From 007c76937f34c11c4c827373f081a9c4eebf1fc3 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 6 Feb 2019 14:50:24 +0100 Subject: [PATCH] Update kernel headers This updates kernel headers to upstream commit 761ec9e29ff867452057f59dc6ca430688b409ea. Update was done via: | git checkout 761ec9e29ff867452057f59dc6ca430688b409ea -- include/uapi Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1641909 Upstream Status: RHEL-only --- include/uapi/linux/atm.h | 1 + include/uapi/linux/atmapi.h | 1 + include/uapi/linux/atmarp.h | 1 + include/uapi/linux/atmdev.h | 1 + include/uapi/linux/atmioc.h | 1 + include/uapi/linux/atmsap.h | 1 + include/uapi/linux/bpf.h | 2481 ++++++++++++++++++++---- include/uapi/linux/bpf_common.h | 8 +- include/uapi/linux/btf.h | 113 ++ include/uapi/linux/can.h | 1 + include/uapi/linux/can/netlink.h | 2 + include/uapi/linux/can/vxcan.h | 1 + include/uapi/linux/devlink.h | 82 + include/uapi/linux/elf-em.h | 1 + include/uapi/linux/fib_rules.h | 12 +- include/uapi/linux/filter.h | 1 + include/uapi/linux/fou.h | 1 + include/uapi/linux/gen_stats.h | 1 + include/uapi/linux/genetlink.h | 1 + include/uapi/linux/hdlc/ioctl.h | 1 + include/uapi/linux/icmpv6.h | 1 + include/uapi/linux/if.h | 1 + include/uapi/linux/if_addr.h | 2 + include/uapi/linux/if_addrlabel.h | 1 + include/uapi/linux/if_alg.h | 1 + include/uapi/linux/if_arp.h | 1 + include/uapi/linux/if_bonding.h | 1 + include/uapi/linux/if_bridge.h | 1 + include/uapi/linux/if_ether.h | 11 + include/uapi/linux/if_link.h | 59 + include/uapi/linux/if_macsec.h | 10 +- include/uapi/linux/if_packet.h | 1 + include/uapi/linux/if_tun.h | 5 + include/uapi/linux/if_tunnel.h | 5 + include/uapi/linux/if_vlan.h | 1 + include/uapi/linux/ife.h | 1 + include/uapi/linux/ila.h | 23 + include/uapi/linux/in.h | 1 + include/uapi/linux/in6.h | 2 + include/uapi/linux/in_route.h | 1 + include/uapi/linux/inet_diag.h | 3 + include/uapi/linux/ip.h | 1 + include/uapi/linux/ip6_tunnel.h | 3 + include/uapi/linux/ipsec.h | 1 + include/uapi/linux/kernel.h | 1 + include/uapi/linux/l2tp.h | 7 +- include/uapi/linux/libc-compat.h | 56 +- include/uapi/linux/limits.h | 1 + include/uapi/linux/lwtunnel.h | 1 + include/uapi/linux/magic.h | 2 + include/uapi/linux/mpls.h | 1 + include/uapi/linux/mpls_iptunnel.h | 1 + include/uapi/linux/neighbour.h | 1 + include/uapi/linux/net_namespace.h | 1 + include/uapi/linux/netconf.h | 1 + include/uapi/linux/netdevice.h | 1 + include/uapi/linux/netfilter.h | 1 + include/uapi/linux/netfilter/ipset/ip_set.h | 1 + include/uapi/linux/netfilter/x_tables.h | 1 + include/uapi/linux/netfilter/xt_set.h | 1 + include/uapi/linux/netfilter/xt_tcpudp.h | 1 + include/uapi/linux/netfilter_ipv4.h | 2 + include/uapi/linux/netfilter_ipv4/ip_tables.h | 1 + include/uapi/linux/netfilter_ipv6.h | 2 + include/uapi/linux/netfilter_ipv6/ip6_tables.h | 1 + include/uapi/linux/netlink.h | 1 + include/uapi/linux/netlink_diag.h | 1 + include/uapi/linux/packet_diag.h | 1 + include/uapi/linux/param.h | 1 + include/uapi/linux/pfkeyv2.h | 1 + include/uapi/linux/pkt_cls.h | 15 +- include/uapi/linux/pkt_sched.h | 198 ++ include/uapi/linux/posix_types.h | 1 + include/uapi/linux/rtnetlink.h | 24 + include/uapi/linux/sctp.h | 71 +- include/uapi/linux/seg6.h | 5 +- include/uapi/linux/seg6_genl.h | 1 + include/uapi/linux/seg6_hmac.h | 1 + include/uapi/linux/seg6_iptunnel.h | 1 + include/uapi/linux/seg6_local.h | 12 + include/uapi/linux/sock_diag.h | 1 + include/uapi/linux/socket.h | 1 + include/uapi/linux/sockios.h | 1 + include/uapi/linux/stddef.h | 1 + include/uapi/linux/sysinfo.h | 1 + include/uapi/linux/tc_act/tc_bpf.h | 1 + include/uapi/linux/tc_act/tc_connmark.h | 1 + include/uapi/linux/tc_act/tc_csum.h | 1 + include/uapi/linux/tc_act/tc_defact.h | 1 + include/uapi/linux/tc_act/tc_gact.h | 1 + include/uapi/linux/tc_act/tc_ife.h | 1 + include/uapi/linux/tc_act/tc_ipt.h | 1 + include/uapi/linux/tc_act/tc_mirred.h | 7 +- include/uapi/linux/tc_act/tc_nat.h | 1 + include/uapi/linux/tc_act/tc_pedit.h | 10 +- include/uapi/linux/tc_act/tc_sample.h | 1 + include/uapi/linux/tc_act/tc_skbedit.h | 3 + include/uapi/linux/tc_act/tc_skbmod.h | 1 + include/uapi/linux/tc_act/tc_tunnel_key.h | 29 + include/uapi/linux/tc_act/tc_vlan.h | 1 + include/uapi/linux/tc_ematch/tc_em_cmp.h | 1 + include/uapi/linux/tc_ematch/tc_em_ipt.h | 20 + include/uapi/linux/tc_ematch/tc_em_meta.h | 1 + include/uapi/linux/tc_ematch/tc_em_nbyte.h | 1 + include/uapi/linux/tcp.h | 22 + include/uapi/linux/tcp_metrics.h | 1 + include/uapi/linux/tipc.h | 188 +- include/uapi/linux/tipc_netlink.h | 37 + include/uapi/linux/tipc_sockets_diag.h | 17 + include/uapi/linux/types.h | 3 + include/uapi/linux/unix_diag.h | 1 + include/uapi/linux/veth.h | 1 + include/uapi/linux/vm_sockets_diag.h | 1 + include/uapi/linux/xfrm.h | 1 + 114 files changed, 3201 insertions(+), 427 deletions(-) create mode 100644 include/uapi/linux/btf.h create mode 100644 include/uapi/linux/tc_ematch/tc_em_ipt.h create mode 100644 include/uapi/linux/tipc_sockets_diag.h diff --git a/include/uapi/linux/atm.h b/include/uapi/linux/atm.h index 08e27be..e33ff6b 100644 --- a/include/uapi/linux/atm.h +++ b/include/uapi/linux/atm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atm.h - general ATM declarations */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ diff --git a/include/uapi/linux/atmapi.h b/include/uapi/linux/atmapi.h index 8fe54d9..c9bf5c2 100644 --- a/include/uapi/linux/atmapi.h +++ b/include/uapi/linux/atmapi.h @@ -1,3 +1,4 @@ +/* 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 */ diff --git a/include/uapi/linux/atmarp.h b/include/uapi/linux/atmarp.h index 231f4bd..8e44d12 100644 --- a/include/uapi/linux/atmarp.h +++ b/include/uapi/linux/atmarp.h @@ -1,3 +1,4 @@ +/* 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 */ diff --git a/include/uapi/linux/atmdev.h b/include/uapi/linux/atmdev.h index 8faa8b9..9bdb96a 100644 --- a/include/uapi/linux/atmdev.h +++ b/include/uapi/linux/atmdev.h @@ -1,3 +1,4 @@ +/* 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 */ diff --git a/include/uapi/linux/atmioc.h b/include/uapi/linux/atmioc.h index 37f67aa..cd7655e 100644 --- a/include/uapi/linux/atmioc.h +++ b/include/uapi/linux/atmioc.h @@ -1,3 +1,4 @@ +/* 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 */ diff --git a/include/uapi/linux/atmsap.h b/include/uapi/linux/atmsap.h index 799b104..fc05248 100644 --- a/include/uapi/linux/atmsap.h +++ b/include/uapi/linux/atmsap.h @@ -1,3 +1,4 @@ +/* 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 */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0895a52..b9a6367 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1,3 +1,4 @@ +/* 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 @@ -16,7 +17,7 @@ #define BPF_ALU64 0x07 /* alu mode in double word width */ /* ld/ldx fields */ -#define BPF_DW 0x18 /* double word */ +#define BPF_DW 0x18 /* double word (64-bit) */ #define BPF_XADD 0xc0 /* exclusive add */ /* alu/jmp fields */ @@ -92,6 +93,11 @@ enum bpf_cmd { 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, }; enum bpf_map_type { @@ -111,6 +117,9 @@ enum bpf_map_type { 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, }; enum bpf_prog_type { @@ -129,6 +138,12 @@ enum bpf_prog_type { 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, }; enum bpf_attach_type { @@ -138,16 +153,63 @@ enum bpf_attach_type { 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, __MAX_BPF_ATTACH_TYPE }; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command - * to the given target_fd cgroup the descendent cgroup will be able to - * override effective bpf program that was inherited from this cgroup +/* 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. + * + * 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) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -156,8 +218,14 @@ enum bpf_attach_type { */ #define BPF_F_STRICT_ALIGNMENT (1U << 0) +/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ #define BPF_PSEUDO_MAP_FD 1 +/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative + * offset to another bpf function + */ +#define BPF_PSEUDO_CALL 1 + /* flags for BPF_MAP_UPDATE_ELEM command */ #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ @@ -175,6 +243,37 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + +#define BPF_OBJ_NAME_LEN 16U + +/* Flags for accessing BPF object */ +#define BPF_F_RDONLY (1U << 3) +#define BPF_F_WRONLY (1U << 4) + +/* Flag for stack_map, store build_id+offset instead of pointer */ +#define BPF_F_STACK_BUILD_ID (1U << 5) + +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; + }; +}; + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -188,6 +287,11 @@ union bpf_attr { __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 */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -210,11 +314,19 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __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; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ __aligned_u64 pathname; __u32 bpf_fd; + __u32 file_flags; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ @@ -240,8 +352,10 @@ union bpf_attr { __u32 start_id; __u32 prog_id; __u32 map_id; + __u32 btf_id; }; __u32 next_id; + __u32 open_flags; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ @@ -249,339 +363,1718 @@ union bpf_attr { __u32 info_len; __aligned_u64 info; } info; + + struct { /* anonymous struct used by BPF_PROG_QUERY command */ + __u32 target_fd; /* container object to query */ + __u32 attach_type; + __u32 query_flags; + __u32 attach_flags; + __aligned_u64 prog_ids; + __u32 prog_cnt; + } query; + + struct { + __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; + }; + + 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; } __attribute__((aligned(8))); -/* BPF helper function descriptions: +/* 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_helpers_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. * - * void *bpf_map_lookup_elem(&map, &key) - * Return: Map value or NULL + * int 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: * - * int bpf_map_update_elem(&map, &key, &value, flags) - * Return: 0 on success or negative error + * **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*. * - * int bpf_map_delete_elem(&map, &key) - * Return: 0 on success or negative error + * 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. * - * int bpf_probe_read(void *dst, int size, void *src) - * Return: 0 on success or negative error + * int 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. + * + * int bpf_probe_read(void *dst, u32 size, const void *src) + * Description + * For tracing programs, safely attempt to read *size* bytes from + * address *src* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_ktime_get_ns(void) - * Return: current ktime - * - * int bpf_trace_printk(const char *fmt, int fmt_size, ...) - * Return: length of buffer written or negative error - * - * u32 bpf_prandom_u32(void) - * Return: random value - * - * u32 bpf_raw_smp_processor_id(void) - * Return: SMP processor ID - * - * int bpf_skb_store_bytes(skb, offset, from, len, flags) - * store bytes into packet - * @skb: pointer to skb - * @offset: offset within packet from skb->mac_header - * @from: pointer where to copy bytes from - * @len: number of bytes to store into packet - * @flags: bit 0 - if true, recompute skb->csum - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l3_csum_replace(skb, offset, from, to, flags) - * recompute IP checksum - * @skb: pointer to skb - * @offset: offset within packet where IP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l4_csum_replace(skb, offset, from, to, flags) - * recompute TCP/UDP checksum - * @skb: pointer to skb - * @offset: offset within packet where TCP/UDP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * bit 4 - is pseudo header - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_tail_call(ctx, prog_array_map, index) - * jump into another BPF program - * @ctx: context pointer passed to next program - * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: index inside array that selects specific program to run - * Return: 0 on success or negative error - * - * int bpf_clone_redirect(skb, ifindex, flags) - * redirect to another netdev - * @skb: pointer to skb - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: 0 on success or negative error + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Return + * Current *ktime*. + * + * int 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/debug/tracing/trace* from DebugFS, 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. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/debug/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: + * + * 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. + * * ```` 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 + * bloc (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 preemption 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. + * + * int 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 underlaying + * 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. + * + * int 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 underlaying + * 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. + * + * int 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 underlaying + * 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. + * + * int 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 32. + * Return + * 0 on success, or a negative error in case of failure. + * + * int 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 underlaying + * 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. * * u64 bpf_get_current_pid_tgid(void) - * Return: current->tgid << 32 | current->pid + * 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) - * Return: current_gid << 32 | current_uid - * - * int bpf_get_current_comm(char *buf, int size_of_buf) - * stores current->comm into buf - * Return: 0 on success or negative error - * - * u32 bpf_get_cgroup_classid(skb) - * retrieve a proc's classid - * @skb: pointer to skb - * Return: classid if != 0 - * - * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) - * Return: 0 on success or negative error - * - * int bpf_skb_vlan_pop(skb) - * Return: 0 on success or negative error - * - * int bpf_skb_get_tunnel_key(skb, key, size, flags) - * int bpf_skb_set_tunnel_key(skb, key, size, flags) - * retrieve or populate tunnel metadata - * @skb: pointer to skb - * @key: pointer to 'struct bpf_tunnel_key' - * @size: size of 'struct bpf_tunnel_key' - * @flags: room for future extensions - * Return: 0 on success or negative error - * - * u64 bpf_perf_event_read(map, flags) - * read perf event counter value - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * Return: value of perf event counter read or error code - * - * int bpf_redirect(ifindex, flags) - * redirect to another netdev - * @ifindex: ifindex of the net device - * @flags: - * cls_bpf: - * bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * xdp_bpf: - * all bits - reserved - * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error - * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error - * int bpf_redirect_map(map, key, flags) - * redirect to endpoint in map - * @map: pointer to dev map - * @key: index in map to lookup - * @flags: -- - * Return: XDP_REDIRECT on success or XDP_ABORT on error - * - * u32 bpf_get_route_realm(skb) - * retrieve a dst's tclassid - * @skb: pointer to skb - * Return: realm if != 0 - * - * int bpf_perf_event_output(ctx, map, flags, data, size) - * output perf raw sample - * @ctx: struct pt_regs* - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @data: data on stack to be output as raw data - * @size: size of data - * Return: 0 on success or negative error - * - * int bpf_get_stackid(ctx, map, flags) - * walk user or kernel stack and return id - * @ctx: struct pt_regs* - * @map: pointer to stack_trace map - * @flags: bits 0-7 - numer of stack frames to skip - * bit 8 - collect user stack instead of kernel - * bit 9 - compare stacks by hash only - * bit 10 - if two different stacks hash into the same stackid - * discard old - * other bits - reserved - * Return: >= 0 stackid on success or negative error - * - * s64 bpf_csum_diff(from, from_size, to, to_size, seed) - * calculate csum diff - * @from: raw from buffer - * @from_size: length of from buffer - * @to: raw to buffer - * @to_size: length of to buffer - * @seed: optional seed - * Return: csum result or negative error code - * - * int bpf_skb_get_tunnel_opt(skb, opt, size) - * retrieve tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: option size - * - * int bpf_skb_set_tunnel_opt(skb, opt, size) - * populate tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: 0 on success or negative error - * - * int bpf_skb_change_proto(skb, proto, flags) - * Change protocol of the skb. Currently supported is v4 -> v6, - * v6 -> v4 transitions. The helper will also resize the skb. eBPF - * program is expected to fill the new headers via skb_store_bytes - * and lX_csum_replace. - * @skb: pointer to skb - * @proto: new skb->protocol type - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_change_type(skb, type) - * Change packet type of skb. - * @skb: pointer to skb - * @type: new skb->pkt_type type - * Return: 0 on success or negative error - * - * int bpf_skb_under_cgroup(skb, map, index) - * Check cgroup2 membership of skb - * @skb: pointer to skb - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 skb failed the cgroup2 descendant test - * == 1 skb succeeded the cgroup2 descendant test - * < 0 error - * - * u32 bpf_get_hash_recalc(skb) - * Retrieve and possibly recalculate skb->hash. - * @skb: pointer to skb - * Return: hash + * Return + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + * + * int bpf_get_current_comm(char *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/cgroup-v1/net_cls.txt*. + * + * 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. + * + * int 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 underlaying + * 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. + * + * int 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 underlaying + * 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. + * + * int 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. + * + * int 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. + * + * 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. + * + * int 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 be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * 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 + * indentifier 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. + * + * int bpf_perf_event_output(struct pt_reg *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. + * + * int bpf_skb_load_bytes(const struct sk_buff *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. + * + * int bpf_get_stackid(struct pt_reg *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= + * 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. + * + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *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. + * + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *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. + * + * int 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 underlaying + * 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. + * + * int 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. + * + * int 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) - * Returns current task_struct - * Return: current - * - * int bpf_probe_write_user(void *dst, void *src, int len) - * safely attempt to write to a location - * @dst: destination address in userspace - * @src: source address on stack - * @len: number of bytes to copy - * Return: 0 on success or negative error - * - * int bpf_current_task_under_cgroup(map, index) - * Check cgroup2 membership of current task - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 current failed the cgroup2 descendant test - * == 1 current succeeded the cgroup2 descendant test - * < 0 error - * - * int bpf_skb_change_tail(skb, len, flags) - * The helper will resize the skb to the given new size, to be used f.e. - * with control messages. - * @skb: pointer to skb - * @len: new skb length - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_pull_data(skb, len) - * The helper will pull in non-linear data in case the skb is non-linear - * and not all of len are part of the linear section. Only needed for - * read/write with direct packet access. - * @skb: pointer to skb - * @len: len to make read/writeable - * Return: 0 on success or negative error - * - * s64 bpf_csum_update(skb, csum) - * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. - * @skb: pointer to skb - * @csum: csum to add - * Return: csum on success or negative error - * - * void bpf_set_hash_invalid(skb) - * Invalidate current skb->hash. - * @skb: pointer to skb - * - * int bpf_get_numa_node_id() - * Return: Id of current NUMA node. - * - * int bpf_skb_change_head() - * Grows headroom of skb and adjusts MAC header offset accordingly. - * Will extends/reallocae as required automatically. - * May change skb data pointer and will thus invalidate any check - * performed for direct packet access. - * @skb: pointer to skb - * @len: length of header to be pushed in front - * @flags: Flags (unused for now) - * Return: 0 on success or negative error - * - * int bpf_xdp_adjust_head(xdp_md, delta) - * Adjust the xdp_md.data by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data - * Return: 0 on success or negative on error + * Return + * A pointer to the current task struct. + * + * int 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. + * + * int 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: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * int 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 underlaying + * 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. + * + * int 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 the whole length of the *skb* is pulled. + * + * 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 underlaying + * 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. + * + * int 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. + * + * int 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 underlaying + * 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. + * + * int 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 underlaying + * 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. * * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) - * Copy a NUL terminated string from unsafe address. In case the string - * length is smaller than size, the target is not padded with further NUL - * bytes. In case the string length is larger than size, just count-1 - * bytes are copied and the last byte is set to NUL. - * @dst: destination address - * @size: maximum number of bytes to copy, including the trailing NUL - * @unsafe_ptr: unsafe address - * Return: - * > 0 length of the string including the trailing NUL on success - * < 0 error - * - * u64 bpf_get_socket_cookie(skb) - * Get the cookie for the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: 8 Bytes non-decreasing number on success or 0 if the socket - * field is missing inside sk_buff - * - * u32 bpf_get_socket_uid(skb) - * Get the owner uid of the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: uid of the socket owner on success or overflowuid if failed. - * - * u32 bpf_set_hash(skb, hash) - * Set full skb->hash. - * @skb: pointer to skb - * @hash: hash to set - * - * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen) - * Calls setsockopt. Not all opts are available, only those with - * integer optvals plus TCP_CONGESTION. - * Supported levels: SOL_SOCKET and IPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: SOL_SOCKET or IPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in byes - * Return: 0 or negative error - * - * int bpf_skb_adjust_room(skb, len_diff, mode, flags) - * Grow or shrink room in sk_buff. - * @skb: pointer to skb - * @len_diff: (signed) amount of room to grow/shrink - * @mode: operation mode (enum bpf_adj_room_mode) - * @flags: reserved for future use - * Return: 0 on success or negative error code - * - * int bpf_sk_redirect_map(map, key, flags) - * Redirect skb to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_REDIRECT - * - * int bpf_sock_map_update(skops, map, key, flags) - * @skops: pointer to bpf_sock_ops - * @map: pointer to sockmap to update - * @key: key to insert/update sock in map - * @flags: same flags as map update elem + * Description + * Copy a NUL terminated string from an unsafe 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, the length of the copied string is returned. 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_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()** 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 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 unique socket + * identifier per namespace. + * Return + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + * + * u32 bpf_get_socket_uid(struct sk_buff *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). + * + * u32 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 + * + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *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*. + * + * 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**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_adjust_room(struct sk_buff *skb, u32 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*. + * + * There is a single supported mode at this time: + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * 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 underlaying + * 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. + * + * int bpf_redirect_map(struct bpf_map *map, u32 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). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * Return + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * + * int bpf_sk_redirect_map(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. + * + * int 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. + * + * int 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 underlaying + * 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. + * + * int 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 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. + * + * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For en 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. + * + * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *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*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_override_return(struct pt_reg *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 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 + * + * int 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. + * + * The supported callback values that *argval* can combine are: + * + * * **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) + * + * 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). + * + * int 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. + * + * int 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 + * + * int 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 + * + * int 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 underlaying + * 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. + * + * int 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**). Looking for a free port to bind to can be + * expensive, therefore binding to port is not permitted by the + * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) + * must be set to zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlaying + * 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. + * + * int 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. + * + * int bpf_get_stack(struct pt_regs *regs, 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 buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **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= + * Return + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. + * + * int bpf_skb_load_bytes_relative(const struct sk_buff *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. + * + * int 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_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). + * + * *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 + * + * int bpf_sock_hash_update(struct bpf_sock_ops_kern *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. + * + * int 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. + * + * int 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 verdeict 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. + * + * int 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. + * + * A call to this helper is susceptible to change the underlaying + * 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. + * + * int 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 underlaying + * 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. + * + * int 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 underlaying + * 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. + * + * int 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 underlaying + * 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. + * + * int 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 + * + * int 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 + * + * uint64_t 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) + * Return + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -638,6 +2131,33 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ + FN(xdp_adjust_meta), \ + FN(perf_event_read_value), \ + FN(perf_prog_read_value), \ + FN(getsockopt), \ + FN(override_return), \ + FN(sock_ops_cb_flags_set), \ + FN(msg_redirect_map), \ + FN(msg_apply_bytes), \ + FN(msg_cork_bytes), \ + FN(msg_pull_data), \ + FN(bind), \ + FN(xdp_adjust_tail), \ + FN(skb_get_xfrm_state), \ + FN(get_stack), \ + FN(skb_load_bytes_relative), \ + FN(fib_lookup), \ + FN(sock_hash_update), \ + FN(msg_redirect_hash), \ + FN(sk_redirect_hash), \ + FN(lwt_push_encap), \ + FN(lwt_seg6_store_bytes), \ + FN(lwt_seg6_adjust_srh), \ + FN(lwt_seg6_action), \ + FN(rc_repeat), \ + FN(rc_keydown), \ + FN(skb_cgroup_id), \ + FN(get_current_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -671,17 +2191,23 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) -/* BPF_FUNC_get_stackid flags. */ +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ #define BPF_F_SKIP_FIELD_MASK 0xffULL #define BPF_F_USER_STACK (1ULL << 8) +/* flags used by BPF_FUNC_get_stackid only. */ #define BPF_F_FAST_STACK_CMP (1ULL << 9) #define BPF_F_REUSE_STACKID (1ULL << 10) +/* flags used by BPF_FUNC_get_stack only. */ +#define BPF_F_USER_BUILD_ID (1ULL << 11) /* BPF_FUNC_skb_set_tunnel_key flags. */ #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) +#define BPF_F_SEQ_NUMBER (1ULL << 3) -/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ +/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and + * BPF_FUNC_perf_event_read_value flags. + */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK /* BPF_FUNC_perf_event_output for sk_buff input context. */ @@ -692,6 +2218,18 @@ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, }; +/* 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 +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -715,7 +2253,7 @@ struct __sk_buff { __u32 data_end; __u32 napi_id; - /* accessed by BPF_PROG_TYPE_sk_skb types */ + /* 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 */ @@ -723,6 +2261,9 @@ struct __sk_buff { __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; }; struct bpf_tunnel_key { @@ -733,10 +2274,24 @@ struct bpf_tunnel_key { }; __u8 tunnel_tos; __u8 tunnel_ttl; - __u16 tunnel_ext; + __u16 tunnel_ext; /* Padding, future use. */ __u32 tunnel_label; }; +/* 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 @@ -760,6 +2315,15 @@ struct bpf_sock { __u32 protocol; __u32 mark; __u32 priority; + __u32 src_ip4; /* Allows 1,2,4-byte read. + * Stored in network byte order. + */ + __u32 src_ip6[4]; /* Allows 1,2,4-byte read. + * Stored in network byte order. + */ + __u32 src_port; /* Allows 4-byte read. + * Stored in host byte order + */ }; #define XDP_PACKET_HEADROOM 256 @@ -783,12 +2347,31 @@ enum xdp_action { 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 */ }; enum sk_action { - SK_ABORTED = 0, - SK_DROP, - SK_REDIRECT, + 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 { + void *data; + 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 */ }; #define BPF_TAG_SIZE 8 @@ -801,6 +2384,19 @@ struct bpf_prog_info { __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; + __u64 netns_dev; + __u64 netns_ino; + __u32 nr_jited_ksyms; + __u32 nr_jited_func_lens; + __aligned_u64 jited_ksyms; + __aligned_u64 jited_func_lens; } __attribute__((aligned(8))); struct bpf_map_info { @@ -810,8 +2406,48 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 :32; + __u64 netns_dev; + __u64 netns_ino; + __u32 btf_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; +} __attribute__((aligned(8))); + +struct bpf_btf_info { + __aligned_u64 btf; + __u32 btf_size; + __u32 id; } __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 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-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 user_port; /* Allows 4-byte read and 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 an 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ +}; + /* 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 @@ -821,8 +2457,9 @@ struct bpf_map_info { struct bpf_sock_ops { __u32 op; union { - __u32 reply; - __u32 replylong[4]; + __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 */ @@ -831,8 +2468,45 @@ struct bpf_sock_ops { __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; }; +/* Definitions for bpf_sock_ops_cb_flags */ +#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) +#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) +#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently + * supported cb flags + */ + /* List of known BPF sock_ops operators. * New entries can only be added at the end */ @@ -859,9 +2533,156 @@ enum { 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. + */ +}; + +/* 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_MAX_STATES /* Leave at the end! */ }; #define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ #define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ +struct bpf_perf_event_value { + __u64 counter; + __u64 enabled; + __u64 running; +}; + +#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) +#define BPF_DEVCG_ACC_READ (1ULL << 1) +#define BPF_DEVCG_ACC_WRITE (1ULL << 2) + +#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) +#define 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 + */ +#define BPF_FIB_LOOKUP_DIRECT BIT(0) +#define BPF_FIB_LOOKUP_OUTPUT BIT(1) + +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 */ +}; + +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; + + /* total length of packet from network header - used for MTU check */ + __u16 tot_len; + + /* 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; + }; + + 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 */ + }; + + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ +}; + +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 */ +}; + #endif /* __LINUX_BPF_H__ */ diff --git a/include/uapi/linux/bpf_common.h b/include/uapi/linux/bpf_common.h index afe7433..f0fe139 100644 --- a/include/uapi/linux/bpf_common.h +++ b/include/uapi/linux/bpf_common.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BPF_COMMON_H__ #define __LINUX_BPF_COMMON_H__ @@ -14,9 +15,10 @@ /* ld/ldx fields */ #define BPF_SIZE(code) ((code) & 0x18) -#define BPF_W 0x00 -#define BPF_H 0x08 -#define BPF_B 0x10 +#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 diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h new file mode 100644 index 0000000..5dd580a --- /dev/null +++ b/include/uapi/linux/btf.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2018 Facebook */ +#ifndef __LINUX_BTF_H__ +#define __LINUX_BTF_H__ + +#include + +#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 0x0000ffff +/* Max offset into the string section */ +#define BTF_MAX_NAME_OFFSET 0x0000ffff +/* 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 24-27: kind (e.g. int, ptr, array...etc) + * bits 28-31: unused + */ + __u32 info; + /* "size" is used by INT, ENUM, STRUCT and UNION. + * "size" tells the size of the type it is describing. + * + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT. + * "type" is a type_id referring to another type. + */ + union { + __u32 size; + __u32 type; + }; +}; + +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f) +#define BTF_INFO_VLEN(info) ((info) & 0xffff) + +#define BTF_KIND_UNKN 0 /* Unknown */ +#define BTF_KIND_INT 1 /* Integer */ +#define BTF_KIND_PTR 2 /* Pointer */ +#define BTF_KIND_ARRAY 3 /* Array */ +#define BTF_KIND_STRUCT 4 /* Struct */ +#define BTF_KIND_UNION 5 /* Union */ +#define BTF_KIND_ENUM 6 /* Enumeration */ +#define BTF_KIND_FWD 7 /* Forward */ +#define BTF_KIND_TYPEDEF 8 /* Typedef */ +#define BTF_KIND_VOLATILE 9 /* Volatile */ +#define BTF_KIND_CONST 10 /* Const */ +#define BTF_KIND_RESTRICT 11 /* Restrict */ +#define BTF_KIND_MAX 11 +#define NR_BTF_KINDS 12 + +/* 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) & 0x0000ffff) + +/* 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; + __u32 offset; /* offset in bits */ +}; + +#endif /* __LINUX_BTF_H__ */ diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index f7a810d..4d1ab8e 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can.h * diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index b9214bd..f0c5e58 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/can/netlink.h * @@ -131,6 +132,7 @@ enum { IFLA_CAN_TERMINATION_CONST, IFLA_CAN_BITRATE_CONST, IFLA_CAN_DATA_BITRATE_CONST, + IFLA_CAN_BITRATE_MAX, __IFLA_CAN_MAX }; diff --git a/include/uapi/linux/can/vxcan.h b/include/uapi/linux/can/vxcan.h index 5b29e8a..b364d77 100644 --- a/include/uapi/linux/can/vxcan.h +++ b/include/uapi/linux/can/vxcan.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _CAN_VXCAN_H #define _CAN_VXCAN_H diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index a62695e..5ee0e73 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -1,3 +1,4 @@ +/* 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. @@ -69,6 +70,24 @@ enum devlink_command { 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, /* add new commands above here */ __DEVLINK_CMD_MAX, @@ -124,6 +143,26 @@ enum devlink_eswitch_encap_mode { 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. + */ +}; + +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_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, @@ -201,6 +240,45 @@ enum devlink_attr { 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 */ /* add new attributes above here, update the policy in devlink.c */ @@ -244,4 +322,8 @@ enum devlink_dpipe_header_id { DEVLINK_DPIPE_HEADER_IPV6, }; +enum devlink_resource_unit { + DEVLINK_RESOURCE_UNIT_ENTRY, +}; + #endif /* _LINUX_DEVLINK_H_ */ diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h index 9cd1de9..31aa101 100644 --- a/include/uapi/linux/elf-em.h +++ b/include/uapi/linux/elf-em.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_ELF_EM_H #define _LINUX_ELF_EM_H diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index bbf02a6..232df14 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_FIB_RULES_H #define __LINUX_FIB_RULES_H @@ -22,7 +23,7 @@ struct fib_rule_hdr { __u8 tos; __u8 table; - __u8 res1; /* reserved */ + __u8 res1; /* reserved */ __u8 res2; /* reserved */ __u8 action; @@ -34,6 +35,11 @@ struct fib_rule_uid_range { __u32 end; }; +struct fib_rule_port_range { + __u16 start; + __u16 end; +}; + enum { FRA_UNSPEC, FRA_DST, /* destination address */ @@ -57,6 +63,10 @@ enum { 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 }; diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h index e4f2f74..eaef459 100644 --- a/include/uapi/linux/filter.h +++ b/include/uapi/linux/filter.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Linux Socket Filter Data Structures */ diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h index 744c323..bf022c6 100644 --- a/include/uapi/linux/fou.h +++ b/include/uapi/linux/fou.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* fou.h - FOU Interface */ #ifndef _LINUX_FOU_H diff --git a/include/uapi/linux/gen_stats.h b/include/uapi/linux/gen_stats.h index 52deccc..24a861c 100644 --- a/include/uapi/linux/gen_stats.h +++ b/include/uapi/linux/gen_stats.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_GEN_STATS_H #define __LINUX_GEN_STATS_H diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h index 08239d8..1317119 100644 --- a/include/uapi/linux/genetlink.h +++ b/include/uapi/linux/genetlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_GENERIC_NETLINK_H #define __LINUX_GENERIC_NETLINK_H diff --git a/include/uapi/linux/hdlc/ioctl.h b/include/uapi/linux/hdlc/ioctl.h index 04bc027..0fe4238 100644 --- a/include/uapi/linux/hdlc/ioctl.h +++ b/include/uapi/linux/hdlc/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __HDLC_IOCTL_H__ #define __HDLC_IOCTL_H__ diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index a2e839e..cb247a5 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_ICMPV6_H #define _LINUX_ICMPV6_H diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index b4ba020..495cdd2 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -1,3 +1,4 @@ +/* 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 diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index 26f0ecf..a924606 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_IF_ADDR_H #define __LINUX_IF_ADDR_H @@ -32,6 +33,7 @@ enum { IFA_CACHEINFO, IFA_MULTICAST, IFA_FLAGS, + IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ __IFA_MAX, }; diff --git a/include/uapi/linux/if_addrlabel.h b/include/uapi/linux/if_addrlabel.h index 54580c2..d1f5974 100644 --- a/include/uapi/linux/if_addrlabel.h +++ b/include/uapi/linux/if_addrlabel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * if_addrlabel.h - netlink interface for address labels * diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h index f2acd2f..bc2bcde 100644 --- a/include/uapi/linux/if_alg.h +++ b/include/uapi/linux/if_alg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * if_alg: User-space algorithm interface * diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h index 199f253..cd136a6 100644 --- a/include/uapi/linux/if_arp.h +++ b/include/uapi/linux/if_arp.h @@ -1,3 +1,4 @@ +/* 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 diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h index 9635a62..61a1bf6 100644 --- a/include/uapi/linux/if_bonding.h +++ b/include/uapi/linux/if_bonding.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. * diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 156f443..bdfecf9 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Linux ethernet bridge * diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 7dde037..8c36f63 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -1,3 +1,4 @@ +/* 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 @@ -29,6 +30,7 @@ */ #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 */ @@ -46,6 +48,7 @@ #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 */ @@ -86,6 +89,7 @@ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #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_MACSEC 0x88E5 /* 802.1ae MACsec */ #define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */ @@ -148,11 +152,18 @@ * 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_link.h b/include/uapi/linux/if_link.h index 1f97d05..1c64ed4 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_IF_LINK_H #define _LINUX_IF_LINK_H @@ -158,6 +159,11 @@ enum { IFLA_PAD, IFLA_XDP, IFLA_EVENT, + IFLA_NEW_NETNSID, + IFLA_IF_NETNSID, + IFLA_CARRIER_UP_COUNT, + IFLA_CARRIER_DOWN_COUNT, + IFLA_NEW_IFINDEX, __IFLA_MAX }; @@ -323,6 +329,9 @@ enum { 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_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -460,6 +469,7 @@ enum macsec_validation_type { enum { IFLA_IPVLAN_UNSPEC, IFLA_IPVLAN_MODE, + IFLA_IPVLAN_FLAGS, __IFLA_IPVLAN_MAX }; @@ -472,6 +482,9 @@ enum ipvlan_mode { IPVLAN_MODE_MAX }; +#define IPVLAN_F_PRIVATE 0x01 +#define IPVLAN_F_VEPA 0x02 + /* VXLAN section */ enum { IFLA_VXLAN_UNSPEC, @@ -502,6 +515,7 @@ enum { IFLA_VXLAN_COLLECT_METADATA, IFLA_VXLAN_LABEL, IFLA_VXLAN_GPE, + IFLA_VXLAN_TTL_INHERIT, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) @@ -721,6 +735,8 @@ enum { 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, }; @@ -902,6 +918,7 @@ enum { XDP_ATTACHED_DRV, XDP_ATTACHED_SKB, XDP_ATTACHED_HW, + XDP_ATTACHED_MULTI, }; enum { @@ -910,6 +927,9 @@ enum { 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_MAX, }; @@ -925,4 +945,43 @@ enum { 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) + +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; +}; + #endif /* _LINUX_IF_LINK_H */ diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h index 22939a3..7743993 100644 --- a/include/uapi/linux/if_macsec.h +++ b/include/uapi/linux/if_macsec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * include/uapi/linux/if_macsec.h - MACsec device * @@ -21,8 +22,13 @@ #define MACSEC_KEYID_LEN 16 -#define MACSEC_DEFAULT_CIPHER_ID 0x0080020001000001ULL -#define MACSEC_DEFAULT_CIPHER_ALT 0x0080C20001000001ULL +/* cipher IDs as per IEEE802.1AEbn-2011 */ +#define MACSEC_CIPHER_ID_GCM_AES_128 0x0080C20001000001ULL +#define MACSEC_CIPHER_ID_GCM_AES_256 0x0080C20001000002ULL + +/* 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 diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 4df96a7..67b61d9 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_IF_PACKET_H #define __LINUX_IF_PACKET_H diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index d5ecb42..be9b744 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Universal TUN/TAP device driver. * Copyright (C) 1999-2000 Maxim Krasnyansky @@ -56,10 +57,14 @@ */ #define TUNSETVNETBE _IOW('T', 222, int) #define TUNGETVNETBE _IOR('T', 223, int) +#define TUNSETSTEERINGEBPF _IOR('T', 224, int) +#define TUNSETFILTEREBPF _IOR('T', 225, int) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 #define IFF_TAP 0x0002 +#define IFF_NAPI 0x0010 +#define IFF_NAPI_FRAGS 0x0020 #define IFF_NO_PI 0x1000 /* This flag has no real effect */ #define IFF_ONE_QUEUE 0x2000 diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 21834ca..ecdc766 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IF_TUNNEL_H_ #define _IF_TUNNEL_H_ @@ -84,6 +85,7 @@ enum tunnel_encap_types { TUNNEL_ENCAP_NONE, TUNNEL_ENCAP_FOU, TUNNEL_ENCAP_GUE, + TUNNEL_ENCAP_MPLS, }; #define TUNNEL_ENCAP_FLAG_CSUM (1<<0) @@ -135,6 +137,9 @@ enum { 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, }; diff --git a/include/uapi/linux/if_vlan.h b/include/uapi/linux/if_vlan.h index 24ae007..18a15da 100644 --- a/include/uapi/linux/if_vlan.h +++ b/include/uapi/linux/if_vlan.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * VLAN An implementation of 802.1Q VLAN tagging. * diff --git a/include/uapi/linux/ife.h b/include/uapi/linux/ife.h index 2954da3..bdd953c 100644 --- a/include/uapi/linux/ife.h +++ b/include/uapi/linux/ife.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UAPI_IFE_H #define __UAPI_IFE_H diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h index 7e328d7..6a6c97c 100644 --- a/include/uapi/linux/ila.h +++ b/include/uapi/linux/ila.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ila.h - ILA Interface */ #ifndef _LINUX_ILA_H @@ -16,6 +17,8 @@ enum { 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, }; @@ -27,6 +30,7 @@ enum { ILA_CMD_ADD, ILA_CMD_DEL, ILA_CMD_GET, + ILA_CMD_FLUSH, __ILA_CMD_MAX, }; @@ -40,6 +44,25 @@ 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 index 9439efa..a4f143b 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -1,3 +1,4 @@ +/* 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 diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 6f3bdee..409bb3f 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Types and definitions for AF_INET6 * Linux INET6 implementation @@ -284,6 +285,7 @@ struct in6_flowlabel_req { #define IPV6_TRANSPARENT 75 #define IPV6_UNICAST_IF 76 #define IPV6_RECVFRAGSIZE 77 +#define IPV6_FREEBIND 78 /* * Multicast Routing: diff --git a/include/uapi/linux/in_route.h b/include/uapi/linux/in_route.h index b261b8c..0cc2c23 100644 --- a/include/uapi/linux/in_route.h +++ b/include/uapi/linux/in_route.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_IN_ROUTE_H #define _LINUX_IN_ROUTE_H diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index bada4d7..f98d82d 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _INET_DIAG_H_ #define _INET_DIAG_H_ @@ -91,6 +92,8 @@ enum { 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, }; struct inet_diag_hostcond { diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 1907284..883fd33 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -1,3 +1,4 @@ +/* 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 diff --git a/include/uapi/linux/ip6_tunnel.h b/include/uapi/linux/ip6_tunnel.h index 425926c..0245269 100644 --- a/include/uapi/linux/ip6_tunnel.h +++ b/include/uapi/linux/ip6_tunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IP6_TUNNEL_H #define _IP6_TUNNEL_H @@ -20,6 +21,8 @@ #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 */ diff --git a/include/uapi/linux/ipsec.h b/include/uapi/linux/ipsec.h index d17a630..50d8ee1 100644 --- a/include/uapi/linux/ipsec.h +++ b/include/uapi/linux/ipsec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_IPSEC_H #define _LINUX_IPSEC_H diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h index 527549f..d99ffa1 100644 --- a/include/uapi/linux/kernel.h +++ b/include/uapi/linux/kernel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index 8a80007..1fe52a7 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * L2TP-over-IP socket for L2TPv3. * @@ -64,7 +65,7 @@ struct sockaddr_l2tpip6 { * TUNNEL_MODIFY - CONN_ID, udpcsum * TUNNEL_GETSTATS - CONN_ID, (stats) * TUNNEL_GET - CONN_ID, (...) - * SESSION_CREATE - SESSION_ID, PW_TYPE, offset, data_seq, cookie, peer_cookie, offset, l2spec + * SESSION_CREATE - SESSION_ID, PW_TYPE, data_seq, cookie, peer_cookie, l2spec * SESSION_DELETE - SESSION_ID * SESSION_MODIFY - SESSION_ID, data_seq * SESSION_GET - SESSION_ID, (...) @@ -93,10 +94,10 @@ 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 */ + L2TP_ATTR_OFFSET, /* u16 (not used) */ L2TP_ATTR_DATA_SEQ, /* u16 */ L2TP_ATTR_L2SPEC_TYPE, /* u8, enum l2tp_l2spec_type */ - L2TP_ATTR_L2SPEC_LEN, /* 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 */ diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index f38571d..a159991 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Compatibility interface for userspace libc header coordination: * @@ -167,46 +168,99 @@ /* 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. */ + * 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__ */ diff --git a/include/uapi/linux/limits.h b/include/uapi/linux/limits.h index 2d0f941..c3547f0 100644 --- a/include/uapi/linux/limits.h +++ b/include/uapi/linux/limits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_LIMITS_H #define _LINUX_LIMITS_H diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index 3298426..3f3fe6f 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LWTUNNEL_H_ #define _LWTUNNEL_H_ diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index e439565..1a6fee9 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_MAGIC_H__ #define __LINUX_MAGIC_H__ @@ -46,6 +47,7 @@ #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 diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h index bf5b625..9effbf9 100644 --- a/include/uapi/linux/mpls.h +++ b/include/uapi/linux/mpls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _MPLS_H #define _MPLS_H diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h index 1a0e57b..2c69b7d 100644 --- a/include/uapi/linux/mpls_iptunnel.h +++ b/include/uapi/linux/mpls_iptunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * mpls tunnel api * diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 3199d28..904db61 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_NEIGHBOUR_H #define __LINUX_NEIGHBOUR_H diff --git a/include/uapi/linux/net_namespace.h b/include/uapi/linux/net_namespace.h index 9a92b7e..6d64d07 100644 --- a/include/uapi/linux/net_namespace.h +++ b/include/uapi/linux/net_namespace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Copyright (c) 2015 6WIND S.A. * Author: Nicolas Dichtel * diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h index 4afbd7d..86ac1eb 100644 --- a/include/uapi/linux/netconf.h +++ b/include/uapi/linux/netconf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_NETCONF_H_ #define _LINUX_NETCONF_H_ diff --git a/include/uapi/linux/netdevice.h b/include/uapi/linux/netdevice.h index 66fceb4..86d961c 100644 --- a/include/uapi/linux/netdevice.h +++ b/include/uapi/linux/netdevice.h @@ -1,3 +1,4 @@ +/* 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 diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h index ff4a4a5..36378a0 100644 --- a/include/uapi/linux/netfilter.h +++ b/include/uapi/linux/netfilter.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_NETFILTER_H #define __LINUX_NETFILTER_H diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index a6c96b0..13eeada 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Copyright (C) 2000-2002 Joakim Axelsson * Patrick Schaaf * Martin Josefsson diff --git a/include/uapi/linux/netfilter/x_tables.h b/include/uapi/linux/netfilter/x_tables.h index 4120970..ae2fd12 100644 --- a/include/uapi/linux/netfilter/x_tables.h +++ b/include/uapi/linux/netfilter/x_tables.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _X_TABLES_H #define _X_TABLES_H #include diff --git a/include/uapi/linux/netfilter/xt_set.h b/include/uapi/linux/netfilter/xt_set.h index d4e0234..8c1ca66 100644 --- a/include/uapi/linux/netfilter/xt_set.h +++ b/include/uapi/linux/netfilter/xt_set.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_SET_H #define _XT_SET_H diff --git a/include/uapi/linux/netfilter/xt_tcpudp.h b/include/uapi/linux/netfilter/xt_tcpudp.h index 38aa7b3..658c169 100644 --- a/include/uapi/linux/netfilter/xt_tcpudp.h +++ b/include/uapi/linux/netfilter/xt_tcpudp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_TCPUDP_H #define _XT_TCPUDP_H diff --git a/include/uapi/linux/netfilter_ipv4.h b/include/uapi/linux/netfilter_ipv4.h index a5f4dc7..074e2c8 100644 --- a/include/uapi/linux/netfilter_ipv4.h +++ b/include/uapi/linux/netfilter_ipv4.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* IPv4-specific defines for netfilter. * (C)1998 Rusty Russell -- This code is GPL. */ @@ -54,6 +55,7 @@ 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, diff --git a/include/uapi/linux/netfilter_ipv4/ip_tables.h b/include/uapi/linux/netfilter_ipv4/ip_tables.h index 456fb86..409cff7 100644 --- a/include/uapi/linux/netfilter_ipv4/ip_tables.h +++ b/include/uapi/linux/netfilter_ipv4/ip_tables.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * 25-Jul-1998 Major changes to allow for ip chain table * diff --git a/include/uapi/linux/netfilter_ipv6.h b/include/uapi/linux/netfilter_ipv6.h index 8483d1d..92701fe 100644 --- a/include/uapi/linux/netfilter_ipv6.h +++ b/include/uapi/linux/netfilter_ipv6.h @@ -1,3 +1,4 @@ +/* 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 @@ -59,6 +60,7 @@ 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, diff --git a/include/uapi/linux/netfilter_ipv6/ip6_tables.h b/include/uapi/linux/netfilter_ipv6/ip6_tables.h index fcc8cca..7ae314b 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6_tables.h +++ b/include/uapi/linux/netfilter_ipv6/ip6_tables.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * 25-Jul-1998 Major changes to allow for ip chain table * diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index ec0690b..0b2c29b 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_NETLINK_H #define __LINUX_NETLINK_H diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h index c8c8c7d..4cd0657 100644 --- a/include/uapi/linux/netlink_diag.h +++ b/include/uapi/linux/netlink_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __NETLINK_DIAG_H__ #define __NETLINK_DIAG_H__ diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h index 0c5d5dd..349ddf0 100644 --- a/include/uapi/linux/packet_diag.h +++ b/include/uapi/linux/packet_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __PACKET_DIAG_H__ #define __PACKET_DIAG_H__ diff --git a/include/uapi/linux/param.h b/include/uapi/linux/param.h index 092e92f..94e0c57 100644 --- a/include/uapi/linux/param.h +++ b/include/uapi/linux/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_PARAM_H #define _LINUX_PARAM_H diff --git a/include/uapi/linux/pfkeyv2.h b/include/uapi/linux/pfkeyv2.h index ada7f01..d65b117 100644 --- a/include/uapi/linux/pfkeyv2.h +++ b/include/uapi/linux/pfkeyv2.h @@ -1,3 +1,4 @@ +/* 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. diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index d5e2bf6..b451225 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_PKT_CLS_H #define __LINUX_PKT_CLS_H @@ -128,6 +129,7 @@ enum { #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 */ @@ -467,6 +469,15 @@ enum { 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_MAX, }; @@ -474,6 +485,7 @@ enum { enum { TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), + TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), }; /* Match-all classifier */ @@ -554,7 +566,8 @@ enum { #define TCF_EM_VLAN 6 #define TCF_EM_CANID 7 #define TCF_EM_IPSET 8 -#define TCF_EM_MAX 8 +#define TCF_EM_IPT 9 +#define TCF_EM_MAX 9 enum { TCF_EM_PROG_TC diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 099bf55..d9cc9dc 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_PKT_SCHED_H #define __LINUX_PKT_SCHED_H @@ -74,6 +75,7 @@ struct tc_estimator { #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 @@ -534,6 +536,10 @@ enum { TCA_NETEM_ECN, TCA_NETEM_RATE64, TCA_NETEM_PAD, + TCA_NETEM_LATENCY64, + TCA_NETEM_JITTER64, + TCA_NETEM_SLOT, + TCA_NETEM_SLOT_DIST, __TCA_NETEM_MAX, }; @@ -571,6 +577,15 @@ struct tc_netem_rate { __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 */ @@ -625,6 +640,22 @@ enum { #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) + struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; @@ -633,6 +664,22 @@ struct tc_mqprio_qopt { __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_UNSPEC, + TCA_MQPRIO_MODE, + TCA_MQPRIO_SHAPER, + TCA_MQPRIO_MIN_RATE64, + TCA_MQPRIO_MAX_RATE64, + __TCA_MQPRIO_MAX, +}; + +#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1) + /* SFB */ enum { @@ -871,4 +918,155 @@ struct tc_pie_xstats { __u32 maxq; /* maximum queue size */ __u32 ecn_mark; /* packets marked with ecn*/ }; + +/* 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 BIT(0) +#define TC_ETF_OFFLOAD_ON BIT(1) +}; + +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_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 +}; + #endif diff --git a/include/uapi/linux/posix_types.h b/include/uapi/linux/posix_types.h index 988f76e..9a7a740 100644 --- a/include/uapi/linux/posix_types.h +++ b/include/uapi/linux/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_POSIX_TYPES_H #define _LINUX_POSIX_TYPES_H diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 813e9e0..c3a7d8e 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_RTNETLINK_H #define __LINUX_RTNETLINK_H @@ -253,6 +254,11 @@ enum { #define RTPROT_DHCP 16 /* DHCP client */ #define RTPROT_MROUTED 17 /* Multicast daemon */ #define RTPROT_BABEL 42 /* Babel daemon */ +#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 @@ -326,6 +332,9 @@ enum rtattr_type_t { RTA_PAD, RTA_UID, RTA_TTL_PROPAGATE, + RTA_IP_PROTO, + RTA_SPORT, + RTA_DPORT, __RTA_MAX }; @@ -430,6 +439,8 @@ enum { #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 }; @@ -538,9 +549,19 @@ struct tcmsg { 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, @@ -554,6 +575,9 @@ enum { TCA_PAD, TCA_DUMP_INVISIBLE, TCA_CHAIN, + TCA_HW_OFFLOAD, + TCA_INGRESS_BLOCK, + TCA_EGRESS_BLOCK, __TCA_MAX }; diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index fec24c4..dd164d7 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -1,3 +1,4 @@ +/* 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. @@ -98,6 +99,8 @@ typedef __s32 sctp_assoc_t; #define SCTP_RECVRCVINFO 32 #define SCTP_RECVNXTINFO 33 #define SCTP_DEFAULT_SNDINFO 34 +#define SCTP_AUTH_DEACTIVATE_KEY 35 +#define SCTP_REUSE_PORT 36 /* Internal Socket Options. Some of the sctp library functions are * implemented using these socket options. @@ -122,6 +125,10 @@ typedef __s32 sctp_assoc_t; #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 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -256,6 +263,31 @@ struct sctp_nxtinfo { 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) * @@ -267,6 +299,8 @@ enum sctp_sinfo_flags { 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_NOTIFICATION = MSG_NOTIFICATION, /* Next message is not user msg but notification. */ SCTP_EOF = MSG_FIN, /* Initiate graceful shutdown process. */ }; @@ -289,6 +323,14 @@ typedef enum sctp_cmsg_type { #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; /* @@ -376,7 +418,7 @@ struct sctp_remote_error { __u16 sre_type; __u16 sre_flags; __u32 sre_length; - __u16 sre_error; + __be16 sre_error; sctp_assoc_t sre_assoc_id; __u8 sre_data[0]; }; @@ -456,6 +498,8 @@ struct sctp_pdapi_event { __u32 pdapi_length; __u32 pdapi_indication; sctp_assoc_t pdapi_assoc_id; + __u32 pdapi_stream; + __u32 pdapi_seq; }; enum { SCTP_PARTIAL_DELIVERY_ABORTED=0, }; @@ -476,7 +520,12 @@ struct sctp_authkey_event { sctp_assoc_t auth_assoc_id; }; -enum { SCTP_AUTH_NEWKEY = 0, }; +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 @@ -714,6 +763,8 @@ enum sctp_spp_flags { 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 { @@ -724,6 +775,8 @@ struct sctp_paddrparams { __u32 spp_pathmtu; __u32 spp_sackdelay; __u32 spp_flags; + __u32 spp_ipv6_flowlabel; + __u8 spp_dscp; } __attribute__((packed, aligned(4))); /* @@ -812,6 +865,12 @@ struct sctp_assoc_value { 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 * @@ -1082,4 +1141,12 @@ struct sctp_add_streams { uint16_t sas_outstrms; }; +/* SCTP Stream schedulers */ +enum sctp_sched_type { + SCTP_SS_FCFS, + SCTP_SS_PRIO, + SCTP_SS_RR, + SCTP_SS_MAX = SCTP_SS_RR +}; + #endif /* _SCTP_H */ diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h index 0715279..329163e 100644 --- a/include/uapi/linux/seg6.h +++ b/include/uapi/linux/seg6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * SR-IPv6 implementation * @@ -25,9 +26,9 @@ struct ipv6_sr_hdr { __u8 hdrlen; __u8 type; __u8 segments_left; - __u8 first_segment; + __u8 first_segment; /* Represents the last_entry field of SRH */ __u8 flags; - __u16 reserved; + __u16 tag; struct in6_addr segments[0]; }; diff --git a/include/uapi/linux/seg6_genl.h b/include/uapi/linux/seg6_genl.h index 99382f9..0c23052 100644 --- a/include/uapi/linux/seg6_genl.h +++ b/include/uapi/linux/seg6_genl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_SEG6_GENL_H #define _LINUX_SEG6_GENL_H diff --git a/include/uapi/linux/seg6_hmac.h b/include/uapi/linux/seg6_hmac.h index 704f93e..3fb3412 100644 --- a/include/uapi/linux/seg6_hmac.h +++ b/include/uapi/linux/seg6_hmac.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_SEG6_HMAC_H #define _LINUX_SEG6_HMAC_H diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h index a5dc05a..3004e98 100644 --- a/include/uapi/linux/seg6_iptunnel.h +++ b/include/uapi/linux/seg6_iptunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * SR-IPv6 implementation * diff --git a/include/uapi/linux/seg6_local.h b/include/uapi/linux/seg6_local.h index 76b90d6..5312de8 100644 --- a/include/uapi/linux/seg6_local.h +++ b/include/uapi/linux/seg6_local.h @@ -25,6 +25,7 @@ enum { SEG6_LOCAL_NH6, SEG6_LOCAL_IIF, SEG6_LOCAL_OIF, + SEG6_LOCAL_BPF, __SEG6_LOCAL_MAX, }; #define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1) @@ -59,10 +60,21 @@ enum { 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, __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) + #endif diff --git a/include/uapi/linux/sock_diag.h b/include/uapi/linux/sock_diag.h index 901231e..a69cf20 100644 --- a/include/uapi/linux/sock_diag.h +++ b/include/uapi/linux/sock_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index 8c1e501..268b948 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_SOCKET_H #define _LINUX_SOCKET_H diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h index 79d029d..d393e9e 100644 --- a/include/uapi/linux/sockios.h +++ b/include/uapi/linux/sockios.h @@ -1,3 +1,4 @@ +/* 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 diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 4bb69de..23e025f 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __always_inline diff --git a/include/uapi/linux/sysinfo.h b/include/uapi/linux/sysinfo.h index 934335a..435d5c2 100644 --- a/include/uapi/linux/sysinfo.h +++ b/include/uapi/linux/sysinfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_SYSINFO_H #define _LINUX_SYSINFO_H diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h index 8dc2ac0..6e89a5d 100644 --- a/include/uapi/linux/tc_act/tc_bpf.h +++ b/include/uapi/linux/tc_act/tc_bpf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2015 Jiri Pirko * diff --git a/include/uapi/linux/tc_act/tc_connmark.h b/include/uapi/linux/tc_act/tc_connmark.h index 62a5e94..80caa47 100644 --- a/include/uapi/linux/tc_act/tc_connmark.h +++ b/include/uapi/linux/tc_act/tc_connmark.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UAPI_TC_CONNMARK_H #define __UAPI_TC_CONNMARK_H diff --git a/include/uapi/linux/tc_act/tc_csum.h b/include/uapi/linux/tc_act/tc_csum.h index a11bb35..0ecf4d2 100644 --- a/include/uapi/linux/tc_act/tc_csum.h +++ b/include/uapi/linux/tc_act/tc_csum.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_CSUM_H #define __LINUX_TC_CSUM_H diff --git a/include/uapi/linux/tc_act/tc_defact.h b/include/uapi/linux/tc_act/tc_defact.h index d2a3abb..e3ecd8b 100644 --- a/include/uapi/linux/tc_act/tc_defact.h +++ b/include/uapi/linux/tc_act/tc_defact.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_DEF_H #define __LINUX_TC_DEF_H diff --git a/include/uapi/linux/tc_act/tc_gact.h b/include/uapi/linux/tc_act/tc_gact.h index 70b536a..94273c3 100644 --- a/include/uapi/linux/tc_act/tc_gact.h +++ b/include/uapi/linux/tc_act/tc_gact.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_GACT_H #define __LINUX_TC_GACT_H diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h index 7c28178..2f48490 100644 --- a/include/uapi/linux/tc_act/tc_ife.h +++ b/include/uapi/linux/tc_act/tc_ife.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UAPI_TC_IFE_H #define __UAPI_TC_IFE_H diff --git a/include/uapi/linux/tc_act/tc_ipt.h b/include/uapi/linux/tc_act/tc_ipt.h index 7c6e155..b743c8b 100644 --- a/include/uapi/linux/tc_act/tc_ipt.h +++ b/include/uapi/linux/tc_act/tc_ipt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_IPT_H #define __LINUX_TC_IPT_H diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h index 3d7a2b3..5dd671c 100644 --- a/include/uapi/linux/tc_act/tc_mirred.h +++ b/include/uapi/linux/tc_act/tc_mirred.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_MIR_H #define __LINUX_TC_MIR_H @@ -9,13 +10,13 @@ #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, @@ -24,5 +25,5 @@ enum { __TCA_MIRRED_MAX }; #define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1) - + #endif diff --git a/include/uapi/linux/tc_act/tc_nat.h b/include/uapi/linux/tc_act/tc_nat.h index 923457c..086be84 100644 --- a/include/uapi/linux/tc_act/tc_nat.h +++ b/include/uapi/linux/tc_act/tc_nat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_NAT_H #define __LINUX_TC_NAT_H diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h index 143d2b3..24ec792 100644 --- a/include/uapi/linux/tc_act/tc_pedit.h +++ b/include/uapi/linux/tc_act/tc_pedit.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_PED_H #define __LINUX_TC_PED_H @@ -16,13 +17,15 @@ enum { 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 @@ -37,6 +40,7 @@ enum pedit_header_type { 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 { @@ -44,6 +48,7 @@ enum pedit_cmd { TCA_PEDIT_KEY_EX_CMD_ADD = 1, __PEDIT_CMD_MAX, }; + #define TCA_PEDIT_CMD_MAX (__PEDIT_CMD_MAX - 1) struct tc_pedit_key { @@ -54,13 +59,14 @@ struct tc_pedit_key { __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 index edc9058..bd7e9f0 100644 --- a/include/uapi/linux/tc_act/tc_sample.h +++ b/include/uapi/linux/tc_act/tc_sample.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_SAMPLE_H #define __LINUX_TC_SAMPLE_H diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h index 2884425..6de6071 100644 --- a/include/uapi/linux/tc_act/tc_skbedit.h +++ b/include/uapi/linux/tc_act/tc_skbedit.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2008, Intel Corporation. * @@ -29,6 +30,7 @@ #define SKBEDIT_F_MARK 0x4 #define SKBEDIT_F_PTYPE 0x8 #define SKBEDIT_F_MASK 0x10 +#define SKBEDIT_F_INHERITDSFIELD 0x20 struct tc_skbedit { tc_gen; @@ -44,6 +46,7 @@ enum { TCA_SKBEDIT_PAD, TCA_SKBEDIT_PTYPE, TCA_SKBEDIT_MASK, + TCA_SKBEDIT_FLAGS, __TCA_SKBEDIT_MAX }; #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1) diff --git a/include/uapi/linux/tc_act/tc_skbmod.h b/include/uapi/linux/tc_act/tc_skbmod.h index 10fc07d..38c072f 100644 --- a/include/uapi/linux/tc_act/tc_skbmod.h +++ b/include/uapi/linux/tc_act/tc_skbmod.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2016, Jamal Hadi Salim * diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h index afcd4be..be384d6 100644 --- a/include/uapi/linux/tc_act/tc_tunnel_key.h +++ b/include/uapi/linux/tc_act/tc_tunnel_key.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2016, Amir Vadai * Copyright (c) 2016, Mellanox Technologies. All rights reserved. @@ -35,9 +36,37 @@ enum { 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_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_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) + #endif diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h index bddb272..0d7b5fd 100644 --- a/include/uapi/linux/tc_act/tc_vlan.h +++ b/include/uapi/linux/tc_act/tc_vlan.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2014 Jiri Pirko * diff --git a/include/uapi/linux/tc_ematch/tc_em_cmp.h b/include/uapi/linux/tc_ematch/tc_em_cmp.h index f34bb1b..2549d9d 100644 --- a/include/uapi/linux/tc_ematch/tc_em_cmp.h +++ b/include/uapi/linux/tc_ematch/tc_em_cmp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_EM_CMP_H #define __LINUX_TC_EM_CMP_H 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 +#include + +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 index b11f8ce..cf30b5b 100644 --- a/include/uapi/linux/tc_ematch/tc_em_meta.h +++ b/include/uapi/linux/tc_ematch/tc_em_meta.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_EM_META_H #define __LINUX_TC_EM_META_H diff --git a/include/uapi/linux/tc_ematch/tc_em_nbyte.h b/include/uapi/linux/tc_ematch/tc_em_nbyte.h index 7172cfb..c76333f 100644 --- a/include/uapi/linux/tc_ematch/tc_em_nbyte.h +++ b/include/uapi/linux/tc_ematch/tc_em_nbyte.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_EM_NBYTE_H #define __LINUX_TC_EM_NBYTE_H diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 8edad3f..2e766cf 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -1,3 +1,4 @@ +/* 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 @@ -119,6 +120,12 @@ enum { #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 struct tcp_repair_opt { __u32 opt_code; @@ -221,6 +228,9 @@ struct tcp_info { __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; }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ @@ -238,6 +248,11 @@ enum { 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 */ }; @@ -265,4 +280,11 @@ struct tcp_diag_md5sig { __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; }; +/* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ + +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 */ +}; #endif /* _LINUX_TCP_H */ diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h index 80ad90d..7cb4a17 100644 --- a/include/uapi/linux/tcp_metrics.h +++ b/include/uapi/linux/tcp_metrics.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* tcp_metrics.h - TCP Metrics Interface */ #ifndef _LINUX_TCP_METRICS_H diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index 924fb5c..7a166a0 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * include/uapi/linux/tipc.h: Header for TIPC socket interface * @@ -44,82 +45,38 @@ * TIPC addressing primitives */ -struct tipc_portid { +struct tipc_socket_addr { __u32 ref; __u32 node; }; -struct tipc_name { +struct tipc_service_addr { __u32 type; __u32 instance; }; -struct tipc_name_seq { +struct tipc_service_range { __u32 type; __u32 lower; __u32 upper; }; -/* TIPC Address Size, Offset, Mask specification for Z.C.N - */ -#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) - -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; -} - /* - * Application-accessible port name types + * Application-accessible service types */ -#define TIPC_CFG_SRV 0 /* configuration service name type */ -#define TIPC_TOP_SRV 1 /* topology service name type */ -#define TIPC_LINK_STATE 2 /* link state name type */ -#define TIPC_RESERVED_TYPES 64 /* lowest user-publishable name type */ +#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 port names and port name sequences + * Publication scopes when binding service / service range */ - -#define TIPC_ZONE_SCOPE 1 -#define TIPC_CLUSTER_SCOPE 2 -#define TIPC_NODE_SCOPE 3 +enum tipc_scope { + TIPC_CLUSTER_SCOPE = 2, /* 0 can also be used */ + TIPC_NODE_SCOPE = 3 +}; /* * Limiting values for messages @@ -151,28 +108,28 @@ static __inline__ unsigned int tipc_node(__u32 addr) * TIPC topology subscription service definitions */ -#define TIPC_SUB_PORTS 0x01 /* filter for port availability */ -#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ -#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ +#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_name_seq seq; /* name sequence of interest */ + 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 /* withdraw 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 name seq instances */ - __u32 found_upper; /* " " " " */ - struct tipc_portid port; /* associated port */ + __u32 found_lower; /* matching range */ + __u32 found_upper; /* " " */ + struct tipc_socket_addr port; /* associated socket */ struct tipc_subscr s; /* associated subscription */ }; @@ -192,20 +149,20 @@ struct tipc_event { #define SOL_TIPC 271 #endif -#define TIPC_ADDR_NAMESEQ 1 -#define TIPC_ADDR_MCAST 1 -#define TIPC_ADDR_NAME 2 -#define TIPC_ADDR_ID 3 +#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_portid id; - struct tipc_name_seq nameseq; + struct tipc_socket_addr id; + struct tipc_service_range nameseq; struct { - struct tipc_name name; + struct tipc_service_addr name; __u32 domain; } name; } addr; @@ -231,26 +188,103 @@ struct sockaddr_tipc { #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 */ + +/* + * 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: Z.C.N:interface-Z.C.N:interface - * + * 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 60 +#define TIPC_MAX_LINK_NAME 68 -#define SIOCGETLINKNAME SIOCPROTOPRIVATE +#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]; +}; + +/* 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 index f9edd20..0ebe02e 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * Copyright (c) 2014, Ericsson AB * All rights reserved. @@ -113,6 +114,14 @@ enum { 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 @@ -161,6 +170,8 @@ 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_MAX, TIPC_NLA_NET_MAX = __TIPC_NLA_NET_MAX - 1 @@ -223,6 +234,19 @@ enum { 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, @@ -237,6 +261,18 @@ enum { 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, @@ -244,6 +280,7 @@ enum { TIPC_NLA_PROP_PRIO, /* u32 */ TIPC_NLA_PROP_TOL, /* u32 */ TIPC_NLA_PROP_WIN, /* u32 */ + TIPC_NLA_PROP_MTU, /* u32 */ __TIPC_NLA_PROP_MAX, TIPC_NLA_PROP_MAX = __TIPC_NLA_PROP_MAX - 1 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 +#include + +/* 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/types.h b/include/uapi/linux/types.h index c640657..999cb0f 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_TYPES_H #define _LINUX_TYPES_H @@ -43,5 +44,7 @@ typedef __u32 __bitwise __wsum; #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/unix_diag.h b/include/uapi/linux/unix_diag.h index 1eb0b8d..5c502fd 100644 --- a/include/uapi/linux/unix_diag.h +++ b/include/uapi/linux/unix_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UNIX_DIAG_H__ #define __UNIX_DIAG_H__ diff --git a/include/uapi/linux/veth.h b/include/uapi/linux/veth.h index 3354c1e..52b58e5 100644 --- a/include/uapi/linux/veth.h +++ b/include/uapi/linux/veth.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __NET_VETH_H_ #define __NET_VETH_H_ diff --git a/include/uapi/linux/vm_sockets_diag.h b/include/uapi/linux/vm_sockets_diag.h index a732a6f..6da42f9 100644 --- a/include/uapi/linux/vm_sockets_diag.h +++ b/include/uapi/linux/vm_sockets_diag.h @@ -1,3 +1,4 @@ +/* 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__ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 5790293..93fb192 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_XFRM_H #define _LINUX_XFRM_H -- 1.8.3.1