTRL_VLAN_ADD 0
+ #define VIRTIO_NET_CTRL_VLAN_DEL 1
+
+/*
+ * Control link announce acknowledgement
+ *
+ * The command VIRTIO_NET_CTRL_ANNOUNCE_ACK is used to indicate that
+ * driver has recevied the notification; device would clear the
+ * VIRTIO_NET_S_ANNOUNCE bit in the status field after it receives
+ * this command.
+ */
+#define VIRTIO_NET_CTRL_ANNOUNCE 3
+ #define VIRTIO_NET_CTRL_ANNOUNCE_ACK 0
+
+/*
+ * Control Receive Flow Steering
+ */
+#define VIRTIO_NET_CTRL_MQ 4
+/*
+ * The command VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET
+ * enables Receive Flow Steering, specifying the number of the transmit and
+ * receive queues that will be used. After the command is consumed and acked by
+ * the device, the device will not steer new packets on receive virtqueues
+ * other than specified nor read from transmit virtqueues other than specified.
+ * Accordingly, driver should not transmit new packets on virtqueues other than
+ * specified.
+ */
+struct virtio_net_ctrl_mq {
+ __virtio16 virtqueue_pairs;
+};
+
+ #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET 0
+ #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN 1
+ #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX 0x8000
+
+/*
+ * The command VIRTIO_NET_CTRL_MQ_RSS_CONFIG has the same effect as
+ * VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET does and additionally configures
+ * the receive steering to use a hash calculated for incoming packet
+ * to decide on receive virtqueue to place the packet. The command
+ * also provides parameters to calculate a hash and receive virtqueue.
+ */
+struct virtio_net_rss_config {
+ __le32 hash_types;
+ __le16 indirection_table_mask;
+ __le16 unclassified_queue;
+ __le16 indirection_table[1/* + indirection_table_mask */];
+ __le16 max_tx_vq;
+ __u8 hash_key_length;
+ __u8 hash_key_data[/* hash_key_length */];
+};
+
+ #define VIRTIO_NET_CTRL_MQ_RSS_CONFIG 1
+
+/*
+ * The command VIRTIO_NET_CTRL_MQ_HASH_CONFIG requests the device
+ * to include in the virtio header of the packet the value of the
+ * calculated hash and the report type of hash. It also provides
+ * parameters for hash calculation. The command requires feature
+ * VIRTIO_NET_F_HASH_REPORT to be negotiated to extend the
+ * layout of virtio header as defined in virtio_net_hdr_v1_hash.
+ */
+struct virtio_net_hash_config {
+ __le32 hash_types;
+ /* for compatibility with virtio_net_rss_config */
+ __le16 reserved[4];
+ __u8 hash_key_length;
+ __u8 hash_key_data[/* hash_key_length */];
+};
+
+ #define VIRTIO_NET_CTRL_MQ_HASH_CONFIG 2
+
+/*
+ * Control network offloads
+ *
+ * Reconfigures the network offloads that Guest can handle.
+ *
+ * Available with the VIRTIO_NET_F_CTRL_GUEST_OFFLOADS feature bit.
+ *
+ * Command data format matches the feature bit mask exactly.
+ *
+ * See VIRTIO_NET_F_GUEST_* for the list of offloads
+ * that can be enabled/disabled.
+ */
+#define VIRTIO_NET_CTRL_GUEST_OFFLOADS 5
+#define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET 0
+
+/*
+ * Control notifications coalescing.
+ *
+ * Request the device to change the notifications coalescing parameters.
+ *
+ * Available with the VIRTIO_NET_F_NOTF_COAL feature bit.
+ */
+#define VIRTIO_NET_CTRL_NOTF_COAL 6
+/*
+ * Set the tx-usecs/tx-max-packets parameters.
+ */
+struct virtio_net_ctrl_coal_tx {
+ /* Maximum number of packets to send before a TX notification */
+ __le32 tx_max_packets;
+ /* Maximum number of usecs to delay a TX notification */
+ __le32 tx_usecs;
+};
+
+#define VIRTIO_NET_CTRL_NOTF_COAL_TX_SET 0
+
+/*
+ * Set the rx-usecs/rx-max-packets parameters.
+ */
+struct virtio_net_ctrl_coal_rx {
+ /* Maximum number of packets to receive before a RX notification */
+ __le32 rx_max_packets;
+ /* Maximum number of usecs to delay a RX notification */
+ __le32 rx_usecs;
+};
+
+#define VIRTIO_NET_CTRL_NOTF_COAL_RX_SET 1
+#define VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET 2
+#define VIRTIO_NET_CTRL_NOTF_COAL_VQ_GET 3
+
+struct virtio_net_ctrl_coal {
+ __le32 max_packets;
+ __le32 max_usecs;
+};
+
+struct virtio_net_ctrl_coal_vq {
+ __le16 vqn;
+ __le16 reserved;
+ struct virtio_net_ctrl_coal coal;
+};
+
+#endif /* _LINUX_VIRTIO_NET_H */
diff --git a/include/uapi/linux/virtio_types.h b/include/uapi/linux/virtio_types.h
new file mode 100644
index 0000000..4eac2e1
--- /dev/null
+++ b/include/uapi/linux/virtio_types.h
@@ -0,0 +1,46 @@
+#ifndef _LINUX_VIRTIO_TYPES_H
+#define _LINUX_VIRTIO_TYPES_H
+/* Type definitions for virtio implementations.
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * Copyright (C) 2014 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ */
+#include <linux/types.h>
+
+/*
+ * __virtio{16,32,64} have the following meaning:
+ * - __u{16,32,64} for virtio devices in legacy mode, accessed in native endian
+ * - __le{16,32,64} for standard-compliant virtio devices
+ */
+
+typedef __u16 __bitwise __virtio16;
+typedef __u32 __bitwise __virtio32;
+typedef __u64 __bitwise __virtio64;
+
+#endif /* _LINUX_VIRTIO_TYPES_H */
diff --git a/include/uapi/linux/vm_sockets_diag.h b/include/uapi/linux/vm_sockets_diag.h
new file mode 100644
index 0000000..6da42f9
--- /dev/null
+++ b/include/uapi/linux/vm_sockets_diag.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* AF_VSOCK sock_diag(7) interface for querying open sockets */
+
+#ifndef __VM_SOCKETS_DIAG_H__
+#define __VM_SOCKETS_DIAG_H__
+
+#include <linux/types.h>
+
+/* Request */
+struct vsock_diag_req {
+ __u8 sdiag_family; /* must be AF_VSOCK */
+ __u8 sdiag_protocol; /* must be 0 */
+ __u16 pad; /* must be 0 */
+ __u32 vdiag_states; /* query bitmap (e.g. 1 << TCP_LISTEN) */
+ __u32 vdiag_ino; /* must be 0 (reserved) */
+ __u32 vdiag_show; /* must be 0 (reserved) */
+ __u32 vdiag_cookie[2];
+};
+
+/* Response */
+struct vsock_diag_msg {
+ __u8 vdiag_family; /* AF_VSOCK */
+ __u8 vdiag_type; /* SOCK_STREAM or SOCK_DGRAM */
+ __u8 vdiag_state; /* sk_state (e.g. TCP_LISTEN) */
+ __u8 vdiag_shutdown; /* local RCV_SHUTDOWN | SEND_SHUTDOWN */
+ __u32 vdiag_src_cid;
+ __u32 vdiag_src_port;
+ __u32 vdiag_dst_cid;
+ __u32 vdiag_dst_port;
+ __u32 vdiag_ino;
+ __u32 vdiag_cookie[2];
+};
+
+#endif /* __VM_SOCKETS_DIAG_H__ */
diff --git a/include/uapi/linux/wwan.h b/include/uapi/linux/wwan.h
new file mode 100644
index 0000000..2c0ccb4
--- /dev/null
+++ b/include/uapi/linux/wwan.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2021 Intel Corporation.
+ */
+#ifndef _WWAN_H_
+#define _WWAN_H_
+
+enum {
+ IFLA_WWAN_UNSPEC,
+ IFLA_WWAN_LINK_ID, /* u32 */
+
+ __IFLA_WWAN_MAX
+};
+#define IFLA_WWAN_MAX (__IFLA_WWAN_MAX - 1)
+
+#endif /* _WWAN_H_ */
diff --git a/include/uapi/linux/xdp_diag.h b/include/uapi/linux/xdp_diag.h
new file mode 100644
index 0000000..66b9973
--- /dev/null
+++ b/include/uapi/linux/xdp_diag.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * xdp_diag: interface for query/monitor XDP sockets
+ * Copyright(c) 2019 Intel Corporation.
+ */
+
+#ifndef _LINUX_XDP_DIAG_H
+#define _LINUX_XDP_DIAG_H
+
+#include <linux/types.h>
+
+struct xdp_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u16 pad;
+ __u32 xdiag_ino;
+ __u32 xdiag_show;
+ __u32 xdiag_cookie[2];
+};
+
+struct xdp_diag_msg {
+ __u8 xdiag_family;
+ __u8 xdiag_type;
+ __u16 pad;
+ __u32 xdiag_ino;
+ __u32 xdiag_cookie[2];
+};
+
+#define XDP_SHOW_INFO (1 << 0) /* Basic information */
+#define XDP_SHOW_RING_CFG (1 << 1)
+#define XDP_SHOW_UMEM (1 << 2)
+#define XDP_SHOW_MEMINFO (1 << 3)
+#define XDP_SHOW_STATS (1 << 4)
+
+enum {
+ XDP_DIAG_NONE,
+ XDP_DIAG_INFO,
+ XDP_DIAG_UID,
+ XDP_DIAG_RX_RING,
+ XDP_DIAG_TX_RING,
+ XDP_DIAG_UMEM,
+ XDP_DIAG_UMEM_FILL_RING,
+ XDP_DIAG_UMEM_COMPLETION_RING,
+ XDP_DIAG_MEMINFO,
+ XDP_DIAG_STATS,
+ __XDP_DIAG_MAX,
+};
+
+#define XDP_DIAG_MAX (__XDP_DIAG_MAX - 1)
+
+struct xdp_diag_info {
+ __u32 ifindex;
+ __u32 queue_id;
+};
+
+struct xdp_diag_ring {
+ __u32 entries; /*num descs */
+};
+
+#define XDP_DU_F_ZEROCOPY (1 << 0)
+
+struct xdp_diag_umem {
+ __u64 size;
+ __u32 id;
+ __u32 num_pages;
+ __u32 chunk_size;
+ __u32 headroom;
+ __u32 ifindex;
+ __u32 queue_id;
+ __u32 flags;
+ __u32 refs;
+};
+
+struct xdp_diag_stats {
+ __u64 n_rx_dropped;
+ __u64 n_rx_invalid;
+ __u64 n_rx_full;
+ __u64 n_fill_ring_empty;
+ __u64 n_tx_invalid;
+ __u64 n_tx_ring_empty;
+};
+
+#endif /* _LINUX_XDP_DIAG_H */
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
new file mode 100644
index 0000000..43efaec
--- /dev/null
+++ b/include/uapi/linux/xfrm.h
@@ -0,0 +1,569 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_XFRM_H
+#define _LINUX_XFRM_H
+
+#include <linux/in6.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+
+/* All of the structures in this file may not change size as they are
+ * passed into the kernel from userspace via netlink sockets.
+ */
+
+/* Structure to encapsulate addresses. I do not want to use
+ * "standard" structure. My apologies.
+ */
+typedef union {
+ __be32 a4;
+ __be32 a6[4];
+ struct in6_addr in6;
+} xfrm_address_t;
+
+/* Ident of a specific xfrm_state. It is used on input to lookup
+ * the state by (spi,daddr,ah/esp) or to store information about
+ * spi, protocol and tunnel address on output.
+ */
+struct xfrm_id {
+ xfrm_address_t daddr;
+ __be32 spi;
+ __u8 proto;
+};
+
+struct xfrm_sec_ctx {
+ __u8 ctx_doi;
+ __u8 ctx_alg;
+ __u16 ctx_len;
+ __u32 ctx_sid;
+ char ctx_str[] __counted_by(ctx_len);
+};
+
+/* Security Context Domains of Interpretation */
+#define XFRM_SC_DOI_RESERVED 0
+#define XFRM_SC_DOI_LSM 1
+
+/* Security Context Algorithms */
+#define XFRM_SC_ALG_RESERVED 0
+#define XFRM_SC_ALG_SELINUX 1
+
+/* Selector, used as selector both on policy rules (SPD) and SAs. */
+
+struct xfrm_selector {
+ xfrm_address_t daddr;
+ xfrm_address_t saddr;
+ __be16 dport;
+ __be16 dport_mask;
+ __be16 sport;
+ __be16 sport_mask;
+ __u16 family;
+ __u8 prefixlen_d;
+ __u8 prefixlen_s;
+ __u8 proto;
+ int ifindex;
+ __kernel_uid32_t user;
+};
+
+#define XFRM_INF (~(__u64)0)
+
+struct xfrm_lifetime_cfg {
+ __u64 soft_byte_limit;
+ __u64 hard_byte_limit;
+ __u64 soft_packet_limit;
+ __u64 hard_packet_limit;
+ __u64 soft_add_expires_seconds;
+ __u64 hard_add_expires_seconds;
+ __u64 soft_use_expires_seconds;
+ __u64 hard_use_expires_seconds;
+};
+
+struct xfrm_lifetime_cur {
+ __u64 bytes;
+ __u64 packets;
+ __u64 add_time;
+ __u64 use_time;
+};
+
+struct xfrm_replay_state {
+ __u32 oseq;
+ __u32 seq;
+ __u32 bitmap;
+};
+
+#define XFRMA_REPLAY_ESN_MAX 4096
+
+struct xfrm_replay_state_esn {
+ unsigned int bmp_len;
+ __u32 oseq;
+ __u32 seq;
+ __u32 oseq_hi;
+ __u32 seq_hi;
+ __u32 replay_window;
+ __u32 bmp[];
+};
+
+struct xfrm_algo {
+ char alg_name[64];
+ unsigned int alg_key_len; /* in bits */
+ char alg_key[];
+};
+
+struct xfrm_algo_auth {
+ char alg_name[64];
+ unsigned int alg_key_len; /* in bits */
+ unsigned int alg_trunc_len; /* in bits */
+ char alg_key[];
+};
+
+struct xfrm_algo_aead {
+ char alg_name[64];
+ unsigned int alg_key_len; /* in bits */
+ unsigned int alg_icv_len; /* in bits */
+ char alg_key[];
+};
+
+struct xfrm_stats {
+ __u32 replay_window;
+ __u32 replay;
+ __u32 integrity_failed;
+};
+
+enum {
+ XFRM_POLICY_TYPE_MAIN = 0,
+ XFRM_POLICY_TYPE_SUB = 1,
+ XFRM_POLICY_TYPE_MAX = 2,
+ XFRM_POLICY_TYPE_ANY = 255
+};
+
+enum {
+ XFRM_POLICY_IN = 0,
+ XFRM_POLICY_OUT = 1,
+ XFRM_POLICY_FWD = 2,
+ XFRM_POLICY_MASK = 3,
+ XFRM_POLICY_MAX = 3
+};
+
+enum {
+ XFRM_SHARE_ANY, /* No limitations */
+ XFRM_SHARE_SESSION, /* For this session only */
+ XFRM_SHARE_USER, /* For this user only */
+ XFRM_SHARE_UNIQUE /* Use once */
+};
+
+#define XFRM_MODE_TRANSPORT 0
+#define XFRM_MODE_TUNNEL 1
+#define XFRM_MODE_ROUTEOPTIMIZATION 2
+#define XFRM_MODE_IN_TRIGGER 3
+#define XFRM_MODE_BEET 4
+#define XFRM_MODE_MAX 5
+
+/* Netlink configuration messages. */
+enum {
+ XFRM_MSG_BASE = 0x10,
+
+ XFRM_MSG_NEWSA = 0x10,
+#define XFRM_MSG_NEWSA XFRM_MSG_NEWSA
+ XFRM_MSG_DELSA,
+#define XFRM_MSG_DELSA XFRM_MSG_DELSA
+ XFRM_MSG_GETSA,
+#define XFRM_MSG_GETSA XFRM_MSG_GETSA
+
+ XFRM_MSG_NEWPOLICY,
+#define XFRM_MSG_NEWPOLICY XFRM_MSG_NEWPOLICY
+ XFRM_MSG_DELPOLICY,
+#define XFRM_MSG_DELPOLICY XFRM_MSG_DELPOLICY
+ XFRM_MSG_GETPOLICY,
+#define XFRM_MSG_GETPOLICY XFRM_MSG_GETPOLICY
+
+ XFRM_MSG_ALLOCSPI,
+#define XFRM_MSG_ALLOCSPI XFRM_MSG_ALLOCSPI
+ XFRM_MSG_ACQUIRE,
+#define XFRM_MSG_ACQUIRE XFRM_MSG_ACQUIRE
+ XFRM_MSG_EXPIRE,
+#define XFRM_MSG_EXPIRE XFRM_MSG_EXPIRE
+
+ XFRM_MSG_UPDPOLICY,
+#define XFRM_MSG_UPDPOLICY XFRM_MSG_UPDPOLICY
+ XFRM_MSG_UPDSA,
+#define XFRM_MSG_UPDSA XFRM_MSG_UPDSA
+
+ XFRM_MSG_POLEXPIRE,
+#define XFRM_MSG_POLEXPIRE XFRM_MSG_POLEXPIRE
+
+ XFRM_MSG_FLUSHSA,
+#define XFRM_MSG_FLUSHSA XFRM_MSG_FLUSHSA
+ XFRM_MSG_FLUSHPOLICY,
+#define XFRM_MSG_FLUSHPOLICY XFRM_MSG_FLUSHPOLICY
+
+ XFRM_MSG_NEWAE,
+#define XFRM_MSG_NEWAE XFRM_MSG_NEWAE
+ XFRM_MSG_GETAE,
+#define XFRM_MSG_GETAE XFRM_MSG_GETAE
+
+ XFRM_MSG_REPORT,
+#define XFRM_MSG_REPORT XFRM_MSG_REPORT
+
+ XFRM_MSG_MIGRATE,
+#define XFRM_MSG_MIGRATE XFRM_MSG_MIGRATE
+
+ XFRM_MSG_NEWSADINFO,
+#define XFRM_MSG_NEWSADINFO XFRM_MSG_NEWSADINFO
+ XFRM_MSG_GETSADINFO,
+#define XFRM_MSG_GETSADINFO XFRM_MSG_GETSADINFO
+
+ XFRM_MSG_NEWSPDINFO,
+#define XFRM_MSG_NEWSPDINFO XFRM_MSG_NEWSPDINFO
+ XFRM_MSG_GETSPDINFO,
+#define XFRM_MSG_GETSPDINFO XFRM_MSG_GETSPDINFO
+
+ XFRM_MSG_MAPPING,
+#define XFRM_MSG_MAPPING XFRM_MSG_MAPPING
+
+ XFRM_MSG_SETDEFAULT,
+#define XFRM_MSG_SETDEFAULT XFRM_MSG_SETDEFAULT
+ XFRM_MSG_GETDEFAULT,
+#define XFRM_MSG_GETDEFAULT XFRM_MSG_GETDEFAULT
+ __XFRM_MSG_MAX
+};
+#define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1)
+
+#define XFRM_NR_MSGTYPES (XFRM_MSG_MAX + 1 - XFRM_MSG_BASE)
+
+/*
+ * Generic LSM security context for comunicating to user space
+ * NOTE: Same format as sadb_x_sec_ctx
+ */
+struct xfrm_user_sec_ctx {
+ __u16 len;
+ __u16 exttype;
+ __u8 ctx_alg; /* LSMs: e.g., selinux == 1 */
+ __u8 ctx_doi;
+ __u16 ctx_len;
+};
+
+struct xfrm_user_tmpl {
+ struct xfrm_id id;
+ __u16 family;
+ xfrm_address_t saddr;
+ __u32 reqid;
+ __u8 mode;
+ __u8 share;
+ __u8 optional;
+ __u32 aalgos;
+ __u32 ealgos;
+ __u32 calgos;
+};
+
+struct xfrm_encap_tmpl {
+ __u16 encap_type;
+ __be16 encap_sport;
+ __be16 encap_dport;
+ xfrm_address_t encap_oa;
+};
+
+/* AEVENT flags */
+enum xfrm_ae_ftype_t {
+ XFRM_AE_UNSPEC,
+ XFRM_AE_RTHR=1, /* replay threshold*/
+ XFRM_AE_RVAL=2, /* replay value */
+ XFRM_AE_LVAL=4, /* lifetime value */
+ XFRM_AE_ETHR=8, /* expiry timer threshold */
+ XFRM_AE_CR=16, /* Event cause is replay update */
+ XFRM_AE_CE=32, /* Event cause is timer expiry */
+ XFRM_AE_CU=64, /* Event cause is policy update */
+ __XFRM_AE_MAX
+
+#define XFRM_AE_MAX (__XFRM_AE_MAX - 1)
+};
+
+struct xfrm_userpolicy_type {
+ __u8 type;
+ __u16 reserved1;
+ __u8 reserved2;
+};
+
+/* Netlink message attributes. */
+enum xfrm_attr_type_t {
+ XFRMA_UNSPEC,
+ XFRMA_ALG_AUTH, /* struct xfrm_algo */
+ XFRMA_ALG_CRYPT, /* struct xfrm_algo */
+ XFRMA_ALG_COMP, /* struct xfrm_algo */
+ XFRMA_ENCAP, /* struct xfrm_algo + struct xfrm_encap_tmpl */
+ XFRMA_TMPL, /* 1 or more struct xfrm_user_tmpl */
+ XFRMA_SA, /* struct xfrm_usersa_info */
+ XFRMA_POLICY, /*struct xfrm_userpolicy_info */
+ XFRMA_SEC_CTX, /* struct xfrm_sec_ctx */
+ XFRMA_LTIME_VAL,
+ XFRMA_REPLAY_VAL,
+ XFRMA_REPLAY_THRESH,
+ XFRMA_ETIMER_THRESH,
+ XFRMA_SRCADDR, /* xfrm_address_t */
+ XFRMA_COADDR, /* xfrm_address_t */
+ XFRMA_LASTUSED, /* __u64 */
+ XFRMA_POLICY_TYPE, /* struct xfrm_userpolicy_type */
+ XFRMA_MIGRATE,
+ XFRMA_ALG_AEAD, /* struct xfrm_algo_aead */
+ XFRMA_KMADDRESS, /* struct xfrm_user_kmaddress */
+ XFRMA_ALG_AUTH_TRUNC, /* struct xfrm_algo_auth */
+ XFRMA_MARK, /* struct xfrm_mark */
+ XFRMA_TFCPAD, /* __u32 */
+ XFRMA_REPLAY_ESN_VAL, /* struct xfrm_replay_state_esn */
+ XFRMA_SA_EXTRA_FLAGS, /* __u32 */
+ XFRMA_PROTO, /* __u8 */
+ XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */
+ XFRMA_PAD,
+ XFRMA_OFFLOAD_DEV, /* struct xfrm_user_offload */
+ XFRMA_SET_MARK, /* __u32 */
+ XFRMA_SET_MARK_MASK, /* __u32 */
+ XFRMA_IF_ID, /* __u32 */
+ XFRMA_MTIMER_THRESH, /* __u32 in seconds for input SA */
+ __XFRMA_MAX
+
+#define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */
+#define XFRMA_MAX (__XFRMA_MAX - 1)
+};
+
+struct xfrm_mark {
+ __u32 v; /* value */
+ __u32 m; /* mask */
+};
+
+enum xfrm_sadattr_type_t {
+ XFRMA_SAD_UNSPEC,
+ XFRMA_SAD_CNT,
+ XFRMA_SAD_HINFO,
+ __XFRMA_SAD_MAX
+
+#define XFRMA_SAD_MAX (__XFRMA_SAD_MAX - 1)
+};
+
+struct xfrmu_sadhinfo {
+ __u32 sadhcnt; /* current hash bkts */
+ __u32 sadhmcnt; /* max allowed hash bkts */
+};
+
+enum xfrm_spdattr_type_t {
+ XFRMA_SPD_UNSPEC,
+ XFRMA_SPD_INFO,
+ XFRMA_SPD_HINFO,
+ XFRMA_SPD_IPV4_HTHRESH,
+ XFRMA_SPD_IPV6_HTHRESH,
+ __XFRMA_SPD_MAX
+
+#define XFRMA_SPD_MAX (__XFRMA_SPD_MAX - 1)
+};
+
+struct xfrmu_spdinfo {
+ __u32 incnt;
+ __u32 outcnt;
+ __u32 fwdcnt;
+ __u32 inscnt;
+ __u32 outscnt;
+ __u32 fwdscnt;
+};
+
+struct xfrmu_spdhinfo {
+ __u32 spdhcnt;
+ __u32 spdhmcnt;
+};
+
+struct xfrmu_spdhthresh {
+ __u8 lbits;
+ __u8 rbits;
+};
+
+struct xfrm_usersa_info {
+ struct xfrm_selector sel;
+ struct xfrm_id id;
+ xfrm_address_t saddr;
+ struct xfrm_lifetime_cfg lft;
+ struct xfrm_lifetime_cur curlft;
+ struct xfrm_stats stats;
+ __u32 seq;
+ __u32 reqid;
+ __u16 family;
+ __u8 mode; /* XFRM_MODE_xxx */
+ __u8 replay_window;
+ __u8 flags;
+#define XFRM_STATE_NOECN 1
+#define XFRM_STATE_DECAP_DSCP 2
+#define XFRM_STATE_NOPMTUDISC 4
+#define XFRM_STATE_WILDRECV 8
+#define XFRM_STATE_ICMP 16
+#define XFRM_STATE_AF_UNSPEC 32
+#define XFRM_STATE_ALIGN4 64
+#define XFRM_STATE_ESN 128
+};
+
+#define XFRM_SA_XFLAG_DONT_ENCAP_DSCP 1
+#define XFRM_SA_XFLAG_OSEQ_MAY_WRAP 2
+
+struct xfrm_usersa_id {
+ xfrm_address_t daddr;
+ __be32 spi;
+ __u16 family;
+ __u8 proto;
+};
+
+struct xfrm_aevent_id {
+ struct xfrm_usersa_id sa_id;
+ xfrm_address_t saddr;
+ __u32 flags;
+ __u32 reqid;
+};
+
+struct xfrm_userspi_info {
+ struct xfrm_usersa_info info;
+ __u32 min;
+ __u32 max;
+};
+
+struct xfrm_userpolicy_info {
+ struct xfrm_selector sel;
+ struct xfrm_lifetime_cfg lft;
+ struct xfrm_lifetime_cur curlft;
+ __u32 priority;
+ __u32 index;
+ __u8 dir;
+ __u8 action;
+#define XFRM_POLICY_ALLOW 0
+#define XFRM_POLICY_BLOCK 1
+ __u8 flags;
+#define XFRM_POLICY_LOCALOK 1 /* Allow user to override global policy */
+ /* Automatically expand selector to include matching ICMP payloads. */
+#define XFRM_POLICY_ICMP 2
+ __u8 share;
+};
+
+struct xfrm_userpolicy_id {
+ struct xfrm_selector sel;
+ __u32 index;
+ __u8 dir;
+};
+
+struct xfrm_user_acquire {
+ struct xfrm_id id;
+ xfrm_address_t saddr;
+ struct xfrm_selector sel;
+ struct xfrm_userpolicy_info policy;
+ __u32 aalgos;
+ __u32 ealgos;
+ __u32 calgos;
+ __u32 seq;
+};
+
+struct xfrm_user_expire {
+ struct xfrm_usersa_info state;
+ __u8 hard;
+};
+
+struct xfrm_user_polexpire {
+ struct xfrm_userpolicy_info pol;
+ __u8 hard;
+};
+
+struct xfrm_usersa_flush {
+ __u8 proto;
+};
+
+struct xfrm_user_report {
+ __u8 proto;
+ struct xfrm_selector sel;
+};
+
+/* Used by MIGRATE to pass addresses IKE should use to perform
+ * SA negotiation with the peer */
+struct xfrm_user_kmaddress {
+ xfrm_address_t local;
+ xfrm_address_t remote;
+ __u32 reserved;
+ __u16 family;
+};
+
+struct xfrm_user_migrate {
+ xfrm_address_t old_daddr;
+ xfrm_address_t old_saddr;
+ xfrm_address_t new_daddr;
+ xfrm_address_t new_saddr;
+ __u8 proto;
+ __u8 mode;
+ __u16 reserved;
+ __u32 reqid;
+ __u16 old_family;
+ __u16 new_family;
+};
+
+struct xfrm_user_mapping {
+ struct xfrm_usersa_id id;
+ __u32 reqid;
+ xfrm_address_t old_saddr;
+ xfrm_address_t new_saddr;
+ __be16 old_sport;
+ __be16 new_sport;
+};
+
+struct xfrm_address_filter {
+ xfrm_address_t saddr;
+ xfrm_address_t daddr;
+ __u16 family;
+ __u8 splen;
+ __u8 dplen;
+};
+
+struct xfrm_user_offload {
+ int ifindex;
+ __u8 flags;
+};
+/* This flag was exposed without any kernel code that supports it.
+ * Unfortunately, strongswan has the code that sets this flag,
+ * which makes it impossible to reuse this bit.
+ *
+ * So leave it here to make sure that it won't be reused by mistake.
+ */
+#define XFRM_OFFLOAD_IPV6 1
+#define XFRM_OFFLOAD_INBOUND 2
+/* Two bits above are relevant for state path only, while
+ * offload is used for both policy and state flows.
+ *
+ * In policy offload mode, they are free and can be safely reused.
+ */
+#define XFRM_OFFLOAD_PACKET 4
+
+struct xfrm_userpolicy_default {
+#define XFRM_USERPOLICY_UNSPEC 0
+#define XFRM_USERPOLICY_BLOCK 1
+#define XFRM_USERPOLICY_ACCEPT 2
+ __u8 in;
+ __u8 fwd;
+ __u8 out;
+};
+
+/* backwards compatibility for userspace */
+#define XFRMGRP_ACQUIRE 1
+#define XFRMGRP_EXPIRE 2
+#define XFRMGRP_SA 4
+#define XFRMGRP_POLICY 8
+#define XFRMGRP_REPORT 0x20
+
+enum xfrm_nlgroups {
+ XFRMNLGRP_NONE,
+#define XFRMNLGRP_NONE XFRMNLGRP_NONE
+ XFRMNLGRP_ACQUIRE,
+#define XFRMNLGRP_ACQUIRE XFRMNLGRP_ACQUIRE
+ XFRMNLGRP_EXPIRE,
+#define XFRMNLGRP_EXPIRE XFRMNLGRP_EXPIRE
+ XFRMNLGRP_SA,
+#define XFRMNLGRP_SA XFRMNLGRP_SA
+ XFRMNLGRP_POLICY,
+#define XFRMNLGRP_POLICY XFRMNLGRP_POLICY
+ XFRMNLGRP_AEVENTS,
+#define XFRMNLGRP_AEVENTS XFRMNLGRP_AEVENTS
+ XFRMNLGRP_REPORT,
+#define XFRMNLGRP_REPORT XFRMNLGRP_REPORT
+ XFRMNLGRP_MIGRATE,
+#define XFRMNLGRP_MIGRATE XFRMNLGRP_MIGRATE
+ XFRMNLGRP_MAPPING,
+#define XFRMNLGRP_MAPPING XFRMNLGRP_MAPPING
+ __XFRMNLGRP_MAX
+};
+#define XFRMNLGRP_MAX (__XFRMNLGRP_MAX - 1)
+
+#endif /* _LINUX_XFRM_H */
diff --git a/include/utils.h b/include/utils.h
new file mode 100644
index 0000000..9ba129b
--- /dev/null
+++ b/include/utils.h
@@ -0,0 +1,396 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __UTILS_H__
+#define __UTILS_H__ 1
+
+#include <sys/types.h>
+#include <asm/types.h>
+#include <resolv.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <time.h>
+#include <stdint.h>
+
+#ifdef HAVE_LIBBSD
+#include <bsd/string.h>
+#endif
+
+#include "libnetlink.h"
+#include "ll_map.h"
+#include "rtm_map.h"
+#include "json_print.h"
+
+extern int preferred_family;
+extern int human_readable;
+extern int show_stats;
+extern int show_details;
+extern int show_raw;
+extern int resolve_hosts;
+extern int oneline;
+extern int brief;
+extern int json;
+extern int pretty;
+extern int timestamp;
+extern int timestamp_short;
+extern const char * _SL_;
+extern int max_flush_loops;
+extern int batch_mode;
+extern int numeric;
+extern bool do_all;
+extern int echo_request;
+
+#ifndef CONF_USR_DIR
+#define CONF_USR_DIR "/usr/lib/iproute2"
+#endif
+#ifndef CONF_ETC_DIR
+#define CONF_ETC_DIR "/etc/iproute2"
+#endif
+
+#define SPRINT_BSIZE 64
+#define SPRINT_BUF(x) char x[SPRINT_BSIZE]
+
+void incomplete_command(void) __attribute__((noreturn));
+
+#define NEXT_ARG() do { argv++; if (--argc <= 0) incomplete_command(); } while(0)
+#define NEXT_ARG_OK() (argc - 1 > 0)
+#define NEXT_ARG_FWD() do { argv++; argc--; } while(0)
+#define PREV_ARG() do { argv--; argc++; } while(0)
+
+/* Upper limit for batch mode */
+#define MAX_ARGS 512
+
+#define TIME_UNITS_PER_SEC 1000000
+#define NSEC_PER_USEC 1000
+#define NSEC_PER_MSEC 1000000
+#define NSEC_PER_SEC 1000000000LL
+
+typedef struct
+{
+ __u16 flags;
+ __u16 bytelen;
+ __s16 bitlen;
+ /* These next two fields match rtvia */
+ __u16 family;
+ __u32 data[64];
+} inet_prefix;
+
+enum {
+ PREFIXLEN_SPECIFIED = (1 << 0),
+ ADDRTYPE_INET = (1 << 1),
+ ADDRTYPE_UNSPEC = (1 << 2),
+ ADDRTYPE_MULTI = (1 << 3),
+
+ ADDRTYPE_INET_UNSPEC = ADDRTYPE_INET | ADDRTYPE_UNSPEC,
+ ADDRTYPE_INET_MULTI = ADDRTYPE_INET | ADDRTYPE_MULTI
+};
+
+static inline void inet_prefix_reset(inet_prefix *p)
+{
+ p->flags = 0;
+}
+
+static inline bool is_addrtype_inet(const inet_prefix *p)
+{
+ return p->flags & ADDRTYPE_INET;
+}
+
+static inline bool is_addrtype_inet_unspec(const inet_prefix *p)
+{
+ return (p->flags & ADDRTYPE_INET_UNSPEC) == ADDRTYPE_INET_UNSPEC;
+}
+
+static inline bool is_addrtype_inet_multi(const inet_prefix *p)
+{
+ return (p->flags & ADDRTYPE_INET_MULTI) == ADDRTYPE_INET_MULTI;
+}
+
+static inline bool is_addrtype_inet_not_unspec(const inet_prefix *p)
+{
+ return (p->flags & ADDRTYPE_INET_UNSPEC) == ADDRTYPE_INET;
+}
+
+static inline bool is_addrtype_inet_not_multi(const inet_prefix *p)
+{
+ return (p->flags & ADDRTYPE_INET_MULTI) == ADDRTYPE_INET;
+}
+
+#ifndef AF_MPLS
+# define AF_MPLS 28
+#endif
+#ifndef IPPROTO_MPLS
+#define IPPROTO_MPLS 137
+#endif
+
+#ifndef CLOCK_TAI
+# define CLOCK_TAI 11
+#endif
+
+#ifndef AF_XDP
+# define AF_XDP 44
+# if AF_MAX < 45
+# undef AF_MAX
+# define AF_MAX 45
+# endif
+#endif
+
+__u32 get_addr32(const char *name);
+int get_addr_1(inet_prefix *dst, const char *arg, int family);
+int get_prefix_1(inet_prefix *dst, char *arg, int family);
+int get_addr(inet_prefix *dst, const char *arg, int family);
+int get_prefix(inet_prefix *dst, char *arg, int family);
+int mask2bits(__u32 netmask);
+int get_addr_rta(inet_prefix *dst, const struct rtattr *rta, int family);
+int get_addr_ila(__u64 *val, const char *arg);
+
+int read_prop(const char *dev, char *prop, long *value);
+int get_long(long *val, const char *arg, int base);
+int get_integer(int *val, const char *arg, int base);
+int get_unsigned(unsigned *val, const char *arg, int base);
+int get_time_rtt(unsigned *val, const char *arg, int *raw);
+#define get_byte get_u8
+#define get_ushort get_u16
+#define get_short get_s16
+int get_s64(__s64 *val, const char *arg, int base);
+int get_u64(__u64 *val, const char *arg, int base);
+int get_u32(__u32 *val, const char *arg, int base);
+int get_s32(__s32 *val, const char *arg, int base);
+int get_u16(__u16 *val, const char *arg, int base);
+int get_u8(__u8 *val, const char *arg, int base);
+int get_be64(__be64 *val, const char *arg, int base);
+int get_be32(__be32 *val, const char *arg, int base);
+int get_be16(__be16 *val, const char *arg, int base);
+int get_addr64(__u64 *ap, const char *cp);
+int get_rate(unsigned int *rate, const char *str);
+int get_rate64(__u64 *rate, const char *str);
+int get_size(unsigned int *size, const char *str);
+
+int hex2mem(const char *buf, uint8_t *mem, int count);
+char *hexstring_n2a(const __u8 *str, int len, char *buf, int blen);
+__u8 *hexstring_a2n(const char *str, __u8 *buf, int blen, unsigned int *len);
+#define ADDR64_BUF_SIZE sizeof("xxxx:xxxx:xxxx:xxxx")
+int addr64_n2a(__u64 addr, char *buff, size_t len);
+
+int af_bit_len(int af);
+
+const char *format_host_r(int af, int len, const void *addr,
+ char *buf, int buflen);
+#define format_host_rta_r(af, rta, buf, buflen) \
+ format_host_r(af, RTA_PAYLOAD(rta), RTA_DATA(rta), \
+ buf, buflen)
+
+const char *format_host(int af, int lne, const void *addr);
+#define format_host_rta(af, rta) \
+ format_host(af, RTA_PAYLOAD(rta), RTA_DATA(rta))
+const char *rt_addr_n2a_r(int af, int len, const void *addr,
+ char *buf, int buflen);
+const char *rt_addr_n2a(int af, int len, const void *addr);
+#define rt_addr_n2a_rta(af, rta) \
+ rt_addr_n2a(af, RTA_PAYLOAD(rta), RTA_DATA(rta))
+
+int read_family(const char *name);
+const char *family_name(int family);
+
+void missarg(const char *) __attribute__((noreturn));
+void invarg(const char *, const char *) __attribute__((noreturn));
+void duparg(const char *, const char *) __attribute__((noreturn));
+void duparg2(const char *, const char *) __attribute__((noreturn));
+int nodev(const char *dev);
+int check_ifname(const char *);
+int check_altifname(const char *name);
+int get_ifname(char *, const char *);
+const char *get_ifname_rta(int ifindex, const struct rtattr *rta);
+int matches(const char *prefix, const char *string);
+int inet_addr_match(const inet_prefix *a, const inet_prefix *b, int bits);
+int inet_addr_match_rta(const inet_prefix *m, const struct rtattr *rta);
+
+const char *ax25_ntop(int af, const void *addr, char *str, socklen_t len);
+
+const char *rose_ntop(int af, const void *addr, char *buf, socklen_t buflen);
+
+const char *mpls_ntop(int af, const void *addr, char *str, size_t len);
+int mpls_pton(int af, const char *src, void *addr, size_t alen);
+
+const char *netrom_ntop(int af, const void *addr, char *str, socklen_t len);
+
+extern int __iproute2_hz_internal;
+int __get_hz(void);
+
+static __inline__ int get_hz(void)
+{
+ if (__iproute2_hz_internal == 0)
+ __iproute2_hz_internal = __get_hz();
+ return __iproute2_hz_internal;
+}
+
+extern int __iproute2_user_hz_internal;
+int __get_user_hz(void);
+
+static __inline__ int get_user_hz(void)
+{
+ if (__iproute2_user_hz_internal == 0)
+ __iproute2_user_hz_internal = __get_user_hz();
+ return __iproute2_user_hz_internal;
+}
+
+static inline __u32 nl_mgrp(__u32 group)
+{
+ if (group > 31 ) {
+ fprintf(stderr, "Use setsockopt for this group %d\n", group);
+ exit(-1);
+ }
+ return group ? (1 << (group - 1)) : 0;
+}
+
+/* courtesy of bridge-utils */
+static inline unsigned long __tv_to_jiffies(const struct timeval *tv)
+{
+ unsigned long long jif;
+
+ jif = 1000000ULL * tv->tv_sec + tv->tv_usec;
+
+ return jif/10000;
+}
+
+static inline void __jiffies_to_tv(struct timeval *tv, unsigned long jiffies)
+{
+ unsigned long long tvusec;
+
+ tvusec = 10000ULL*jiffies;
+ tv->tv_sec = tvusec/1000000;
+ tv->tv_usec = tvusec - 1000000 * tv->tv_sec;
+}
+
+void print_escape_buf(const __u8 *buf, size_t len, const char *escape);
+
+int print_timestamp(FILE *fp);
+void print_nlmsg_timestamp(FILE *fp, const struct nlmsghdr *n);
+
+unsigned int print_name_and_link(const char *fmt,
+ const char *name, struct rtattr *tb[])
+ __attribute__((format(printf, 1, 0)));
+
+
+#define BIT(nr) (UINT64_C(1) << (nr))
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+#define BUILD_BUG_ON(cond) ((void)sizeof(char[1 - 2 * !!(cond)]))
+
+#ifndef offsetof
+# define offsetof(type, member) ((size_t) &((type *)0)->member)
+#endif
+
+#ifndef min
+# define min(x, y) ({ \
+ typeof(x) _min1 = (x); \
+ typeof(y) _min2 = (y); \
+ (void) (&_min1 == &_min2); \
+ _min1 < _min2 ? _min1 : _min2; })
+#endif
+
+#ifndef max
+# define max(x, y) ({ \
+ typeof(x) _max1 = (x); \
+ typeof(y) _max2 = (y); \
+ (void) (&_max1 == &_max2); \
+ _max1 < _max2 ? _max2 : _max1; })
+#endif
+
+#ifndef __check_format_string
+# define __check_format_string(pos_str, pos_args) \
+ __attribute__ ((format (printf, (pos_str), (pos_args))))
+#endif
+
+#define _textify(x) #x
+#define textify(x) _textify(x)
+
+#define htonll(x) ((1==htonl(1)) ? (x) : ((uint64_t)htonl((x) & 0xFFFFFFFF) << 32) | htonl((x) >> 32))
+#define ntohll(x) ((1==ntohl(1)) ? (x) : ((uint64_t)ntohl((x) & 0xFFFFFFFF) << 32) | ntohl((x) >> 32))
+
+extern int cmdlineno;
+
+char *int_to_str(int val, char *buf);
+char *uint_to_str(unsigned int val, char *buf);
+int get_guid(__u64 *guid, const char *arg);
+int get_real_family(int rtm_type, int rtm_family);
+
+int cmd_exec(const char *cmd, char **argv, bool do_fork,
+ int (*setup)(void *), void *arg);
+int make_path(const char *path, mode_t mode);
+char *find_cgroup2_mount(bool do_mount);
+__u64 get_cgroup2_id(const char *path);
+char *get_cgroup2_path(__u64 id, bool full);
+int get_command_name(const char *pid, char *comm, size_t len);
+int get_task_name(pid_t pid, char *name, size_t len);
+
+int get_rtnl_link_stats_rta(struct rtnl_link_stats64 *stats64,
+ struct rtattr *tb[]);
+
+#ifdef NEED_STRLCPY
+size_t strlcpy(char *dst, const char *src, size_t size);
+size_t strlcat(char *dst, const char *src, size_t size);
+#endif
+
+void drop_cap(void);
+
+int get_time(unsigned int *time, const char *str);
+int get_time64(__s64 *time, const char *str);
+char *sprint_time(__u32 time, char *buf);
+char *sprint_time64(__s64 time, char *buf);
+
+int do_batch(const char *name, bool force,
+ int (*cmd)(int argc, char *argv[], void *user), void *user);
+
+int parse_one_of(const char *msg, const char *realval, const char * const *list,
+ size_t len, int *p_err);
+int parse_one_of_deprecated(const char *msg, const char *realval,
+ const char * const *list,
+ size_t len, int *p_err);
+bool parse_on_off(const char *msg, const char *realval, int *p_err);
+
+int parse_mapping_num_all(__u32 *keyp, const char *key);
+int parse_mapping_gen(int *argcp, char ***argvp,
+ int (*key_cb)(__u32 *keyp, const char *key),
+ int (*mapping_cb)(__u32 key, char *value, void *data),
+ void *mapping_cb_data);
+int parse_mapping(int *argcp, char ***argvp, bool allow_all,
+ int (*mapping_cb)(__u32 key, char *value, void *data),
+ void *mapping_cb_data);
+
+struct str_num_map {
+ const char *str;
+ unsigned int num;
+};
+
+int str_map_lookup_str(const struct str_num_map *map, const char *needle);
+const char *str_map_lookup_uint(const struct str_num_map *map,
+ unsigned int val);
+const char *str_map_lookup_u16(const struct str_num_map *map, uint16_t val);
+const char *str_map_lookup_u8(const struct str_num_map *map, uint8_t val);
+
+unsigned int get_str_char_count(const char *str, int match);
+int str_split_by_char(char *str, char **before, char **after, int match);
+
+#define INDENT_STR_MAXLEN 32
+
+struct indent_mem {
+ int indent_level;
+ char indent_str[INDENT_STR_MAXLEN + 1];
+};
+
+struct indent_mem *alloc_indent_mem(void);
+void free_indent_mem(struct indent_mem *mem);
+void inc_indent(struct indent_mem *mem);
+void dec_indent(struct indent_mem *mem);
+void print_indent(struct indent_mem *mem);
+
+struct proto {
+ int id;
+ const char *name;
+};
+
+int proto_a2n(unsigned short *id, const char *buf,
+ const struct proto *proto_tb, size_t tb_len);
+const char *proto_n2a(unsigned short id, char *buf, int len,
+ const struct proto *proto_tb, size_t tb_len);
+
+#endif /* __UTILS_H__ */
diff --git a/include/version.h b/include/version.h
new file mode 100644
index 0000000..ae9eec9
--- /dev/null
+++ b/include/version.h
@@ -0,0 +1 @@
+static const char version[] = "6.8.0";
diff --git a/include/xt-internal.h b/include/xt-internal.h
new file mode 100644
index 0000000..0721614
--- /dev/null
+++ b/include/xt-internal.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _XTABLES_INTERNAL_H
+#define _XTABLES_INTERNAL_H 1
+
+#ifndef XT_LIB_DIR
+# define XT_LIB_DIR "/lib/xtables"
+#endif
+
+/* protocol family dependent information */
+struct afinfo {
+ /* protocol family */
+ int family;
+
+ /* prefix of library name (ex "libipt_" */
+ char *libprefix;
+
+ /* used by setsockopt (ex IPPROTO_IP */
+ int ipproto;
+
+ /* kernel module (ex "ip_tables" */
+ char *kmod;
+
+ /* optname to check revision support of match */
+ int so_rev_match;
+
+ /* optname to check revision support of match */
+ int so_rev_target;
+};
+
+enum xt_tryload {
+ DONT_LOAD,
+ DURING_LOAD,
+ TRY_LOAD,
+ LOAD_MUST_SUCCEED
+};
+
+struct xtables_rule_match {
+ struct xtables_rule_match *next;
+ struct xtables_match *match;
+ /* Multiple matches of the same type: the ones before
+ the current one are completed from parsing point of view */
+ unsigned int completed;
+};
+
+extern char *lib_dir;
+
+extern void *fw_calloc(size_t count, size_t size);
+extern void *fw_malloc(size_t size);
+
+extern const char *modprobe_program;
+extern int xtables_insmod(const char *modname, const char *modprobe, int quiet);
+extern int load_xtables_ko(const char *modprobe, int quiet);
+
+/* This is decleared in ip[6]tables.c */
+extern struct afinfo afinfo;
+
+/* Keeping track of external matches and targets: linked lists. */
+extern struct xtables_match *xtables_matches;
+extern struct xtables_target *xtables_targets;
+
+extern struct xtables_match *find_match(const char *name, enum xt_tryload,
+ struct xtables_rule_match **match);
+extern struct xtables_target *find_target(const char *name, enum xt_tryload);
+
+extern void _init(void);
+
+#endif /* _XTABLES_INTERNAL_H */
diff --git a/include/xtables.h b/include/xtables.h
new file mode 100644
index 0000000..583619f
--- /dev/null
+++ b/include/xtables.h
@@ -0,0 +1,598 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _XTABLES_H
+#define _XTABLES_H
+
+/*
+ * Changing any structs/functions may incur a needed change
+ * in libxtables_vcurrent/vage too.
+ */
+
+#include <sys/socket.h> /* PF_* */
+#include <sys/types.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <netinet/in.h>
+#include <net/if.h>
+#include <linux/types.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/x_tables.h>
+
+#ifndef IPPROTO_SCTP
+#define IPPROTO_SCTP 132
+#endif
+#ifndef IPPROTO_DCCP
+#define IPPROTO_DCCP 33
+#endif
+#ifndef IPPROTO_MH
+# define IPPROTO_MH 135
+#endif
+#ifndef IPPROTO_UDPLITE
+#define IPPROTO_UDPLITE 136
+#endif
+
+#include <xtables-version.h>
+
+struct in_addr;
+
+/*
+ * .size is here so that there is a somewhat reasonable check
+ * against the chosen .type.
+ */
+#define XTOPT_POINTER(stype, member) \
+ .ptroff = offsetof(stype, member), \
+ .size = sizeof(((stype *)NULL)->member)
+#define XTOPT_TABLEEND {.name = NULL}
+
+/**
+ * Select the format the input has to conform to, as well as the target type
+ * (area pointed to with XTOPT_POINTER). Note that the storing is not always
+ * uniform. @cb->val will be populated with as much as there is space, i.e.
+ * exactly 2 items for ranges, but the target area can receive more values
+ * (e.g. in case of ranges), or less values (e.g. %XTTYPE_HOSTMASK).
+ *
+ * %XTTYPE_NONE: option takes no argument
+ * %XTTYPE_UINT*: standard integer
+ * %XTTYPE_UINT*RC: colon-separated range of standard integers
+ * %XTTYPE_DOUBLE: double-precision floating point number
+ * %XTTYPE_STRING: arbitrary string
+ * %XTTYPE_TOSMASK: 8-bit TOS value with optional mask
+ * %XTTYPE_MARKMASK32: 32-bit mark with optional mask
+ * %XTTYPE_SYSLOGLEVEL: syslog level by name or number
+ * %XTTYPE_HOST: one host or address (ptr: union nf_inet_addr)
+ * %XTTYPE_HOSTMASK: one host or address, with an optional prefix length
+ * (ptr: union nf_inet_addr; only host portion is stored)
+ * %XTTYPE_PROTOCOL: protocol number/name from /etc/protocols (ptr: uint8_t)
+ * %XTTYPE_PORT: 16-bit port name or number (supports %XTOPT_NBO)
+ * %XTTYPE_PORTRC: colon-separated port range (names acceptable),
+ * (supports %XTOPT_NBO)
+ * %XTTYPE_PLEN: prefix length
+ * %XTTYPE_PLENMASK: prefix length (ptr: union nf_inet_addr)
+ * %XTTYPE_ETHERMAC: Ethernet MAC address in hex form
+ */
+enum xt_option_type {
+ XTTYPE_NONE,
+ XTTYPE_UINT8,
+ XTTYPE_UINT16,
+ XTTYPE_UINT32,
+ XTTYPE_UINT64,
+ XTTYPE_UINT8RC,
+ XTTYPE_UINT16RC,
+ XTTYPE_UINT32RC,
+ XTTYPE_UINT64RC,
+ XTTYPE_DOUBLE,
+ XTTYPE_STRING,
+ XTTYPE_TOSMASK,
+ XTTYPE_MARKMASK32,
+ XTTYPE_SYSLOGLEVEL,
+ XTTYPE_HOST,
+ XTTYPE_HOSTMASK,
+ XTTYPE_PROTOCOL,
+ XTTYPE_PORT,
+ XTTYPE_PORTRC,
+ XTTYPE_PLEN,
+ XTTYPE_PLENMASK,
+ XTTYPE_ETHERMAC,
+};
+
+/**
+ * %XTOPT_INVERT: option is invertible (usable with !)
+ * %XTOPT_MAND: option is mandatory
+ * %XTOPT_MULTI: option may be specified multiple times
+ * %XTOPT_PUT: store value into memory at @ptroff
+ * %XTOPT_NBO: store value in network-byte order
+ * (only certain XTTYPEs recognize this)
+ */
+enum xt_option_flags {
+ XTOPT_INVERT = 1 << 0,
+ XTOPT_MAND = 1 << 1,
+ XTOPT_MULTI = 1 << 2,
+ XTOPT_PUT = 1 << 3,
+ XTOPT_NBO = 1 << 4,
+};
+
+/**
+ * @name: name of option
+ * @type: type of input and validation method, see %XTTYPE_*
+ * @id: unique number (within extension) for option, 0-31
+ * @excl: bitmask of flags that cannot be used with this option
+ * @also: bitmask of flags that must be used with this option
+ * @flags: bitmask of option flags, see %XTOPT_*
+ * @ptroff: offset into private structure for member
+ * @size: size of the item pointed to by @ptroff; this is a safeguard
+ * @min: lowest allowed value (for singular integral types)
+ * @max: highest allowed value (for singular integral types)
+ */
+struct xt_option_entry {
+ const char *name;
+ enum xt_option_type type;
+ unsigned int id, excl, also, flags;
+ unsigned int ptroff;
+ size_t size;
+ unsigned int min, max;
+};
+
+/**
+ * @arg: input from command line
+ * @ext_name: name of extension currently being processed
+ * @entry: current option being processed
+ * @data: per-extension kernel data block
+ * @xflags: options of the extension that have been used
+ * @invert: whether option was used with !
+ * @nvals: number of results in uXX_multi
+ * @val: parsed result
+ * @udata: per-extension private scratch area
+ * (cf. xtables_{match,target}->udata_size)
+ */
+struct xt_option_call {
+ const char *arg, *ext_name;
+ const struct xt_option_entry *entry;
+ void *data;
+ unsigned int xflags;
+ bool invert;
+ uint8_t nvals;
+ union {
+ uint8_t u8, u8_range[2], syslog_level, protocol;
+ uint16_t u16, u16_range[2], port, port_range[2];
+ uint32_t u32, u32_range[2];
+ uint64_t u64, u64_range[2];
+ double dbl;
+ struct {
+ union nf_inet_addr haddr, hmask;
+ uint8_t hlen;
+ };
+ struct {
+ uint8_t tos_value, tos_mask;
+ };
+ struct {
+ uint32_t mark, mask;
+ };
+ uint8_t ethermac[6];
+ } val;
+ /* Wished for a world where the ones below were gone: */
+ union {
+ struct xt_entry_match **match;
+ struct xt_entry_target **target;
+ };
+ void *xt_entry;
+ void *udata;
+};
+
+/**
+ * @ext_name: name of extension currently being processed
+ * @data: per-extension (kernel) data block
+ * @udata: per-extension private scratch area
+ * (cf. xtables_{match,target}->udata_size)
+ * @xflags: options of the extension that have been used
+ */
+struct xt_fcheck_call {
+ const char *ext_name;
+ void *data, *udata;
+ unsigned int xflags;
+};
+
+/**
+ * A "linear"/linked-list based name<->id map, for files similar to
+ * /etc/iproute2/.
+ */
+struct xtables_lmap {
+ char *name;
+ int id;
+ struct xtables_lmap *next;
+};
+
+enum xtables_ext_flags {
+ XTABLES_EXT_ALIAS = 1 << 0,
+};
+
+#if XTABLES_VERSION_CODE >= 12
+struct xt_xlate;
+
+struct xt_xlate_mt_params {
+ const void *ip;
+ const struct xt_entry_match *match;
+ int numeric;
+ bool escape_quotes;
+};
+
+struct xt_xlate_tg_params {
+ const void *ip;
+ const struct xt_entry_target *target;
+ int numeric;
+ bool escape_quotes;
+};
+#endif
+
+/* Include file for additions: new matches and targets. */
+struct xtables_match
+{
+ /*
+ * ABI/API version this module requires. Must be first member,
+ * as the rest of this struct may be subject to ABI changes.
+ */
+ const char *version;
+
+ struct xtables_match *next;
+
+ const char *name;
+ const char *real_name;
+
+ /* Revision of match (0 by default). */
+ uint8_t revision;
+
+ /* Extension flags */
+ uint8_t ext_flags;
+
+ uint16_t family;
+
+ /* Size of match data. */
+ size_t size;
+
+ /* Size of match data relevant for userspace comparison purposes */
+ size_t userspacesize;
+
+ /* Function which prints out usage message. */
+ void (*help)(void);
+
+ /* Initialize the match. */
+ void (*init)(struct xt_entry_match *m);
+
+ /* Function which parses command options; returns true if it
+ ate an option */
+ /* entry is struct ipt_entry for example */
+ int (*parse)(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry,
+ struct xt_entry_match **match);
+
+ /* Final check; exit if not ok. */
+ void (*final_check)(unsigned int flags);
+
+ /* Prints out the match iff non-NULL: put space at end */
+ /* ip is struct ipt_ip * for example */
+ void (*print)(const void *ip,
+ const struct xt_entry_match *match, int numeric);
+
+ /* Saves the match info in parsable form to stdout. */
+ /* ip is struct ipt_ip * for example */
+ void (*save)(const void *ip, const struct xt_entry_match *match);
+
+ /* Print match name or alias */
+ const char *(*alias)(const struct xt_entry_match *match);
+
+ /* Pointer to list of extra command-line options */
+ const struct option *extra_opts;
+
+ /* New parser */
+ void (*x6_parse)(struct xt_option_call *);
+ void (*x6_fcheck)(struct xt_fcheck_call *);
+ const struct xt_option_entry *x6_options;
+
+#if XTABLES_VERSION_CODE >= 12
+ /* Translate iptables to nft */
+ int (*xlate)(struct xt_xlate *xl,
+ const struct xt_xlate_mt_params *params);
+#endif
+
+ /* Size of per-extension instance extra "global" scratch space */
+ size_t udata_size;
+
+ /* Ignore these men behind the curtain: */
+ void *udata;
+ unsigned int option_offset;
+ struct xt_entry_match *m;
+ unsigned int mflags;
+ unsigned int loaded; /* simulate loading so options are merged properly */
+};
+
+struct xtables_target
+{
+ /*
+ * ABI/API version this module requires. Must be first member,
+ * as the rest of this struct may be subject to ABI changes.
+ */
+ const char *version;
+
+ struct xtables_target *next;
+
+
+ const char *name;
+
+ /* Real target behind this, if any. */
+ const char *real_name;
+
+ /* Revision of target (0 by default). */
+ uint8_t revision;
+
+ /* Extension flags */
+ uint8_t ext_flags;
+
+ uint16_t family;
+
+
+ /* Size of target data. */
+ size_t size;
+
+ /* Size of target data relevant for userspace comparison purposes */
+ size_t userspacesize;
+
+ /* Function which prints out usage message. */
+ void (*help)(void);
+
+ /* Initialize the target. */
+ void (*init)(struct xt_entry_target *t);
+
+ /* Function which parses command options; returns true if it
+ ate an option */
+ /* entry is struct ipt_entry for example */
+ int (*parse)(int c, char **argv, int invert, unsigned int *flags,
+ const void *entry,
+ struct xt_entry_target **targetinfo);
+
+ /* Final check; exit if not ok. */
+ void (*final_check)(unsigned int flags);
+
+ /* Prints out the target iff non-NULL: put space at end */
+ void (*print)(const void *ip,
+ const struct xt_entry_target *target, int numeric);
+
+ /* Saves the targinfo in parsable form to stdout. */
+ void (*save)(const void *ip,
+ const struct xt_entry_target *target);
+
+ /* Print target name or alias */
+ const char *(*alias)(const struct xt_entry_target *target);
+
+ /* Pointer to list of extra command-line options */
+ const struct option *extra_opts;
+
+ /* New parser */
+ void (*x6_parse)(struct xt_option_call *);
+ void (*x6_fcheck)(struct xt_fcheck_call *);
+ const struct xt_option_entry *x6_options;
+
+#if XTABLES_VERSION_CODE >= 12
+ /* Translate iptables to nft */
+ int (*xlate)(struct xt_xlate *xl,
+ const struct xt_xlate_tg_params *params);
+#endif
+
+ size_t udata_size;
+
+ /* Ignore these men behind the curtain: */
+ void *udata;
+ unsigned int option_offset;
+ struct xt_entry_target *t;
+ unsigned int tflags;
+ unsigned int used;
+ unsigned int loaded; /* simulate loading so options are merged properly */
+};
+
+struct xtables_rule_match {
+ struct xtables_rule_match *next;
+ struct xtables_match *match;
+ /* Multiple matches of the same type: the ones before
+ the current one are completed from parsing point of view */
+ bool completed;
+};
+
+/**
+ * struct xtables_pprot -
+ *
+ * A few hardcoded protocols for 'all' and in case the user has no
+ * /etc/protocols.
+ */
+struct xtables_pprot {
+ const char *name;
+ uint8_t num;
+};
+
+enum xtables_tryload {
+ XTF_DONT_LOAD,
+ XTF_DURING_LOAD,
+ XTF_TRY_LOAD,
+ XTF_LOAD_MUST_SUCCEED,
+};
+
+enum xtables_exittype {
+ OTHER_PROBLEM = 1,
+ PARAMETER_PROBLEM,
+ VERSION_PROBLEM,
+ RESOURCE_PROBLEM,
+ XTF_ONLY_ONCE,
+ XTF_NO_INVERT,
+ XTF_BAD_VALUE,
+ XTF_ONE_ACTION,
+};
+
+struct xtables_globals
+{
+ unsigned int option_offset;
+ const char *program_name, *program_version;
+ struct option *orig_opts;
+ struct option *opts;
+ void (*exit_err)(enum xtables_exittype status, const char *msg, ...) __attribute__((noreturn, format(printf,2,3)));
+ int (*compat_rev)(const char *name, uint8_t rev, int opt);
+};
+
+#define XT_GETOPT_TABLEEND {.name = NULL, .has_arg = false}
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+extern const char *xtables_modprobe_program;
+extern struct xtables_match *xtables_matches;
+extern struct xtables_target *xtables_targets;
+
+extern void xtables_init(void);
+extern void xtables_set_nfproto(uint8_t);
+extern void *xtables_calloc(size_t, size_t);
+extern void *xtables_malloc(size_t);
+extern void *xtables_realloc(void *, size_t);
+
+extern int xtables_insmod(const char *, const char *, bool);
+extern int xtables_load_ko(const char *, bool);
+extern int xtables_set_params(struct xtables_globals *xtp);
+extern void xtables_free_opts(int reset_offset);
+extern struct option *xtables_merge_options(struct option *origopts,
+ struct option *oldopts, const struct option *newopts,
+ unsigned int *option_offset);
+
+extern int xtables_init_all(struct xtables_globals *xtp, uint8_t nfproto);
+extern struct xtables_match *xtables_find_match(const char *name,
+ enum xtables_tryload, struct xtables_rule_match **match);
+extern struct xtables_target *xtables_find_target(const char *name,
+ enum xtables_tryload);
+extern int xtables_compatible_revision(const char *name, uint8_t revision,
+ int opt);
+
+extern void xtables_rule_matches_free(struct xtables_rule_match **matches);
+
+/* Your shared library should call one of these. */
+extern void xtables_register_match(struct xtables_match *me);
+extern void xtables_register_matches(struct xtables_match *, unsigned int);
+extern void xtables_register_target(struct xtables_target *me);
+extern void xtables_register_targets(struct xtables_target *, unsigned int);
+
+extern bool xtables_strtoul(const char *, char **, uintmax_t *,
+ uintmax_t, uintmax_t);
+extern bool xtables_strtoui(const char *, char **, unsigned int *,
+ unsigned int, unsigned int);
+extern int xtables_service_to_port(const char *name, const char *proto);
+extern uint16_t xtables_parse_port(const char *port, const char *proto);
+extern void
+xtables_parse_interface(const char *arg, char *vianame, unsigned char *mask);
+
+/* this is a special 64bit data type that is 8-byte aligned */
+#define aligned_u64 uint64_t __attribute__((aligned(8)))
+
+extern struct xtables_globals *xt_params;
+#define xtables_error (xt_params->exit_err)
+
+extern void xtables_param_act(unsigned int, const char *, ...);
+
+extern const char *xtables_ipaddr_to_numeric(const struct in_addr *);
+extern const char *xtables_ipaddr_to_anyname(const struct in_addr *);
+extern const char *xtables_ipmask_to_numeric(const struct in_addr *);
+extern struct in_addr *xtables_numeric_to_ipaddr(const char *);
+extern struct in_addr *xtables_numeric_to_ipmask(const char *);
+extern int xtables_ipmask_to_cidr(const struct in_addr *);
+extern void xtables_ipparse_any(const char *, struct in_addr **,
+ struct in_addr *, unsigned int *);
+extern void xtables_ipparse_multiple(const char *, struct in_addr **,
+ struct in_addr **, unsigned int *);
+
+extern struct in6_addr *xtables_numeric_to_ip6addr(const char *);
+extern const char *xtables_ip6addr_to_numeric(const struct in6_addr *);
+extern const char *xtables_ip6addr_to_anyname(const struct in6_addr *);
+extern const char *xtables_ip6mask_to_numeric(const struct in6_addr *);
+extern int xtables_ip6mask_to_cidr(const struct in6_addr *);
+extern void xtables_ip6parse_any(const char *, struct in6_addr **,
+ struct in6_addr *, unsigned int *);
+extern void xtables_ip6parse_multiple(const char *, struct in6_addr **,
+ struct in6_addr **, unsigned int *);
+
+/**
+ * Print the specified value to standard output, quoting dangerous
+ * characters if required.
+ */
+extern void xtables_save_string(const char *value);
+
+#define FMT_NUMERIC 0x0001
+#define FMT_NOCOUNTS 0x0002
+#define FMT_KILOMEGAGIGA 0x0004
+#define FMT_OPTIONS 0x0008
+#define FMT_NOTABLE 0x0010
+#define FMT_NOTARGET 0x0020
+#define FMT_VIA 0x0040
+#define FMT_NONEWLINE 0x0080
+#define FMT_LINENUMBERS 0x0100
+
+#define FMT_PRINT_RULE (FMT_NOCOUNTS | FMT_OPTIONS | FMT_VIA \
+ | FMT_NUMERIC | FMT_NOTABLE)
+#define FMT(tab,notab) ((format) & FMT_NOTABLE ? (notab) : (tab))
+
+extern void xtables_print_num(uint64_t number, unsigned int format);
+
+#if defined(ALL_INCLUSIVE) || defined(NO_SHARED_LIBS)
+# ifdef _INIT
+# undef _init
+# define _init _INIT
+# endif
+ extern void init_extensions(void);
+ extern void init_extensions4(void);
+ extern void init_extensions6(void);
+#else
+# define _init __attribute__((constructor)) _INIT
+#endif
+
+extern const struct xtables_pprot xtables_chain_protos[];
+extern uint16_t xtables_parse_protocol(const char *s);
+
+/* kernel revision handling */
+extern int kernel_version;
+extern void get_kernel_version(void);
+#define LINUX_VERSION(x,y,z) (0x10000*(x) + 0x100*(y) + z)
+#define LINUX_VERSION_MAJOR(x) (((x)>>16) & 0xFF)
+#define LINUX_VERSION_MINOR(x) (((x)>> 8) & 0xFF)
+#define LINUX_VERSION_PATCH(x) ( (x) & 0xFF)
+
+/* xtoptions.c */
+extern void xtables_option_metavalidate(const char *,
+ const struct xt_option_entry *);
+extern struct option *xtables_options_xfrm(struct option *, struct option *,
+ const struct xt_option_entry *,
+ unsigned int *);
+extern void xtables_option_parse(struct xt_option_call *);
+extern void xtables_option_tpcall(unsigned int, char **, bool,
+ struct xtables_target *, void *);
+extern void xtables_option_mpcall(unsigned int, char **, bool,
+ struct xtables_match *, void *);
+extern void xtables_option_tfcall(struct xtables_target *);
+extern void xtables_option_mfcall(struct xtables_match *);
+extern void xtables_options_fcheck(const char *, unsigned int,
+ const struct xt_option_entry *);
+
+extern struct xtables_lmap *xtables_lmap_init(const char *);
+extern void xtables_lmap_free(struct xtables_lmap *);
+extern int xtables_lmap_name2id(const struct xtables_lmap *, const char *);
+extern const char *xtables_lmap_id2name(const struct xtables_lmap *, int);
+
+#ifdef XTABLES_INTERNAL
+
+/* Shipped modules rely on this... */
+
+# ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+# endif
+
+extern void _init(void);
+
+#endif
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* _XTABLES_H */