diff options
author | Yu Watanabe <watanabe.yu+github@gmail.com> | 2019-04-10 19:55:53 +0900 |
---|---|---|
committer | Lennart Poettering <lennart@poettering.net> | 2019-04-11 19:00:37 +0200 |
commit | 01234e1fe777602265ffd25ab6e73823c62b0efe (patch) | |
tree | 4135491d107232d081ae3f4a0013baad8dd1d50b /src/shared/linux | |
parent | aa46c28418c3111df9b9341d8796c16e0d40261c (diff) | |
download | systemd-01234e1fe777602265ffd25ab6e73823c62b0efe.tar.gz |
tree-wide: drop several missing_*.h and import relevant headers from kernel-5.0
Diffstat (limited to 'src/shared/linux')
-rw-r--r-- | src/shared/linux/README | 8 | ||||
-rw-r--r-- | src/shared/linux/auto_dev-ioctl.h | 33 | ||||
-rw-r--r-- | src/shared/linux/bpf.h | 3536 | ||||
-rw-r--r-- | src/shared/linux/bpf_common.h | 14 | ||||
-rw-r--r-- | src/shared/linux/bpf_insn.h | 205 | ||||
-rw-r--r-- | src/shared/linux/dm-ioctl.h | 363 | ||||
-rw-r--r-- | src/shared/linux/ethtool.h | 1843 | ||||
-rw-r--r-- | src/shared/linux/libbpf.h | 207 | ||||
-rw-r--r-- | src/shared/linux/netdevice.h | 66 |
9 files changed, 5247 insertions, 1028 deletions
diff --git a/src/shared/linux/README b/src/shared/linux/README new file mode 100644 index 0000000000..34f90486bb --- /dev/null +++ b/src/shared/linux/README @@ -0,0 +1,8 @@ +The files in this directory are copied from kernel-5.0, and the following modifications are applied: +- auto_dev-ioctl.h: set AUTOFS_DEV_IOCTL_VERSION_MINOR to 0 +- auto_dev-ioctl.h: define AUTOFS_IOCTL if not defined +- bpf_insn.h: This is imported from samples/bpf/bpf_insn.h +- bpf_insn.h: BPF_JMP_A() macro is also imported from include/linux/filter.h +- dm-ioctl.h: set DM_VERSION_MINOR to 27 +- ethtool.h: add a type cast to SPEED_UNKNOWN +- ethtool.h: define __KERNEL_DIV_ROUND_UP if not defined diff --git a/src/shared/linux/auto_dev-ioctl.h b/src/shared/linux/auto_dev-ioctl.h index d9838eba49..261546c667 100644 --- a/src/shared/linux/auto_dev-ioctl.h +++ b/src/shared/linux/auto_dev-ioctl.h @@ -1,31 +1,24 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* - * Copyright © 2008 Red Hat, Inc. All rights reserved. - * Copyright © 2008 Ian Kent <raven@themaw.net> + * Copyright 2008 Red Hat, Inc. All rights reserved. + * Copyright 2008 Ian Kent <raven@themaw.net> * * This file is part of the Linux kernel and is made available under * the terms of the GNU General Public License, version 2, or at your * option, any later version, incorporated herein by reference. */ -#ifndef _LINUX_AUTO_DEV_IOCTL_H -#define _LINUX_AUTO_DEV_IOCTL_H +#ifndef _UAPI_LINUX_AUTO_DEV_IOCTL_H +#define _UAPI_LINUX_AUTO_DEV_IOCTL_H #include <linux/auto_fs.h> - -#ifdef __KERNEL__ #include <linux/string.h> -#else -#include <string.h> -#endif /* __KERNEL__ */ #define AUTOFS_DEVICE_NAME "autofs" #define AUTOFS_DEV_IOCTL_VERSION_MAJOR 1 #define AUTOFS_DEV_IOCTL_VERSION_MINOR 0 -#define AUTOFS_DEVID_LEN 16 - #define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) /* @@ -119,19 +112,15 @@ struct autofs_dev_ioctl { char path[0]; }; -static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) { - memset(in, 0, sizeof(struct autofs_dev_ioctl)); +static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) +{ + memset(in, 0, AUTOFS_DEV_IOCTL_SIZE); in->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; in->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; - in->size = sizeof(struct autofs_dev_ioctl); + in->size = AUTOFS_DEV_IOCTL_SIZE; in->ioctlfd = -1; - return; } -/* - * If you change this make sure you make the corresponding change - * to autofs-dev-ioctl.c:lookup_ioctl() - */ enum { /* Get various version info */ AUTOFS_DEV_IOCTL_VERSION_CMD = 0x71, @@ -168,7 +157,9 @@ enum { AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, }; +#ifndef AUTOFS_IOCTL #define AUTOFS_IOCTL 0x93 +#endif #define AUTOFS_DEV_IOCTL_VERSION \ _IOWR(AUTOFS_IOCTL, \ @@ -226,4 +217,4 @@ enum { _IOWR(AUTOFS_IOCTL, \ AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, struct autofs_dev_ioctl) -#endif /* _LINUX_AUTO_DEV_IOCTL_H */ +#endif /* _UAPI_LINUX_AUTO_DEV_IOCTL_H */ diff --git a/src/shared/linux/bpf.h b/src/shared/linux/bpf.h index 1df9e7e3d0..91c43884f2 100644 --- a/src/shared/linux/bpf.h +++ b/src/shared/linux/bpf.h @@ -44,106 +44,149 @@ /* Register numbers */ enum { - BPF_REG_0 = 0, - BPF_REG_1, - BPF_REG_2, - BPF_REG_3, - BPF_REG_4, - BPF_REG_5, - BPF_REG_6, - BPF_REG_7, - BPF_REG_8, - BPF_REG_9, - BPF_REG_10, - __MAX_BPF_REG, + BPF_REG_0 = 0, + BPF_REG_1, + BPF_REG_2, + BPF_REG_3, + BPF_REG_4, + BPF_REG_5, + BPF_REG_6, + BPF_REG_7, + BPF_REG_8, + BPF_REG_9, + BPF_REG_10, + __MAX_BPF_REG, }; /* BPF has 10 general purpose 64-bit registers and stack frame. */ #define MAX_BPF_REG __MAX_BPF_REG struct bpf_insn { - __u8 code; /* opcode */ - __u8 dst_reg:4; /* dest register */ - __u8 src_reg:4; /* source register */ - __s16 off; /* signed offset */ - __s32 imm; /* signed immediate constant */ + __u8 code; /* opcode */ + __u8 dst_reg:4; /* dest register */ + __u8 src_reg:4; /* source register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ }; /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { - __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[0]; /* Arbitrary size */ + __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ + __u8 data[0]; /* Arbitrary size */ +}; + +struct bpf_cgroup_storage_key { + __u64 cgroup_inode_id; /* cgroup inode id */ + __u32 attach_type; /* program attach type */ }; /* BPF syscall commands, see bpf(2) man-page for details. */ enum bpf_cmd { - BPF_MAP_CREATE, - BPF_MAP_LOOKUP_ELEM, - BPF_MAP_UPDATE_ELEM, - BPF_MAP_DELETE_ELEM, - BPF_MAP_GET_NEXT_KEY, - BPF_PROG_LOAD, - BPF_OBJ_PIN, - BPF_OBJ_GET, - BPF_PROG_ATTACH, - BPF_PROG_DETACH, - BPF_PROG_TEST_RUN, - BPF_PROG_GET_NEXT_ID, - BPF_MAP_GET_NEXT_ID, - BPF_PROG_GET_FD_BY_ID, - BPF_MAP_GET_FD_BY_ID, - BPF_OBJ_GET_INFO_BY_FD, - BPF_PROG_QUERY, + BPF_MAP_CREATE, + BPF_MAP_LOOKUP_ELEM, + BPF_MAP_UPDATE_ELEM, + BPF_MAP_DELETE_ELEM, + BPF_MAP_GET_NEXT_KEY, + BPF_PROG_LOAD, + BPF_OBJ_PIN, + BPF_OBJ_GET, + BPF_PROG_ATTACH, + BPF_PROG_DETACH, + BPF_PROG_TEST_RUN, + BPF_PROG_GET_NEXT_ID, + BPF_MAP_GET_NEXT_ID, + BPF_PROG_GET_FD_BY_ID, + BPF_MAP_GET_FD_BY_ID, + BPF_OBJ_GET_INFO_BY_FD, + BPF_PROG_QUERY, + BPF_RAW_TRACEPOINT_OPEN, + BPF_BTF_LOAD, + BPF_BTF_GET_FD_BY_ID, + BPF_TASK_FD_QUERY, + BPF_MAP_LOOKUP_AND_DELETE_ELEM, }; enum bpf_map_type { - BPF_MAP_TYPE_UNSPEC, - BPF_MAP_TYPE_HASH, - BPF_MAP_TYPE_ARRAY, - BPF_MAP_TYPE_PROG_ARRAY, - BPF_MAP_TYPE_PERF_EVENT_ARRAY, - BPF_MAP_TYPE_PERCPU_HASH, - BPF_MAP_TYPE_PERCPU_ARRAY, - BPF_MAP_TYPE_STACK_TRACE, - BPF_MAP_TYPE_CGROUP_ARRAY, - BPF_MAP_TYPE_LRU_HASH, - BPF_MAP_TYPE_LRU_PERCPU_HASH, - BPF_MAP_TYPE_LPM_TRIE, - BPF_MAP_TYPE_ARRAY_OF_MAPS, - BPF_MAP_TYPE_HASH_OF_MAPS, - BPF_MAP_TYPE_DEVMAP, - BPF_MAP_TYPE_SOCKMAP, - BPF_MAP_TYPE_CPUMAP, + BPF_MAP_TYPE_UNSPEC, + BPF_MAP_TYPE_HASH, + BPF_MAP_TYPE_ARRAY, + BPF_MAP_TYPE_PROG_ARRAY, + BPF_MAP_TYPE_PERF_EVENT_ARRAY, + BPF_MAP_TYPE_PERCPU_HASH, + BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, + BPF_MAP_TYPE_LRU_HASH, + BPF_MAP_TYPE_LRU_PERCPU_HASH, + BPF_MAP_TYPE_LPM_TRIE, + BPF_MAP_TYPE_ARRAY_OF_MAPS, + BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, + BPF_MAP_TYPE_XSKMAP, + BPF_MAP_TYPE_SOCKHASH, + BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, }; +/* Note that tracing related programs such as + * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT} + * are not subject to a stable API since kernel internal data + * structures can change from release to release and may + * therefore break existing tracing BPF programs. Tracing BPF + * programs correspond to /a/ specific kernel which is to be + * analyzed, and not /a/ specific kernel /and/ all future ones. + */ enum bpf_prog_type { - BPF_PROG_TYPE_UNSPEC, - BPF_PROG_TYPE_SOCKET_FILTER, - BPF_PROG_TYPE_KPROBE, - BPF_PROG_TYPE_SCHED_CLS, - BPF_PROG_TYPE_SCHED_ACT, - BPF_PROG_TYPE_TRACEPOINT, - BPF_PROG_TYPE_XDP, - BPF_PROG_TYPE_PERF_EVENT, - BPF_PROG_TYPE_CGROUP_SKB, - BPF_PROG_TYPE_CGROUP_SOCK, - BPF_PROG_TYPE_LWT_IN, - BPF_PROG_TYPE_LWT_OUT, - BPF_PROG_TYPE_LWT_XMIT, - BPF_PROG_TYPE_SOCK_OPS, - BPF_PROG_TYPE_SK_SKB, - BPF_PROG_TYPE_CGROUP_DEVICE, + BPF_PROG_TYPE_UNSPEC, + BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_KPROBE, + BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, + BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, + BPF_PROG_TYPE_PERF_EVENT, + BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_CGROUP_SOCK, + BPF_PROG_TYPE_LWT_IN, + BPF_PROG_TYPE_LWT_OUT, + BPF_PROG_TYPE_LWT_XMIT, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_CGROUP_DEVICE, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_RAW_TRACEPOINT, + BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_PROG_TYPE_LWT_SEG6LOCAL, + BPF_PROG_TYPE_LIRC_MODE2, + BPF_PROG_TYPE_SK_REUSEPORT, + BPF_PROG_TYPE_FLOW_DISSECTOR, }; enum bpf_attach_type { - BPF_CGROUP_INET_INGRESS, - BPF_CGROUP_INET_EGRESS, - BPF_CGROUP_INET_SOCK_CREATE, - BPF_CGROUP_SOCK_OPS, - BPF_SK_SKB_STREAM_PARSER, - BPF_SK_SKB_STREAM_VERDICT, - BPF_CGROUP_DEVICE, - __MAX_BPF_ATTACH_TYPE + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_SOCK_OPS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, + BPF_SK_MSG_VERDICT, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_POST_BIND, + BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + BPF_LIRC_MODE2, + BPF_FLOW_DISSECTOR, + __MAX_BPF_ATTACH_TYPE }; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE @@ -197,6 +240,20 @@ enum bpf_attach_type { */ #define BPF_F_STRICT_ALIGNMENT (1U << 0) +/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the + * verifier will allow any alignment whatsoever. On platforms + * with strict alignment requirements for loads ands stores (such + * as sparc and mips) the verifier validates that all loads and + * stores provably follow this requirement. This flag turns that + * checking and enforcement off. + * + * It is mostly used for testing when we want to validate the + * context and memory access aspects of the verifier, but because + * of an unaligned access the alignment check would trigger before + * the one we are interested in. + */ +#define BPF_F_ANY_ALIGNMENT (1U << 1) + /* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ #define BPF_PSEUDO_MAP_FD 1 @@ -222,550 +279,2157 @@ 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) + +/* Zero-initialize hash function seed. This should only be used for testing. */ +#define BPF_F_ZERO_SEED (1U << 6) + +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + +enum bpf_stack_build_id_status { + /* user space need an empty entry to identify end of a trace */ + BPF_STACK_BUILD_ID_EMPTY = 0, + /* with valid build_id and offset */ + BPF_STACK_BUILD_ID_VALID = 1, + /* couldn't get build_id, fallback to ip */ + BPF_STACK_BUILD_ID_IP = 2, +}; + +#define BPF_BUILD_ID_SIZE 20 +struct bpf_stack_build_id { + __s32 status; + unsigned char build_id[BPF_BUILD_ID_SIZE]; + union { + __u64 offset; + __u64 ip; + }; +}; + union bpf_attr { - struct { /* anonymous struct used by BPF_MAP_CREATE command */ - __u32 map_type; /* one of enum bpf_map_type */ - __u32 key_size; /* size of key in bytes */ - __u32 value_size; /* size of value in bytes */ - __u32 max_entries; /* max number of entries in a map */ - __u32 map_flags; /* BPF_MAP_CREATE related - * flags defined above. - */ - __u32 inner_map_fd; /* fd pointing to the inner map */ - __u32 numa_node; /* numa node (effective only if - * BPF_F_NUMA_NODE is set). - */ - char map_name[BPF_OBJ_NAME_LEN]; - __u32 map_ifindex; /* ifindex of netdev to create on */ - }; - - struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ - __u32 map_fd; - __aligned_u64 key; - union { - __aligned_u64 value; - __aligned_u64 next_key; - }; - __u64 flags; - }; - - struct { /* anonymous struct used by BPF_PROG_LOAD command */ - __u32 prog_type; /* one of enum bpf_prog_type */ - __u32 insn_cnt; - __aligned_u64 insns; - __aligned_u64 license; - __u32 log_level; /* verbosity level of verifier */ - __u32 log_size; /* size of user buffer */ - __aligned_u64 log_buf; /* user supplied buffer */ - __u32 kern_version; /* checked when prog_type=kprobe */ - __u32 prog_flags; - char prog_name[BPF_OBJ_NAME_LEN]; - __u32 prog_ifindex; /* ifindex of netdev to prep for */ - }; - - 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 */ - __u32 target_fd; /* container object to attach to */ - __u32 attach_bpf_fd; /* eBPF program to attach */ - __u32 attach_type; - __u32 attach_flags; - }; - - struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ - __u32 prog_fd; - __u32 retval; - __u32 data_size_in; - __u32 data_size_out; - __aligned_u64 data_in; - __aligned_u64 data_out; - __u32 repeat; - __u32 duration; - } test; - - struct { /* anonymous struct used by BPF_*_GET_*_ID */ - union { - __u32 start_id; - __u32 prog_id; - __u32 map_id; - }; - __u32 next_id; - __u32 open_flags; - }; - - struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ - __u32 bpf_fd; - __u32 info_len; - __aligned_u64 info; - } info; - - struct { /* anonymous struct used by BPF_PROG_QUERY command */ - __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 { /* anonymous struct used by BPF_MAP_CREATE command */ + __u32 map_type; /* one of enum bpf_map_type */ + __u32 key_size; /* size of key in bytes */ + __u32 value_size; /* size of value in bytes */ + __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* BPF_MAP_CREATE related + * flags defined above. + */ + __u32 inner_map_fd; /* fd pointing to the inner map */ + __u32 numa_node; /* numa node (effective only if + * BPF_F_NUMA_NODE is set). + */ + char map_name[BPF_OBJ_NAME_LEN]; + __u32 map_ifindex; /* ifindex of netdev to create on */ + __u32 btf_fd; /* fd pointing to a BTF type data */ + __u32 btf_key_type_id; /* BTF type_id of the key */ + __u32 btf_value_type_id; /* BTF type_id of the value */ + }; + + struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + __u32 map_fd; + __aligned_u64 key; + union { + __aligned_u64 value; + __aligned_u64 next_key; + }; + __u64 flags; + }; + + struct { /* anonymous struct used by BPF_PROG_LOAD command */ + __u32 prog_type; /* one of enum bpf_prog_type */ + __u32 insn_cnt; + __aligned_u64 insns; + __aligned_u64 license; + __u32 log_level; /* verbosity level of verifier */ + __u32 log_size; /* size of user buffer */ + __aligned_u64 log_buf; /* user supplied buffer */ + __u32 kern_version; /* not used */ + __u32 prog_flags; + char prog_name[BPF_OBJ_NAME_LEN]; + __u32 prog_ifindex; /* ifindex of netdev to prep for */ + /* For some prog types expected attach type must be known at + * load time to verify attach type specific parts of prog + * (context accesses, allowed helpers, etc). + */ + __u32 expected_attach_type; + __u32 prog_btf_fd; /* fd pointing to BTF type data */ + __u32 func_info_rec_size; /* userspace bpf_func_info size */ + __aligned_u64 func_info; /* func info */ + __u32 func_info_cnt; /* number of bpf_func_info records */ + __u32 line_info_rec_size; /* userspace bpf_line_info size */ + __aligned_u64 line_info; /* line info */ + __u32 line_info_cnt; /* number of bpf_line_info records */ + }; + + 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 */ + __u32 target_fd; /* container object to attach to */ + __u32 attach_bpf_fd; /* eBPF program to attach */ + __u32 attach_type; + __u32 attach_flags; + }; + + struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ + __u32 prog_fd; + __u32 retval; + __u32 data_size_in; /* input: len of data_in */ + __u32 data_size_out; /* input/output: len of data_out + * returns ENOSPC if data_out + * is too small. + */ + __aligned_u64 data_in; + __aligned_u64 data_out; + __u32 repeat; + __u32 duration; + } test; + + struct { /* anonymous struct used by BPF_*_GET_*_ID */ + union { + __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 */ + __u32 bpf_fd; + __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: - * - * void *bpf_map_lookup_elem(&map, &key) - * Return: Map value or NULL - * - * int bpf_map_update_elem(&map, &key, &value, flags) - * Return: 0 on success or negative error - * - * int bpf_map_delete_elem(&map, &key) - * Return: 0 on success or negative error - * - * int bpf_probe_read(void *dst, int size, void *src) - * Return: 0 on success or negative error +/* 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. + * + * 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: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * 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_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is removed to + * make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * 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: 32-bit 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: <formatted msg> + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ``<formatted msg>`` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * 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=<new value> + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * 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 IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: SOL_SOCKET or IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen) - * Calls getsockopt. Not all opts are available. - * Supported levels: IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags) - * Set callback flags for sock_ops - * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct - * @flags: flags value - * Return: 0 for no error - * -EINVAL if there is no full tcp socket - * bits in flags that are not supported by current kernel - * - * 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_PASS - * - * 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 - * - * int bpf_xdp_adjust_meta(xdp_md, delta) - * Adjust the xdp_md.data_meta by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data_meta - * Return: 0 on success or negative on error - * - * int bpf_perf_event_read_value(map, flags, buf, buf_size) - * read perf event counter value and perf event enabled/running time - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @buf: buf to fill - * @buf_size: size of the buf - * Return: 0 on success or negative error code - * - * int bpf_perf_prog_read_value(ctx, buf, buf_size) - * read perf prog attached perf event counter and enabled/running time - * @ctx: pointer to ctx - * @buf: buf to fill - * @buf_size: size of the buf - * Return : 0 on success or negative error code - * - * int bpf_override_return(pt_regs, rc) - * @pt_regs: pointer to struct pt_regs - * @rc: the return value to set + * 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*. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_addr** contex. + * Return + * A 8-byte long non-decreasing number. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_ops** contex. + * Return + * A 8-byte long non-decreasing number. + * + * 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, s32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * 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=<new value> + * 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_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * 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. + * + * void* get_local_storage(void *map, u64 flags) + * Description + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the BPF program type, a local storage area + * can be shared between multiple instances of the BPF program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the **BPF_STX_XADD** instruction to alter + * the shared data. + * Return + * A pointer to the local storage area. + * + * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * Description + * Select a **SO_REUSEPORT** socket from a + * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. + * It checks the selected socket is matching the incoming + * request in the socket buffer. + * Return + * 0 on success, or a negative error in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from **reuse->socks**\ [] using the hash of the tuple. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from **reuse->socks**\ [] using the hash of the tuple. + * + * int bpf_sk_release(struct bpf_sock *sock) + * Description + * Release the reference held by *sock*. *sock* must be a + * non-**NULL** pointer that was returned from + * **bpf_sk_lookup_xxx**\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags) + * Description + * For socket policies, insert *len* bytes into *msg* at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the *msg*. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags) + * Description + * Will remove *pop* bytes from a *msg* starting at byte *start*. + * This may result in **ENOMEM** errors under certain situations if + * an allocation and copy are required due to a full ring buffer. + * However, the helper will try to avoid doing the allocation + * if possible. Other errors can occur if input parameters are + * invalid either due to *start* byte not being valid part of *msg* + * payload and/or *pop* value being to large. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded pointer movement. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 */ #define __BPF_FUNC_MAPPER(FN) \ - FN(unspec), \ - FN(map_lookup_elem), \ - FN(map_update_elem), \ - FN(map_delete_elem), \ - FN(probe_read), \ - FN(ktime_get_ns), \ - FN(trace_printk), \ - FN(get_prandom_u32), \ - FN(get_smp_processor_id), \ - FN(skb_store_bytes), \ - FN(l3_csum_replace), \ - FN(l4_csum_replace), \ - FN(tail_call), \ - FN(clone_redirect), \ - FN(get_current_pid_tgid), \ - FN(get_current_uid_gid), \ - FN(get_current_comm), \ - FN(get_cgroup_classid), \ - FN(skb_vlan_push), \ - FN(skb_vlan_pop), \ - FN(skb_get_tunnel_key), \ - FN(skb_set_tunnel_key), \ - FN(perf_event_read), \ - FN(redirect), \ - FN(get_route_realm), \ - FN(perf_event_output), \ - FN(skb_load_bytes), \ - FN(get_stackid), \ - FN(csum_diff), \ - FN(skb_get_tunnel_opt), \ - FN(skb_set_tunnel_opt), \ - FN(skb_change_proto), \ - FN(skb_change_type), \ - FN(skb_under_cgroup), \ - FN(get_hash_recalc), \ - FN(get_current_task), \ - FN(probe_write_user), \ - FN(current_task_under_cgroup), \ - FN(skb_change_tail), \ - FN(skb_pull_data), \ - FN(csum_update), \ - FN(set_hash_invalid), \ - FN(get_numa_node_id), \ - FN(skb_change_head), \ - FN(xdp_adjust_head), \ - FN(probe_read_str), \ - FN(get_socket_cookie), \ - FN(get_socket_uid), \ - FN(set_hash), \ - FN(setsockopt), \ - FN(skb_adjust_room), \ - 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(unspec), \ + FN(map_lookup_elem), \ + FN(map_update_elem), \ + FN(map_delete_elem), \ + FN(probe_read), \ + FN(ktime_get_ns), \ + FN(trace_printk), \ + FN(get_prandom_u32), \ + FN(get_smp_processor_id), \ + FN(skb_store_bytes), \ + FN(l3_csum_replace), \ + FN(l4_csum_replace), \ + FN(tail_call), \ + FN(clone_redirect), \ + FN(get_current_pid_tgid), \ + FN(get_current_uid_gid), \ + FN(get_current_comm), \ + FN(get_cgroup_classid), \ + FN(skb_vlan_push), \ + FN(skb_vlan_pop), \ + FN(skb_get_tunnel_key), \ + FN(skb_set_tunnel_key), \ + FN(perf_event_read), \ + FN(redirect), \ + FN(get_route_realm), \ + FN(perf_event_output), \ + FN(skb_load_bytes), \ + FN(get_stackid), \ + FN(csum_diff), \ + FN(skb_get_tunnel_opt), \ + FN(skb_set_tunnel_opt), \ + FN(skb_change_proto), \ + FN(skb_change_type), \ + FN(skb_under_cgroup), \ + FN(get_hash_recalc), \ + FN(get_current_task), \ + FN(probe_write_user), \ + FN(current_task_under_cgroup), \ + FN(skb_change_tail), \ + FN(skb_pull_data), \ + FN(csum_update), \ + FN(set_hash_invalid), \ + FN(get_numa_node_id), \ + FN(skb_change_head), \ + FN(xdp_adjust_head), \ + FN(probe_read_str), \ + FN(get_socket_cookie), \ + FN(get_socket_uid), \ + FN(set_hash), \ + FN(setsockopt), \ + FN(skb_adjust_room), \ + 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), \ + FN(get_local_storage), \ + FN(sk_select_reuseport), \ + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), \ + FN(msg_push_data), \ + FN(msg_pop_data), \ + FN(rc_pointer_rel), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call */ #define __BPF_ENUM_FN(x) BPF_FUNC_ ## x enum bpf_func_id { - __BPF_FUNC_MAPPER(__BPF_ENUM_FN) - __BPF_FUNC_MAX_ID, + __BPF_FUNC_MAPPER(__BPF_ENUM_FN) + __BPF_FUNC_MAX_ID, }; #undef __BPF_ENUM_FN @@ -791,15 +2455,19 @@ 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, BPF_FUNC_perf_event_read and * BPF_FUNC_perf_event_read_value flags. @@ -809,57 +2477,95 @@ enum bpf_func_id { /* BPF_FUNC_perf_event_output for sk_buff input context. */ #define BPF_F_CTXLEN_MASK (0xfffffULL << 32) +/* Current network namespace */ +#define BPF_F_CURRENT_NETNS (-1L) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { - BPF_ADJ_ROOM_NET, + 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 +}; + +#define __bpf_md_ptr(type, name) \ +union { \ + type name; \ + __u64 :64; \ +} __attribute__((aligned(8))) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ struct __sk_buff { - __u32 len; - __u32 pkt_type; - __u32 mark; - __u32 queue_mapping; - __u32 protocol; - __u32 vlan_present; - __u32 vlan_tci; - __u32 vlan_proto; - __u32 priority; - __u32 ingress_ifindex; - __u32 ifindex; - __u32 tc_index; - __u32 cb[5]; - __u32 hash; - __u32 tc_classid; - __u32 data; - __u32 data_end; - __u32 napi_id; - - /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ - __u32 family; - __u32 remote_ip4; /* Stored in network byte order */ - __u32 local_ip4; /* Stored in network byte order */ - __u32 remote_ip6[4]; /* Stored in network byte order */ - __u32 local_ip6[4]; /* Stored in network byte order */ - __u32 remote_port; /* Stored in network byte order */ - __u32 local_port; /* stored in host byte order */ - /* ... here. */ - - __u32 data_meta; + __u32 len; + __u32 pkt_type; + __u32 mark; + __u32 queue_mapping; + __u32 protocol; + __u32 vlan_present; + __u32 vlan_tci; + __u32 vlan_proto; + __u32 priority; + __u32 ingress_ifindex; + __u32 ifindex; + __u32 tc_index; + __u32 cb[5]; + __u32 hash; + __u32 tc_classid; + __u32 data; + __u32 data_end; + __u32 napi_id; + + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; + __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); + __u64 tstamp; + __u32 wire_len; }; struct bpf_tunnel_key { - __u32 tunnel_id; - union { - __u32 remote_ipv4; - __u32 remote_ipv6[4]; - }; - __u8 tunnel_tos; - __u8 tunnel_ttl; - __u16 tunnel_ext; - __u32 tunnel_label; + __u32 tunnel_id; + union { + __u32 remote_ipv4; + __u32 remote_ipv6[4]; + }; + __u8 tunnel_tos; + __u8 tunnel_ttl; + __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. @@ -870,21 +2576,47 @@ struct bpf_tunnel_key { * XDP is handled seprately, see XDP_*. */ enum bpf_ret_code { - BPF_OK = 0, - /* 1 reserved */ - BPF_DROP = 2, - /* 3-6 reserved */ - BPF_REDIRECT = 7, - /* >127 are reserved for prog type specific return codes */ + BPF_OK = 0, + /* 1 reserved */ + BPF_DROP = 2, + /* 3-6 reserved */ + BPF_REDIRECT = 7, + /* >127 are reserved for prog type specific return codes */ }; struct bpf_sock { - __u32 bound_dev_if; - __u32 family; - __u32 type; - __u32 protocol; - __u32 mark; - __u32 priority; + __u32 bound_dev_if; + __u32 family; + __u32 type; + __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 + */ +}; + +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; }; #define XDP_PACKET_HEADROOM 256 @@ -895,63 +2627,158 @@ struct bpf_sock { * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). */ enum xdp_action { - XDP_ABORTED = 0, - XDP_DROP, - XDP_PASS, - XDP_TX, - XDP_REDIRECT, + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, + XDP_REDIRECT, }; /* user accessible metadata for XDP packet hook * new fields must be added to the end of this structure */ struct xdp_md { - __u32 data; - __u32 data_end; - __u32 data_meta; - /* Below access go through struct xdp_rxq_info */ - __u32 ingress_ifindex; /* rxq->dev->ifindex */ - __u32 rx_queue_index; /* rxq->queue_index */ + __u32 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_DROP = 0, - SK_PASS, + SK_DROP = 0, + SK_PASS, +}; + +/* user accessible metadata for SK_MSG packet hook, new fields must + * be added to the end of this structure + */ +struct sk_msg_md { + __bpf_md_ptr(void *, data); + __bpf_md_ptr(void *, data_end); + + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + __u32 size; /* Total size of sk_msg */ +}; + +struct sk_reuseport_md { + /* + * Start of directly accessible data. It begins from + * the tcp/udp header. + */ + __bpf_md_ptr(void *, data); + /* End of directly accessible data */ + __bpf_md_ptr(void *, data_end); + /* + * Total length of packet (starting from the tcp/udp header). + * Note that the directly accessible bytes (data_end - data) + * could be less than this "len". Those bytes could be + * indirectly read by a helper "bpf_skb_load_bytes()". + */ + __u32 len; + /* + * Eth protocol in the mac header (network byte order). e.g. + * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD) + */ + __u32 eth_protocol; + __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ + __u32 bind_inany; /* Is sock bound to an INANY address? */ + __u32 hash; /* A hash of the packet 4 tuples */ }; #define BPF_TAG_SIZE 8 struct bpf_prog_info { - __u32 type; - __u32 id; - __u8 tag[BPF_TAG_SIZE]; - __u32 jited_prog_len; - __u32 xlated_prog_len; - __aligned_u64 jited_prog_insns; - __aligned_u64 xlated_prog_insns; - __u64 load_time; /* ns since boottime */ - __u32 created_by_uid; - __u32 nr_map_ids; - __aligned_u64 map_ids; - char name[BPF_OBJ_NAME_LEN]; - __u32 ifindex; - __u64 netns_dev; - __u64 netns_ino; + __u32 type; + __u32 id; + __u8 tag[BPF_TAG_SIZE]; + __u32 jited_prog_len; + __u32 xlated_prog_len; + __aligned_u64 jited_prog_insns; + __aligned_u64 xlated_prog_insns; + __u64 load_time; /* ns since boottime */ + __u32 created_by_uid; + __u32 nr_map_ids; + __aligned_u64 map_ids; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 gpl_compatible:1; + __u64 netns_dev; + __u64 netns_ino; + __u32 nr_jited_ksyms; + __u32 nr_jited_func_lens; + __aligned_u64 jited_ksyms; + __aligned_u64 jited_func_lens; + __u32 btf_id; + __u32 func_info_rec_size; + __aligned_u64 func_info; + __u32 nr_func_info; + __u32 nr_line_info; + __aligned_u64 line_info; + __aligned_u64 jited_line_info; + __u32 nr_jited_line_info; + __u32 line_info_rec_size; + __u32 jited_line_info_rec_size; + __u32 nr_prog_tags; + __aligned_u64 prog_tags; } __attribute__((aligned(8))); struct bpf_map_info { - __u32 type; - __u32 id; - __u32 key_size; - __u32 value_size; - __u32 max_entries; - __u32 map_flags; - char name[BPF_OBJ_NAME_LEN]; - __u32 ifindex; - __u64 netns_dev; - __u64 netns_ino; + __u32 type; + __u32 id; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 map_flags; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 :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 @@ -959,48 +2786,48 @@ struct bpf_map_info { * New fields can only be added at the end of this structure */ struct bpf_sock_ops { - __u32 op; - union { - __u32 args[4]; /* Optionally passed to bpf program */ - __u32 reply; /* Returned by bpf program */ - __u32 replylong[4]; /* Optionally returned by bpf prog */ - }; - __u32 family; - __u32 remote_ip4; /* Stored in network byte order */ - __u32 local_ip4; /* Stored in network byte order */ - __u32 remote_ip6[4]; /* Stored in network byte order */ - __u32 local_ip6[4]; /* Stored in network byte order */ - __u32 remote_port; /* Stored in network byte order */ - __u32 local_port; /* stored in host byte order */ - __u32 is_fullsock; /* Some TCP fields are only valid if - * there is a full socket. If not, the - * fields read as zero. - */ - __u32 snd_cwnd; - __u32 srtt_us; /* Averaged RTT << 3 in usecs */ - __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */ - __u32 state; - __u32 rtt_min; - __u32 snd_ssthresh; - __u32 rcv_nxt; - __u32 snd_nxt; - __u32 snd_una; - __u32 mss_cache; - __u32 ecn_flags; - __u32 rate_delivered; - __u32 rate_interval_us; - __u32 packets_out; - __u32 retrans_out; - __u32 total_retrans; - __u32 segs_in; - __u32 data_segs_in; - __u32 segs_out; - __u32 data_segs_out; - __u32 lost_out; - __u32 sacked_out; - __u32 sk_txhash; - __u64 bytes_received; - __u64 bytes_acked; + __u32 op; + union { + __u32 args[4]; /* Optionally passed to bpf program */ + __u32 reply; /* Returned by bpf program */ + __u32 replylong[4]; /* Optionally returned by bpf prog */ + }; + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + __u32 is_fullsock; /* Some TCP fields are only valid if + * there is a full socket. If not, the + * fields read as zero. + */ + __u32 snd_cwnd; + __u32 srtt_us; /* Averaged RTT << 3 in usecs */ + __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */ + __u32 state; + __u32 rtt_min; + __u32 snd_ssthresh; + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u32 mss_cache; + __u32 ecn_flags; + __u32 rate_delivered; + __u32 rate_interval_us; + __u32 packets_out; + __u32 retrans_out; + __u32 total_retrans; + __u32 segs_in; + __u32 data_segs_in; + __u32 segs_out; + __u32 data_segs_out; + __u32 lost_out; + __u32 sacked_out; + __u32 sk_txhash; + __u64 bytes_received; + __u64 bytes_acked; }; /* Definitions for bpf_sock_ops_cb_flags */ @@ -1008,57 +2835,60 @@ struct bpf_sock_ops { #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 - */ + * supported cb flags + */ /* List of known BPF sock_ops operators. * New entries can only be added at the end */ enum { - BPF_SOCK_OPS_VOID, - BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or - * -1 if default value should be used - */ - BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized - * window (in packets) or -1 if default - * value should be used - */ - BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an - * active connection is initialized - */ - BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an - * active connection is - * established - */ - BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a - * passive connection is - * established - */ - BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control - * needs ECN - */ - BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is - * based on the path and may be - * dependent on the congestion control - * algorithm. In general it indicates - * a congestion threshold. RTTs above - * this indicate congestion - */ - BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered. - * Arg1: value of icsk_retransmits - * Arg2: value of icsk_rto - * Arg3: whether RTO has expired - */ - BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted. - * Arg1: sequence number of 1st byte - * Arg2: # segments - * Arg3: return value of - * tcp_transmit_skb (0 => success) - */ - BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state. - * Arg1: old_state - * Arg2: new_state - */ + BPF_SOCK_OPS_VOID, + BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or + * -1 if default value should be used + */ + BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized + * window (in packets) or -1 if default + * value should be used + */ + BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an + * active connection is initialized + */ + BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an + * active connection is + * established + */ + BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a + * passive connection is + * established + */ + BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control + * needs ECN + */ + BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is + * based on the path and may be + * dependent on the congestion control + * algorithm. In general it indicates + * a congestion threshold. RTTs above + * this indicate congestion + */ + BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered. + * Arg1: value of icsk_retransmits + * Arg2: value of icsk_rto + * Arg3: whether RTO has expired + */ + BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted. + * Arg1: sequence number of 1st byte + * Arg2: # segments + * Arg3: return value of + * tcp_transmit_skb (0 => success) + */ + BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state. + * Arg1: old_state + * Arg2: new_state + */ + BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after + * socket transition to LISTEN state. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -1067,29 +2897,29 @@ enum { * 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! */ + 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; + __u64 counter; + __u64 enabled; + __u64 running; }; #define BPF_DEVCG_ACC_MKNOD (1ULL << 0) @@ -1100,10 +2930,128 @@ struct bpf_perf_event_value { #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; + /* 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 */ +}; + +struct bpf_flow_keys { + __u16 nhoff; + __u16 thoff; + __u16 addr_proto; /* ETH_P_* of valid addrs */ + __u8 is_frag; + __u8 is_first_frag; + __u8 is_encap; + __u8 ip_proto; + __be16 n_proto; + __be16 sport; + __be16 dport; + union { + struct { + __be32 ipv4_src; + __be32 ipv4_dst; + }; + struct { + __u32 ipv6_src[4]; /* in6_addr; network order */ + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + }; +}; + +struct bpf_func_info { + __u32 insn_off; + __u32 type_id; +}; + +#define BPF_LINE_INFO_LINE_NUM(line_col) ((line_col) >> 10) +#define BPF_LINE_INFO_LINE_COL(line_col) ((line_col) & 0x3ff) + +struct bpf_line_info { + __u32 insn_off; + __u32 file_name_off; + __u32 line_off; + __u32 line_col; }; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/src/shared/linux/bpf_common.h b/src/shared/linux/bpf_common.h index afe7433b98..ee97668bda 100644 --- a/src/shared/linux/bpf_common.h +++ b/src/shared/linux/bpf_common.h @@ -1,5 +1,6 @@ -#ifndef __LINUX_BPF_COMMON_H__ -#define __LINUX_BPF_COMMON_H__ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_BPF_COMMON_H__ +#define _UAPI__LINUX_BPF_COMMON_H__ /* Instruction classes */ #define BPF_CLASS(code) ((code) & 0x07) @@ -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 @@ -52,4 +54,4 @@ #define BPF_MAXINSNS 4096 #endif -#endif /* __LINUX_BPF_COMMON_H__ */ +#endif /* _UAPI__LINUX_BPF_COMMON_H__ */ diff --git a/src/shared/linux/bpf_insn.h b/src/shared/linux/bpf_insn.h new file mode 100644 index 0000000000..e88459fdaa --- /dev/null +++ b/src/shared/linux/bpf_insn.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* eBPF instruction mini library */ +#ifndef __BPF_INSN_H +#define __BPF_INSN_H + +struct bpf_insn; + +/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ + +#define BPF_ALU64_REG(OP, DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_ALU32_REG(OP, DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ + +#define BPF_ALU64_IMM(OP, DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_ALU32_IMM(OP, DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* Short form of mov, dst_reg = src_reg */ + +#define BPF_MOV64_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_MOV32_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +/* Short form of mov, dst_reg = imm32 */ + +#define BPF_MOV64_IMM(DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_MOV32_IMM(DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ +#define BPF_LD_IMM64(DST, IMM) \ + BPF_LD_IMM64_RAW(DST, 0, IMM) + +#define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_DW | BPF_IMM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = (__u32) (IMM) }), \ + ((struct bpf_insn) { \ + .code = 0, /* zero is reserved opcode */ \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = ((__u64) (IMM)) >> 32 }) + +#ifndef BPF_PSEUDO_MAP_FD +# define BPF_PSEUDO_MAP_FD 1 +#endif + +/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ +#define BPF_LD_MAP_FD(DST, MAP_FD) \ + BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) + + +/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ + +#define BPF_LD_ABS(SIZE, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +/* Memory load, dst_reg = *(uint *) (src_reg + off16) */ + +#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Memory store, *(uint *) (dst_reg + off16) = src_reg */ + +#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ + +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Memory store, *(uint *) (dst_reg + off16) = imm32 */ + +#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ + +#define BPF_JMP_REG(OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ + +#define BPF_JMP_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +#define BPF_JMP_A(OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_JA, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = 0 }) + +/* Raw code statement block */ + +#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ + ((struct bpf_insn) { \ + .code = CODE, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = IMM }) + +/* Program exit */ + +#define BPF_EXIT_INSN() \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_EXIT, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = 0 }) + +#endif diff --git a/src/shared/linux/dm-ioctl.h b/src/shared/linux/dm-ioctl.h new file mode 100644 index 0000000000..8faa188c35 --- /dev/null +++ b/src/shared/linux/dm-ioctl.h @@ -0,0 +1,363 @@ +/* SPDX-License-Identifier: LGPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright (C) 2001 - 2003 Sistina Software (UK) Limited. + * Copyright (C) 2004 - 2009 Red Hat, Inc. All rights reserved. + * + * This file is released under the LGPL. + */ + +#ifndef _LINUX_DM_IOCTL_V4_H +#define _LINUX_DM_IOCTL_V4_H + +#include <linux/types.h> + +#define DM_DIR "mapper" /* Slashes not supported */ +#define DM_CONTROL_NODE "control" +#define DM_MAX_TYPE_NAME 16 +#define DM_NAME_LEN 128 +#define DM_UUID_LEN 129 + +/* + * A traditional ioctl interface for the device mapper. + * + * Each device can have two tables associated with it, an + * 'active' table which is the one currently used by io passing + * through the device, and an 'inactive' one which is a table + * that is being prepared as a replacement for the 'active' one. + * + * DM_VERSION: + * Just get the version information for the ioctl interface. + * + * DM_REMOVE_ALL: + * Remove all dm devices, destroy all tables. Only really used + * for debug. + * + * DM_LIST_DEVICES: + * Get a list of all the dm device names. + * + * DM_DEV_CREATE: + * Create a new device, neither the 'active' or 'inactive' table + * slots will be filled. The device will be in suspended state + * after creation, however any io to the device will get errored + * since it will be out-of-bounds. + * + * DM_DEV_REMOVE: + * Remove a device, destroy any tables. + * + * DM_DEV_RENAME: + * Rename a device or set its uuid if none was previously supplied. + * + * DM_SUSPEND: + * This performs both suspend and resume, depending which flag is + * passed in. + * Suspend: This command will not return until all pending io to + * the device has completed. Further io will be deferred until + * the device is resumed. + * Resume: It is no longer an error to issue this command on an + * unsuspended device. If a table is present in the 'inactive' + * slot, it will be moved to the active slot, then the old table + * from the active slot will be _destroyed_. Finally the device + * is resumed. + * + * DM_DEV_STATUS: + * Retrieves the status for the table in the 'active' slot. + * + * DM_DEV_WAIT: + * Wait for a significant event to occur to the device. This + * could either be caused by an event triggered by one of the + * targets of the table in the 'active' slot, or a table change. + * + * DM_TABLE_LOAD: + * Load a table into the 'inactive' slot for the device. The + * device does _not_ need to be suspended prior to this command. + * + * DM_TABLE_CLEAR: + * Destroy any table in the 'inactive' slot (ie. abort). + * + * DM_TABLE_DEPS: + * Return a set of device dependencies for the 'active' table. + * + * DM_TABLE_STATUS: + * Return the targets status for the 'active' table. + * + * DM_TARGET_MSG: + * Pass a message string to the target at a specific offset of a device. + * + * DM_DEV_SET_GEOMETRY: + * Set the geometry of a device by passing in a string in this format: + * + * "cylinders heads sectors_per_track start_sector" + * + * Beware that CHS geometry is nearly obsolete and only provided + * for compatibility with dm devices that can be booted by a PC + * BIOS. See struct hd_geometry for range limits. Also note that + * the geometry is erased if the device size changes. + */ + +/* + * All ioctl arguments consist of a single chunk of memory, with + * this structure at the start. If a uuid is specified any + * lookup (eg. for a DM_INFO) will be done on that, *not* the + * name. + */ +struct dm_ioctl { + /* + * The version number is made up of three parts: + * major - no backward or forward compatibility, + * minor - only backwards compatible, + * patch - both backwards and forwards compatible. + * + * All clients of the ioctl interface should fill in the + * version number of the interface that they were + * compiled with. + * + * All recognised ioctl commands (ie. those that don't + * return -ENOTTY) fill out this field, even if the + * command failed. + */ + __u32 version[3]; /* in/out */ + __u32 data_size; /* total size of data passed in + * including this struct */ + + __u32 data_start; /* offset to start of data + * relative to start of this struct */ + + __u32 target_count; /* in/out */ + __s32 open_count; /* out */ + __u32 flags; /* in/out */ + + /* + * event_nr holds either the event number (input and output) or the + * udev cookie value (input only). + * The DM_DEV_WAIT ioctl takes an event number as input. + * The DM_SUSPEND, DM_DEV_REMOVE and DM_DEV_RENAME ioctls + * use the field as a cookie to return in the DM_COOKIE + * variable with the uevents they issue. + * For output, the ioctls return the event number, not the cookie. + */ + __u32 event_nr; /* in/out */ + __u32 padding; + + __u64 dev; /* in/out */ + + char name[DM_NAME_LEN]; /* device name */ + char uuid[DM_UUID_LEN]; /* unique identifier for + * the block device */ + char data[7]; /* padding or data */ +}; + +/* + * Used to specify tables. These structures appear after the + * dm_ioctl. + */ +struct dm_target_spec { + __u64 sector_start; + __u64 length; + __s32 status; /* used when reading from kernel only */ + + /* + * Location of the next dm_target_spec. + * - When specifying targets on a DM_TABLE_LOAD command, this value is + * the number of bytes from the start of the "current" dm_target_spec + * to the start of the "next" dm_target_spec. + * - When retrieving targets on a DM_TABLE_STATUS command, this value + * is the number of bytes from the start of the first dm_target_spec + * (that follows the dm_ioctl struct) to the start of the "next" + * dm_target_spec. + */ + __u32 next; + + char target_type[DM_MAX_TYPE_NAME]; + + /* + * Parameter string starts immediately after this object. + * Be careful to add padding after string to ensure correct + * alignment of subsequent dm_target_spec. + */ +}; + +/* + * Used to retrieve the target dependencies. + */ +struct dm_target_deps { + __u32 count; /* Array size */ + __u32 padding; /* unused */ + __u64 dev[0]; /* out */ +}; + +/* + * Used to get a list of all dm devices. + */ +struct dm_name_list { + __u64 dev; + __u32 next; /* offset to the next record from + the _start_ of this */ + char name[0]; +}; + +/* + * Used to retrieve the target versions + */ +struct dm_target_versions { + __u32 next; + __u32 version[3]; + + char name[0]; +}; + +/* + * Used to pass message to a target + */ +struct dm_target_msg { + __u64 sector; /* Device sector */ + + char message[0]; +}; + +/* + * If you change this make sure you make the corresponding change + * to dm-ioctl.c:lookup_ioctl() + */ +enum { + /* Top level cmds */ + DM_VERSION_CMD = 0, + DM_REMOVE_ALL_CMD, + DM_LIST_DEVICES_CMD, + + /* device level cmds */ + DM_DEV_CREATE_CMD, + DM_DEV_REMOVE_CMD, + DM_DEV_RENAME_CMD, + DM_DEV_SUSPEND_CMD, + DM_DEV_STATUS_CMD, + DM_DEV_WAIT_CMD, + + /* Table level cmds */ + DM_TABLE_LOAD_CMD, + DM_TABLE_CLEAR_CMD, + DM_TABLE_DEPS_CMD, + DM_TABLE_STATUS_CMD, + + /* Added later */ + DM_LIST_VERSIONS_CMD, + DM_TARGET_MSG_CMD, + DM_DEV_SET_GEOMETRY_CMD, + DM_DEV_ARM_POLL_CMD, +}; + +#define DM_IOCTL 0xfd + +#define DM_VERSION _IOWR(DM_IOCTL, DM_VERSION_CMD, struct dm_ioctl) +#define DM_REMOVE_ALL _IOWR(DM_IOCTL, DM_REMOVE_ALL_CMD, struct dm_ioctl) +#define DM_LIST_DEVICES _IOWR(DM_IOCTL, DM_LIST_DEVICES_CMD, struct dm_ioctl) + +#define DM_DEV_CREATE _IOWR(DM_IOCTL, DM_DEV_CREATE_CMD, struct dm_ioctl) +#define DM_DEV_REMOVE _IOWR(DM_IOCTL, DM_DEV_REMOVE_CMD, struct dm_ioctl) +#define DM_DEV_RENAME _IOWR(DM_IOCTL, DM_DEV_RENAME_CMD, struct dm_ioctl) +#define DM_DEV_SUSPEND _IOWR(DM_IOCTL, DM_DEV_SUSPEND_CMD, struct dm_ioctl) +#define DM_DEV_STATUS _IOWR(DM_IOCTL, DM_DEV_STATUS_CMD, struct dm_ioctl) +#define DM_DEV_WAIT _IOWR(DM_IOCTL, DM_DEV_WAIT_CMD, struct dm_ioctl) +#define DM_DEV_ARM_POLL _IOWR(DM_IOCTL, DM_DEV_ARM_POLL_CMD, struct dm_ioctl) + +#define DM_TABLE_LOAD _IOWR(DM_IOCTL, DM_TABLE_LOAD_CMD, struct dm_ioctl) +#define DM_TABLE_CLEAR _IOWR(DM_IOCTL, DM_TABLE_CLEAR_CMD, struct dm_ioctl) +#define DM_TABLE_DEPS _IOWR(DM_IOCTL, DM_TABLE_DEPS_CMD, struct dm_ioctl) +#define DM_TABLE_STATUS _IOWR(DM_IOCTL, DM_TABLE_STATUS_CMD, struct dm_ioctl) + +#define DM_LIST_VERSIONS _IOWR(DM_IOCTL, DM_LIST_VERSIONS_CMD, struct dm_ioctl) + +#define DM_TARGET_MSG _IOWR(DM_IOCTL, DM_TARGET_MSG_CMD, struct dm_ioctl) +#define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) + +#define DM_VERSION_MAJOR 4 +#define DM_VERSION_MINOR 27 +#define DM_VERSION_PATCHLEVEL 0 +#define DM_VERSION_EXTRA "-ioctl (2018-04-03)" + +/* Status bits */ +#define DM_READONLY_FLAG (1 << 0) /* In/Out */ +#define DM_SUSPEND_FLAG (1 << 1) /* In/Out */ +#define DM_PERSISTENT_DEV_FLAG (1 << 3) /* In */ + +/* + * Flag passed into ioctl STATUS command to get table information + * rather than current status. + */ +#define DM_STATUS_TABLE_FLAG (1 << 4) /* In */ + +/* + * Flags that indicate whether a table is present in either of + * the two table slots that a device has. + */ +#define DM_ACTIVE_PRESENT_FLAG (1 << 5) /* Out */ +#define DM_INACTIVE_PRESENT_FLAG (1 << 6) /* Out */ + +/* + * Indicates that the buffer passed in wasn't big enough for the + * results. + */ +#define DM_BUFFER_FULL_FLAG (1 << 8) /* Out */ + +/* + * This flag is now ignored. + */ +#define DM_SKIP_BDGET_FLAG (1 << 9) /* In */ + +/* + * Set this to avoid attempting to freeze any filesystem when suspending. + */ +#define DM_SKIP_LOCKFS_FLAG (1 << 10) /* In */ + +/* + * Set this to suspend without flushing queued ios. + * Also disables flushing uncommitted changes in the thin target before + * generating statistics for DM_TABLE_STATUS and DM_DEV_WAIT. + */ +#define DM_NOFLUSH_FLAG (1 << 11) /* In */ + +/* + * If set, any table information returned will relate to the inactive + * table instead of the live one. Always check DM_INACTIVE_PRESENT_FLAG + * is set before using the data returned. + */ +#define DM_QUERY_INACTIVE_TABLE_FLAG (1 << 12) /* In */ + +/* + * If set, a uevent was generated for which the caller may need to wait. + */ +#define DM_UEVENT_GENERATED_FLAG (1 << 13) /* Out */ + +/* + * If set, rename changes the uuid not the name. Only permitted + * if no uuid was previously supplied: an existing uuid cannot be changed. + */ +#define DM_UUID_FLAG (1 << 14) /* In */ + +/* + * If set, all buffers are wiped after use. Use when sending + * or requesting sensitive data such as an encryption key. + */ +#define DM_SECURE_DATA_FLAG (1 << 15) /* In */ + +/* + * If set, a message generated output data. + */ +#define DM_DATA_OUT_FLAG (1 << 16) /* Out */ + +/* + * If set with DM_DEV_REMOVE or DM_REMOVE_ALL this indicates that if + * the device cannot be removed immediately because it is still in use + * it should instead be scheduled for removal when it gets closed. + * + * On return from DM_DEV_REMOVE, DM_DEV_STATUS or other ioctls, this + * flag indicates that the device is scheduled to be removed when it + * gets closed. + */ +#define DM_DEFERRED_REMOVE (1 << 17) /* In/Out */ + +/* + * If set, the device is suspended internally. + */ +#define DM_INTERNAL_SUSPEND_FLAG (1 << 18) /* Out */ + +#endif /* _LINUX_DM_IOCTL_H */ diff --git a/src/shared/linux/ethtool.h b/src/shared/linux/ethtool.h new file mode 100644 index 0000000000..f6c45a36c9 --- /dev/null +++ b/src/shared/linux/ethtool.h @@ -0,0 +1,1843 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * ethtool.h: Defines for Linux ethtool. + * + * Copyright (C) 1998 David S. Miller (davem@redhat.com) + * Copyright 2001 Jeff Garzik <jgarzik@pobox.com> + * Portions Copyright 2001 Sun Microsystems (thockin@sun.com) + * Portions Copyright 2002 Intel (eli.kupermann@intel.com, + * christopher.leech@intel.com, + * scott.feldman@intel.com) + * Portions Copyright (C) Sun Microsystems 2008 + */ + +#ifndef _UAPI_LINUX_ETHTOOL_H +#define _UAPI_LINUX_ETHTOOL_H + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/if_ether.h> + +#ifndef __KERNEL__ +#include <limits.h> /* for INT_MAX */ +#endif + +#ifndef __KERNEL_DIV_ROUND_UP +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) +#endif + +/* All structures exposed to userland should be defined such that they + * have the same layout for 32-bit and 64-bit userland. + */ + +/** + * struct ethtool_cmd - DEPRECATED, link control and status + * This structure is DEPRECATED, please use struct ethtool_link_settings. + * @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET + * @supported: Bitmask of %SUPPORTED_* flags for the link modes, + * physical connectors and other link features for which the + * interface supports autonegotiation or auto-detection. + * Read-only. + * @advertising: Bitmask of %ADVERTISED_* flags for the link modes, + * physical connectors and other link features that are + * advertised through autonegotiation or enabled for + * auto-detection. + * @speed: Low bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN + * @duplex: Duplex mode; one of %DUPLEX_* + * @port: Physical connector type; one of %PORT_* + * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not + * applicable. For clause 45 PHYs this is the PRTAD. + * @transceiver: Historically used to distinguish different possible + * PHY types, but not in a consistent way. Deprecated. + * @autoneg: Enable/disable autonegotiation and auto-detection; + * either %AUTONEG_DISABLE or %AUTONEG_ENABLE + * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO + * protocols supported by the interface; 0 if unknown. + * Read-only. + * @maxtxpkt: Historically used to report TX IRQ coalescing; now + * obsoleted by &struct ethtool_coalesce. Read-only; deprecated. + * @maxrxpkt: Historically used to report RX IRQ coalescing; now + * obsoleted by &struct ethtool_coalesce. Read-only; deprecated. + * @speed_hi: High bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN + * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of + * %ETH_TP_MDI_*. If the status is unknown or not applicable, the + * value will be %ETH_TP_MDI_INVALID. Read-only. + * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of + * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads + * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected. + * When written successfully, the link should be renegotiated if + * necessary. + * @lp_advertising: Bitmask of %ADVERTISED_* flags for the link modes + * and other link features that the link partner advertised + * through autonegotiation; 0 if unknown or not applicable. + * Read-only. + * + * The link speed in Mbps is split between @speed and @speed_hi. Use + * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to + * access it. + * + * If autonegotiation is disabled, the speed and @duplex represent the + * fixed link mode and are writable if the driver supports multiple + * link modes. If it is enabled then they are read-only; if the link + * is up they represent the negotiated link mode; if the link is down, + * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and + * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode. + * + * Some hardware interfaces may have multiple PHYs and/or physical + * connectors fitted or do not allow the driver to detect which are + * fitted. For these interfaces @port and/or @phy_address may be + * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE. + * Otherwise, attempts to write different values may be ignored or + * rejected. + * + * Users should assume that all fields not marked read-only are + * writable and subject to validation by the driver. They should use + * %ETHTOOL_GSET to get the current values before making specific + * changes and then applying them with %ETHTOOL_SSET. + * + * Deprecated fields should be ignored by both users and drivers. + */ +struct ethtool_cmd { + __u32 cmd; + __u32 supported; + __u32 advertising; + __u16 speed; + __u8 duplex; + __u8 port; + __u8 phy_address; + __u8 transceiver; + __u8 autoneg; + __u8 mdio_support; + __u32 maxtxpkt; + __u32 maxrxpkt; + __u16 speed_hi; + __u8 eth_tp_mdix; + __u8 eth_tp_mdix_ctrl; + __u32 lp_advertising; + __u32 reserved[2]; +}; + +static inline void ethtool_cmd_speed_set(struct ethtool_cmd *ep, + __u32 speed) +{ + ep->speed = (__u16)(speed & 0xFFFF); + ep->speed_hi = (__u16)(speed >> 16); +} + +static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep) +{ + return (ep->speed_hi << 16) | ep->speed; +} + +/* Device supports clause 22 register access to PHY or peripherals + * using the interface defined in <linux/mii.h>. This should not be + * set if there are known to be no such peripherals present or if + * the driver only emulates clause 22 registers for compatibility. + */ +#define ETH_MDIO_SUPPORTS_C22 1 + +/* Device supports clause 45 register access to PHY or peripherals + * using the interface defined in <linux/mii.h> and <linux/mdio.h>. + * This should not be set if there are known to be no such peripherals + * present. + */ +#define ETH_MDIO_SUPPORTS_C45 2 + +#define ETHTOOL_FWVERS_LEN 32 +#define ETHTOOL_BUSINFO_LEN 32 +#define ETHTOOL_EROMVERS_LEN 32 + +/** + * struct ethtool_drvinfo - general driver and device information + * @cmd: Command number = %ETHTOOL_GDRVINFO + * @driver: Driver short name. This should normally match the name + * in its bus driver structure (e.g. pci_driver::name). Must + * not be an empty string. + * @version: Driver version string; may be an empty string + * @fw_version: Firmware version string; may be an empty string + * @erom_version: Expansion ROM version string; may be an empty string + * @bus_info: Device bus address. This should match the dev_name() + * string for the underlying bus device, if there is one. May be + * an empty string. + * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and + * %ETHTOOL_SPFLAGS commands; also the number of strings in the + * %ETH_SS_PRIV_FLAGS set + * @n_stats: Number of u64 statistics returned by the %ETHTOOL_GSTATS + * command; also the number of strings in the %ETH_SS_STATS set + * @testinfo_len: Number of results returned by the %ETHTOOL_TEST + * command; also the number of strings in the %ETH_SS_TEST set + * @eedump_len: Size of EEPROM accessible through the %ETHTOOL_GEEPROM + * and %ETHTOOL_SEEPROM commands, in bytes + * @regdump_len: Size of register dump returned by the %ETHTOOL_GREGS + * command, in bytes + * + * Users can use the %ETHTOOL_GSSET_INFO command to get the number of + * strings in any string set (from Linux 2.6.34). + * + * Drivers should set at most @driver, @version, @fw_version and + * @bus_info in their get_drvinfo() implementation. The ethtool + * core fills in the other fields using other driver operations. + */ +struct ethtool_drvinfo { + __u32 cmd; + char driver[32]; + char version[32]; + char fw_version[ETHTOOL_FWVERS_LEN]; + char bus_info[ETHTOOL_BUSINFO_LEN]; + char erom_version[ETHTOOL_EROMVERS_LEN]; + char reserved2[12]; + __u32 n_priv_flags; + __u32 n_stats; + __u32 testinfo_len; + __u32 eedump_len; + __u32 regdump_len; +}; + +#define SOPASS_MAX 6 + +/** + * struct ethtool_wolinfo - Wake-On-Lan configuration + * @cmd: Command number = %ETHTOOL_GWOL or %ETHTOOL_SWOL + * @supported: Bitmask of %WAKE_* flags for supported Wake-On-Lan modes. + * Read-only. + * @wolopts: Bitmask of %WAKE_* flags for enabled Wake-On-Lan modes. + * @sopass: SecureOn(tm) password; meaningful only if %WAKE_MAGICSECURE + * is set in @wolopts. + */ +struct ethtool_wolinfo { + __u32 cmd; + __u32 supported; + __u32 wolopts; + __u8 sopass[SOPASS_MAX]; +}; + +/* for passing single values */ +struct ethtool_value { + __u32 cmd; + __u32 data; +}; + +#define PFC_STORM_PREVENTION_AUTO 0xffff +#define PFC_STORM_PREVENTION_DISABLE 0 + +enum tunable_id { + ETHTOOL_ID_UNSPEC, + ETHTOOL_RX_COPYBREAK, + ETHTOOL_TX_COPYBREAK, + ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ + /* + * Add your fresh new tunable attribute above and remember to update + * tunable_strings[] in net/core/ethtool.c + */ + __ETHTOOL_TUNABLE_COUNT, +}; + +enum tunable_type_id { + ETHTOOL_TUNABLE_UNSPEC, + ETHTOOL_TUNABLE_U8, + ETHTOOL_TUNABLE_U16, + ETHTOOL_TUNABLE_U32, + ETHTOOL_TUNABLE_U64, + ETHTOOL_TUNABLE_STRING, + ETHTOOL_TUNABLE_S8, + ETHTOOL_TUNABLE_S16, + ETHTOOL_TUNABLE_S32, + ETHTOOL_TUNABLE_S64, +}; + +struct ethtool_tunable { + __u32 cmd; + __u32 id; + __u32 type_id; + __u32 len; + void *data[0]; +}; + +#define DOWNSHIFT_DEV_DEFAULT_COUNT 0xff +#define DOWNSHIFT_DEV_DISABLE 0 + +enum phy_tunable_id { + ETHTOOL_PHY_ID_UNSPEC, + ETHTOOL_PHY_DOWNSHIFT, + /* + * Add your fresh new phy tunable attribute above and remember to update + * phy_tunable_strings[] in net/core/ethtool.c + */ + __ETHTOOL_PHY_TUNABLE_COUNT, +}; + +/** + * struct ethtool_regs - hardware register dump + * @cmd: Command number = %ETHTOOL_GREGS + * @version: Dump format version. This is driver-specific and may + * distinguish different chips/revisions. Drivers must use new + * version numbers whenever the dump format changes in an + * incompatible way. + * @len: On entry, the real length of @data. On return, the number of + * bytes used. + * @data: Buffer for the register dump + * + * Users should use %ETHTOOL_GDRVINFO to find the maximum length of + * a register dump for the interface. They must allocate the buffer + * immediately following this structure. + */ +struct ethtool_regs { + __u32 cmd; + __u32 version; + __u32 len; + __u8 data[0]; +}; + +/** + * struct ethtool_eeprom - EEPROM dump + * @cmd: Command number = %ETHTOOL_GEEPROM, %ETHTOOL_GMODULEEEPROM or + * %ETHTOOL_SEEPROM + * @magic: A 'magic cookie' value to guard against accidental changes. + * The value passed in to %ETHTOOL_SEEPROM must match the value + * returned by %ETHTOOL_GEEPROM for the same device. This is + * unused when @cmd is %ETHTOOL_GMODULEEEPROM. + * @offset: Offset within the EEPROM to begin reading/writing, in bytes + * @len: On entry, number of bytes to read/write. On successful + * return, number of bytes actually read/written. In case of + * error, this may indicate at what point the error occurred. + * @data: Buffer to read/write from + * + * Users may use %ETHTOOL_GDRVINFO or %ETHTOOL_GMODULEINFO to find + * the length of an on-board or module EEPROM, respectively. They + * must allocate the buffer immediately following this structure. + */ +struct ethtool_eeprom { + __u32 cmd; + __u32 magic; + __u32 offset; + __u32 len; + __u8 data[0]; +}; + +/** + * struct ethtool_eee - Energy Efficient Ethernet information + * @cmd: ETHTOOL_{G,S}EEE + * @supported: Mask of %SUPPORTED_* flags for the speed/duplex combinations + * for which there is EEE support. + * @advertised: Mask of %ADVERTISED_* flags for the speed/duplex combinations + * advertised as eee capable. + * @lp_advertised: Mask of %ADVERTISED_* flags for the speed/duplex + * combinations advertised by the link partner as eee capable. + * @eee_active: Result of the eee auto negotiation. + * @eee_enabled: EEE configured mode (enabled/disabled). + * @tx_lpi_enabled: Whether the interface should assert its tx lpi, given + * that eee was negotiated. + * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting + * its tx lpi (after reaching 'idle' state). Effective only when eee + * was negotiated and tx_lpi_enabled was set. + */ +struct ethtool_eee { + __u32 cmd; + __u32 supported; + __u32 advertised; + __u32 lp_advertised; + __u32 eee_active; + __u32 eee_enabled; + __u32 tx_lpi_enabled; + __u32 tx_lpi_timer; + __u32 reserved[2]; +}; + +/** + * struct ethtool_modinfo - plugin module eeprom information + * @cmd: %ETHTOOL_GMODULEINFO + * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx + * @eeprom_len: Length of the eeprom + * + * This structure is used to return the information to + * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM. + * The type code indicates the eeprom data format + */ +struct ethtool_modinfo { + __u32 cmd; + __u32 type; + __u32 eeprom_len; + __u32 reserved[8]; +}; + +/** + * struct ethtool_coalesce - coalescing parameters for IRQs and stats updates + * @cmd: ETHTOOL_{G,S}COALESCE + * @rx_coalesce_usecs: How many usecs to delay an RX interrupt after + * a packet arrives. + * @rx_max_coalesced_frames: Maximum number of packets to receive + * before an RX interrupt. + * @rx_coalesce_usecs_irq: Same as @rx_coalesce_usecs, except that + * this value applies while an IRQ is being serviced by the host. + * @rx_max_coalesced_frames_irq: Same as @rx_max_coalesced_frames, + * except that this value applies while an IRQ is being serviced + * by the host. + * @tx_coalesce_usecs: How many usecs to delay a TX interrupt after + * a packet is sent. + * @tx_max_coalesced_frames: Maximum number of packets to be sent + * before a TX interrupt. + * @tx_coalesce_usecs_irq: Same as @tx_coalesce_usecs, except that + * this value applies while an IRQ is being serviced by the host. + * @tx_max_coalesced_frames_irq: Same as @tx_max_coalesced_frames, + * except that this value applies while an IRQ is being serviced + * by the host. + * @stats_block_coalesce_usecs: How many usecs to delay in-memory + * statistics block updates. Some drivers do not have an + * in-memory statistic block, and in such cases this value is + * ignored. This value must not be zero. + * @use_adaptive_rx_coalesce: Enable adaptive RX coalescing. + * @use_adaptive_tx_coalesce: Enable adaptive TX coalescing. + * @pkt_rate_low: Threshold for low packet rate (packets per second). + * @rx_coalesce_usecs_low: How many usecs to delay an RX interrupt after + * a packet arrives, when the packet rate is below @pkt_rate_low. + * @rx_max_coalesced_frames_low: Maximum number of packets to be received + * before an RX interrupt, when the packet rate is below @pkt_rate_low. + * @tx_coalesce_usecs_low: How many usecs to delay a TX interrupt after + * a packet is sent, when the packet rate is below @pkt_rate_low. + * @tx_max_coalesced_frames_low: Maximum nuumber of packets to be sent before + * a TX interrupt, when the packet rate is below @pkt_rate_low. + * @pkt_rate_high: Threshold for high packet rate (packets per second). + * @rx_coalesce_usecs_high: How many usecs to delay an RX interrupt after + * a packet arrives, when the packet rate is above @pkt_rate_high. + * @rx_max_coalesced_frames_high: Maximum number of packets to be received + * before an RX interrupt, when the packet rate is above @pkt_rate_high. + * @tx_coalesce_usecs_high: How many usecs to delay a TX interrupt after + * a packet is sent, when the packet rate is above @pkt_rate_high. + * @tx_max_coalesced_frames_high: Maximum number of packets to be sent before + * a TX interrupt, when the packet rate is above @pkt_rate_high. + * @rate_sample_interval: How often to do adaptive coalescing packet rate + * sampling, measured in seconds. Must not be zero. + * + * Each pair of (usecs, max_frames) fields specifies that interrupts + * should be coalesced until + * (usecs > 0 && time_since_first_completion >= usecs) || + * (max_frames > 0 && completed_frames >= max_frames) + * + * It is illegal to set both usecs and max_frames to zero as this + * would cause interrupts to never be generated. To disable + * coalescing, set usecs = 0 and max_frames = 1. + * + * Some implementations ignore the value of max_frames and use the + * condition time_since_first_completion >= usecs + * + * This is deprecated. Drivers for hardware that does not support + * counting completions should validate that max_frames == !rx_usecs. + * + * Adaptive RX/TX coalescing is an algorithm implemented by some + * drivers to improve latency under low packet rates and improve + * throughput under high packet rates. Some drivers only implement + * one of RX or TX adaptive coalescing. Anything not implemented by + * the driver causes these values to be silently ignored. + * + * When the packet rate is below @pkt_rate_high but above + * @pkt_rate_low (both measured in packets per second) the + * normal {rx,tx}_* coalescing parameters are used. + */ +struct ethtool_coalesce { + __u32 cmd; + __u32 rx_coalesce_usecs; + __u32 rx_max_coalesced_frames; + __u32 rx_coalesce_usecs_irq; + __u32 rx_max_coalesced_frames_irq; + __u32 tx_coalesce_usecs; + __u32 tx_max_coalesced_frames; + __u32 tx_coalesce_usecs_irq; + __u32 tx_max_coalesced_frames_irq; + __u32 stats_block_coalesce_usecs; + __u32 use_adaptive_rx_coalesce; + __u32 use_adaptive_tx_coalesce; + __u32 pkt_rate_low; + __u32 rx_coalesce_usecs_low; + __u32 rx_max_coalesced_frames_low; + __u32 tx_coalesce_usecs_low; + __u32 tx_max_coalesced_frames_low; + __u32 pkt_rate_high; + __u32 rx_coalesce_usecs_high; + __u32 rx_max_coalesced_frames_high; + __u32 tx_coalesce_usecs_high; + __u32 tx_max_coalesced_frames_high; + __u32 rate_sample_interval; +}; + +/** + * struct ethtool_ringparam - RX/TX ring parameters + * @cmd: Command number = %ETHTOOL_GRINGPARAM or %ETHTOOL_SRINGPARAM + * @rx_max_pending: Maximum supported number of pending entries per + * RX ring. Read-only. + * @rx_mini_max_pending: Maximum supported number of pending entries + * per RX mini ring. Read-only. + * @rx_jumbo_max_pending: Maximum supported number of pending entries + * per RX jumbo ring. Read-only. + * @tx_max_pending: Maximum supported number of pending entries per + * TX ring. Read-only. + * @rx_pending: Current maximum number of pending entries per RX ring + * @rx_mini_pending: Current maximum number of pending entries per RX + * mini ring + * @rx_jumbo_pending: Current maximum number of pending entries per RX + * jumbo ring + * @tx_pending: Current maximum supported number of pending entries + * per TX ring + * + * If the interface does not have separate RX mini and/or jumbo rings, + * @rx_mini_max_pending and/or @rx_jumbo_max_pending will be 0. + * + * There may also be driver-dependent minimum values for the number + * of entries per ring. + */ +struct ethtool_ringparam { + __u32 cmd; + __u32 rx_max_pending; + __u32 rx_mini_max_pending; + __u32 rx_jumbo_max_pending; + __u32 tx_max_pending; + __u32 rx_pending; + __u32 rx_mini_pending; + __u32 rx_jumbo_pending; + __u32 tx_pending; +}; + +/** + * struct ethtool_channels - configuring number of network channel + * @cmd: ETHTOOL_{G,S}CHANNELS + * @max_rx: Read only. Maximum number of receive channel the driver support. + * @max_tx: Read only. Maximum number of transmit channel the driver support. + * @max_other: Read only. Maximum number of other channel the driver support. + * @max_combined: Read only. Maximum number of combined channel the driver + * support. Set of queues RX, TX or other. + * @rx_count: Valid values are in the range 1 to the max_rx. + * @tx_count: Valid values are in the range 1 to the max_tx. + * @other_count: Valid values are in the range 1 to the max_other. + * @combined_count: Valid values are in the range 1 to the max_combined. + * + * This can be used to configure RX, TX and other channels. + */ + +struct ethtool_channels { + __u32 cmd; + __u32 max_rx; + __u32 max_tx; + __u32 max_other; + __u32 max_combined; + __u32 rx_count; + __u32 tx_count; + __u32 other_count; + __u32 combined_count; +}; + +/** + * struct ethtool_pauseparam - Ethernet pause (flow control) parameters + * @cmd: Command number = %ETHTOOL_GPAUSEPARAM or %ETHTOOL_SPAUSEPARAM + * @autoneg: Flag to enable autonegotiation of pause frame use + * @rx_pause: Flag to enable reception of pause frames + * @tx_pause: Flag to enable transmission of pause frames + * + * Drivers should reject a non-zero setting of @autoneg when + * autoneogotiation is disabled (or not supported) for the link. + * + * If the link is autonegotiated, drivers should use + * mii_advertise_flowctrl() or similar code to set the advertised + * pause frame capabilities based on the @rx_pause and @tx_pause flags, + * even if @autoneg is zero. They should also allow the advertised + * pause frame capabilities to be controlled directly through the + * advertising field of &struct ethtool_cmd. + * + * If @autoneg is non-zero, the MAC is configured to send and/or + * receive pause frames according to the result of autonegotiation. + * Otherwise, it is configured directly based on the @rx_pause and + * @tx_pause flags. + */ +struct ethtool_pauseparam { + __u32 cmd; + __u32 autoneg; + __u32 rx_pause; + __u32 tx_pause; +}; + +#define ETH_GSTRING_LEN 32 + +/** + * enum ethtool_stringset - string set ID + * @ETH_SS_TEST: Self-test result names, for use with %ETHTOOL_TEST + * @ETH_SS_STATS: Statistic names, for use with %ETHTOOL_GSTATS + * @ETH_SS_PRIV_FLAGS: Driver private flag names, for use with + * %ETHTOOL_GPFLAGS and %ETHTOOL_SPFLAGS + * @ETH_SS_NTUPLE_FILTERS: Previously used with %ETHTOOL_GRXNTUPLE; + * now deprecated + * @ETH_SS_FEATURES: Device feature names + * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names + * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS + * @ETH_SS_PHY_TUNABLES: PHY tunable names + */ +enum ethtool_stringset { + ETH_SS_TEST = 0, + ETH_SS_STATS, + ETH_SS_PRIV_FLAGS, + ETH_SS_NTUPLE_FILTERS, + ETH_SS_FEATURES, + ETH_SS_RSS_HASH_FUNCS, + ETH_SS_TUNABLES, + ETH_SS_PHY_STATS, + ETH_SS_PHY_TUNABLES, +}; + +/** + * struct ethtool_gstrings - string set for data tagging + * @cmd: Command number = %ETHTOOL_GSTRINGS + * @string_set: String set ID; one of &enum ethtool_stringset + * @len: On return, the number of strings in the string set + * @data: Buffer for strings. Each string is null-padded to a size of + * %ETH_GSTRING_LEN. + * + * Users must use %ETHTOOL_GSSET_INFO to find the number of strings in + * the string set. They must allocate a buffer of the appropriate + * size immediately following this structure. + */ +struct ethtool_gstrings { + __u32 cmd; + __u32 string_set; + __u32 len; + __u8 data[0]; +}; + +/** + * struct ethtool_sset_info - string set information + * @cmd: Command number = %ETHTOOL_GSSET_INFO + * @sset_mask: On entry, a bitmask of string sets to query, with bits + * numbered according to &enum ethtool_stringset. On return, a + * bitmask of those string sets queried that are supported. + * @data: Buffer for string set sizes. On return, this contains the + * size of each string set that was queried and supported, in + * order of ID. + * + * Example: The user passes in @sset_mask = 0x7 (sets 0, 1, 2) and on + * return @sset_mask == 0x6 (sets 1, 2). Then @data[0] contains the + * size of set 1 and @data[1] contains the size of set 2. + * + * Users must allocate a buffer of the appropriate size (4 * number of + * sets queried) immediately following this structure. + */ +struct ethtool_sset_info { + __u32 cmd; + __u32 reserved; + __u64 sset_mask; + __u32 data[0]; +}; + +/** + * enum ethtool_test_flags - flags definition of ethtool_test + * @ETH_TEST_FL_OFFLINE: if set perform online and offline tests, otherwise + * only online tests. + * @ETH_TEST_FL_FAILED: Driver set this flag if test fails. + * @ETH_TEST_FL_EXTERNAL_LB: Application request to perform external loopback + * test. + * @ETH_TEST_FL_EXTERNAL_LB_DONE: Driver performed the external loopback test + */ + +enum ethtool_test_flags { + ETH_TEST_FL_OFFLINE = (1 << 0), + ETH_TEST_FL_FAILED = (1 << 1), + ETH_TEST_FL_EXTERNAL_LB = (1 << 2), + ETH_TEST_FL_EXTERNAL_LB_DONE = (1 << 3), +}; + +/** + * struct ethtool_test - device self-test invocation + * @cmd: Command number = %ETHTOOL_TEST + * @flags: A bitmask of flags from &enum ethtool_test_flags. Some + * flags may be set by the user on entry; others may be set by + * the driver on return. + * @len: On return, the number of test results + * @data: Array of test results + * + * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the + * number of test results that will be returned. They must allocate a + * buffer of the appropriate size (8 * number of results) immediately + * following this structure. + */ +struct ethtool_test { + __u32 cmd; + __u32 flags; + __u32 reserved; + __u32 len; + __u64 data[0]; +}; + +/** + * struct ethtool_stats - device-specific statistics + * @cmd: Command number = %ETHTOOL_GSTATS + * @n_stats: On return, the number of statistics + * @data: Array of statistics + * + * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the + * number of statistics that will be returned. They must allocate a + * buffer of the appropriate size (8 * number of statistics) + * immediately following this structure. + */ +struct ethtool_stats { + __u32 cmd; + __u32 n_stats; + __u64 data[0]; +}; + +/** + * struct ethtool_perm_addr - permanent hardware address + * @cmd: Command number = %ETHTOOL_GPERMADDR + * @size: On entry, the size of the buffer. On return, the size of the + * address. The command fails if the buffer is too small. + * @data: Buffer for the address + * + * Users must allocate the buffer immediately following this structure. + * A buffer size of %MAX_ADDR_LEN should be sufficient for any address + * type. + */ +struct ethtool_perm_addr { + __u32 cmd; + __u32 size; + __u8 data[0]; +}; + +/* boolean flags controlling per-interface behavior characteristics. + * When reading, the flag indicates whether or not a certain behavior + * is enabled/present. When writing, the flag indicates whether + * or not the driver should turn on (set) or off (clear) a behavior. + * + * Some behaviors may read-only (unconditionally absent or present). + * If such is the case, return EINVAL in the set-flags operation if the + * flag differs from the read-only value. + */ +enum ethtool_flags { + ETH_FLAG_TXVLAN = (1 << 7), /* TX VLAN offload enabled */ + ETH_FLAG_RXVLAN = (1 << 8), /* RX VLAN offload enabled */ + ETH_FLAG_LRO = (1 << 15), /* LRO is enabled */ + ETH_FLAG_NTUPLE = (1 << 27), /* N-tuple filters enabled */ + ETH_FLAG_RXHASH = (1 << 28), +}; + +/* The following structures are for supporting RX network flow + * classification and RX n-tuple configuration. Note, all multibyte + * fields, e.g., ip4src, ip4dst, psrc, pdst, spi, etc. are expected to + * be in network byte order. + */ + +/** + * struct ethtool_tcpip4_spec - flow specification for TCP/IPv4 etc. + * @ip4src: Source host + * @ip4dst: Destination host + * @psrc: Source port + * @pdst: Destination port + * @tos: Type-of-service + * + * This can be used to specify a TCP/IPv4, UDP/IPv4 or SCTP/IPv4 flow. + */ +struct ethtool_tcpip4_spec { + __be32 ip4src; + __be32 ip4dst; + __be16 psrc; + __be16 pdst; + __u8 tos; +}; + +/** + * struct ethtool_ah_espip4_spec - flow specification for IPsec/IPv4 + * @ip4src: Source host + * @ip4dst: Destination host + * @spi: Security parameters index + * @tos: Type-of-service + * + * This can be used to specify an IPsec transport or tunnel over IPv4. + */ +struct ethtool_ah_espip4_spec { + __be32 ip4src; + __be32 ip4dst; + __be32 spi; + __u8 tos; +}; + +#define ETH_RX_NFC_IP4 1 + +/** + * struct ethtool_usrip4_spec - general flow specification for IPv4 + * @ip4src: Source host + * @ip4dst: Destination host + * @l4_4_bytes: First 4 bytes of transport (layer 4) header + * @tos: Type-of-service + * @ip_ver: Value must be %ETH_RX_NFC_IP4; mask must be 0 + * @proto: Transport protocol number; mask must be 0 + */ +struct ethtool_usrip4_spec { + __be32 ip4src; + __be32 ip4dst; + __be32 l4_4_bytes; + __u8 tos; + __u8 ip_ver; + __u8 proto; +}; + +/** + * struct ethtool_tcpip6_spec - flow specification for TCP/IPv6 etc. + * @ip6src: Source host + * @ip6dst: Destination host + * @psrc: Source port + * @pdst: Destination port + * @tclass: Traffic Class + * + * This can be used to specify a TCP/IPv6, UDP/IPv6 or SCTP/IPv6 flow. + */ +struct ethtool_tcpip6_spec { + __be32 ip6src[4]; + __be32 ip6dst[4]; + __be16 psrc; + __be16 pdst; + __u8 tclass; +}; + +/** + * struct ethtool_ah_espip6_spec - flow specification for IPsec/IPv6 + * @ip6src: Source host + * @ip6dst: Destination host + * @spi: Security parameters index + * @tclass: Traffic Class + * + * This can be used to specify an IPsec transport or tunnel over IPv6. + */ +struct ethtool_ah_espip6_spec { + __be32 ip6src[4]; + __be32 ip6dst[4]; + __be32 spi; + __u8 tclass; +}; + +/** + * struct ethtool_usrip6_spec - general flow specification for IPv6 + * @ip6src: Source host + * @ip6dst: Destination host + * @l4_4_bytes: First 4 bytes of transport (layer 4) header + * @tclass: Traffic Class + * @l4_proto: Transport protocol number (nexthdr after any Extension Headers) + */ +struct ethtool_usrip6_spec { + __be32 ip6src[4]; + __be32 ip6dst[4]; + __be32 l4_4_bytes; + __u8 tclass; + __u8 l4_proto; +}; + +union ethtool_flow_union { + struct ethtool_tcpip4_spec tcp_ip4_spec; + struct ethtool_tcpip4_spec udp_ip4_spec; + struct ethtool_tcpip4_spec sctp_ip4_spec; + struct ethtool_ah_espip4_spec ah_ip4_spec; + struct ethtool_ah_espip4_spec esp_ip4_spec; + struct ethtool_usrip4_spec usr_ip4_spec; + struct ethtool_tcpip6_spec tcp_ip6_spec; + struct ethtool_tcpip6_spec udp_ip6_spec; + struct ethtool_tcpip6_spec sctp_ip6_spec; + struct ethtool_ah_espip6_spec ah_ip6_spec; + struct ethtool_ah_espip6_spec esp_ip6_spec; + struct ethtool_usrip6_spec usr_ip6_spec; + struct ethhdr ether_spec; + __u8 hdata[52]; +}; + +/** + * struct ethtool_flow_ext - additional RX flow fields + * @h_dest: destination MAC address + * @vlan_etype: VLAN EtherType + * @vlan_tci: VLAN tag control information + * @data: user defined data + * + * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT + * is set in &struct ethtool_rx_flow_spec @flow_type. + * @h_dest is valid if %FLOW_MAC_EXT is set. + */ +struct ethtool_flow_ext { + __u8 padding[2]; + unsigned char h_dest[ETH_ALEN]; + __be16 vlan_etype; + __be16 vlan_tci; + __be32 data[2]; +}; + +/** + * struct ethtool_rx_flow_spec - classification rule for RX flows + * @flow_type: Type of match to perform, e.g. %TCP_V4_FLOW + * @h_u: Flow fields to match (dependent on @flow_type) + * @h_ext: Additional fields to match + * @m_u: Masks for flow field bits to be matched + * @m_ext: Masks for additional field bits to be matched + * Note, all additional fields must be ignored unless @flow_type + * includes the %FLOW_EXT or %FLOW_MAC_EXT flag + * (see &struct ethtool_flow_ext description). + * @ring_cookie: RX ring/queue index to deliver to, or %RX_CLS_FLOW_DISC + * if packets should be discarded, or %RX_CLS_FLOW_WAKE if the + * packets should be used for Wake-on-LAN with %WAKE_FILTER + * @location: Location of rule in the table. Locations must be + * numbered such that a flow matching multiple rules will be + * classified according to the first (lowest numbered) rule. + */ +struct ethtool_rx_flow_spec { + __u32 flow_type; + union ethtool_flow_union h_u; + struct ethtool_flow_ext h_ext; + union ethtool_flow_union m_u; + struct ethtool_flow_ext m_ext; + __u64 ring_cookie; + __u32 location; +}; + +/* How rings are laid out when accessing virtual functions or + * offloaded queues is device specific. To allow users to do flow + * steering and specify these queues the ring cookie is partitioned + * into a 32bit queue index with an 8 bit virtual function id. + * This also leaves the 3bytes for further specifiers. It is possible + * future devices may support more than 256 virtual functions if + * devices start supporting PCIe w/ARI. However at the moment I + * do not know of any devices that support this so I do not reserve + * space for this at this time. If a future patch consumes the next + * byte it should be aware of this possibility. + */ +#define ETHTOOL_RX_FLOW_SPEC_RING 0x00000000FFFFFFFFLL +#define ETHTOOL_RX_FLOW_SPEC_RING_VF 0x000000FF00000000LL +#define ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF 32 +static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie) +{ + return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie; +} + +static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie) +{ + return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >> + ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF; +} + +/** + * struct ethtool_rxnfc - command to get or set RX flow classification rules + * @cmd: Specific command number - %ETHTOOL_GRXFH, %ETHTOOL_SRXFH, + * %ETHTOOL_GRXRINGS, %ETHTOOL_GRXCLSRLCNT, %ETHTOOL_GRXCLSRULE, + * %ETHTOOL_GRXCLSRLALL, %ETHTOOL_SRXCLSRLDEL or %ETHTOOL_SRXCLSRLINS + * @flow_type: Type of flow to be affected, e.g. %TCP_V4_FLOW + * @data: Command-dependent value + * @fs: Flow classification rule + * @rss_context: RSS context to be affected + * @rule_cnt: Number of rules to be affected + * @rule_locs: Array of used rule locations + * + * For %ETHTOOL_GRXFH and %ETHTOOL_SRXFH, @data is a bitmask indicating + * the fields included in the flow hash, e.g. %RXH_IP_SRC. The following + * structure fields must not be used, except that if @flow_type includes + * the %FLOW_RSS flag, then @rss_context determines which RSS context to + * act on. + * + * For %ETHTOOL_GRXRINGS, @data is set to the number of RX rings/queues + * on return. + * + * For %ETHTOOL_GRXCLSRLCNT, @rule_cnt is set to the number of defined + * rules on return. If @data is non-zero on return then it is the + * size of the rule table, plus the flag %RX_CLS_LOC_SPECIAL if the + * driver supports any special location values. If that flag is not + * set in @data then special location values should not be used. + * + * For %ETHTOOL_GRXCLSRULE, @fs.@location specifies the location of an + * existing rule on entry and @fs contains the rule on return; if + * @fs.@flow_type includes the %FLOW_RSS flag, then @rss_context is + * filled with the RSS context ID associated with the rule. + * + * For %ETHTOOL_GRXCLSRLALL, @rule_cnt specifies the array size of the + * user buffer for @rule_locs on entry. On return, @data is the size + * of the rule table, @rule_cnt is the number of defined rules, and + * @rule_locs contains the locations of the defined rules. Drivers + * must use the second parameter to get_rxnfc() instead of @rule_locs. + * + * For %ETHTOOL_SRXCLSRLINS, @fs specifies the rule to add or update. + * @fs.@location either specifies the location to use or is a special + * location value with %RX_CLS_LOC_SPECIAL flag set. On return, + * @fs.@location is the actual rule location. If @fs.@flow_type + * includes the %FLOW_RSS flag, @rss_context is the RSS context ID to + * use for flow spreading traffic which matches this rule. The value + * from the rxfh indirection table will be added to @fs.@ring_cookie + * to choose which ring to deliver to. + * + * For %ETHTOOL_SRXCLSRLDEL, @fs.@location specifies the location of an + * existing rule on entry. + * + * A driver supporting the special location values for + * %ETHTOOL_SRXCLSRLINS may add the rule at any suitable unused + * location, and may remove a rule at a later location (lower + * priority) that matches exactly the same set of flows. The special + * values are %RX_CLS_LOC_ANY, selecting any location; + * %RX_CLS_LOC_FIRST, selecting the first suitable location (maximum + * priority); and %RX_CLS_LOC_LAST, selecting the last suitable + * location (minimum priority). Additional special values may be + * defined in future and drivers must return -%EINVAL for any + * unrecognised value. + */ +struct ethtool_rxnfc { + __u32 cmd; + __u32 flow_type; + __u64 data; + struct ethtool_rx_flow_spec fs; + union { + __u32 rule_cnt; + __u32 rss_context; + }; + __u32 rule_locs[0]; +}; + + +/** + * struct ethtool_rxfh_indir - command to get or set RX flow hash indirection + * @cmd: Specific command number - %ETHTOOL_GRXFHINDIR or %ETHTOOL_SRXFHINDIR + * @size: On entry, the array size of the user buffer, which may be zero. + * On return from %ETHTOOL_GRXFHINDIR, the array size of the hardware + * indirection table. + * @ring_index: RX ring/queue index for each hash value + * + * For %ETHTOOL_GRXFHINDIR, a @size of zero means that only the size + * should be returned. For %ETHTOOL_SRXFHINDIR, a @size of zero means + * the table should be reset to default values. This last feature + * is not supported by the original implementations. + */ +struct ethtool_rxfh_indir { + __u32 cmd; + __u32 size; + __u32 ring_index[0]; +}; + +/** + * struct ethtool_rxfh - command to get/set RX flow hash indir or/and hash key. + * @cmd: Specific command number - %ETHTOOL_GRSSH or %ETHTOOL_SRSSH + * @rss_context: RSS context identifier. Context 0 is the default for normal + * traffic; other contexts can be referenced as the destination for RX flow + * classification rules. %ETH_RXFH_CONTEXT_ALLOC is used with command + * %ETHTOOL_SRSSH to allocate a new RSS context; on return this field will + * contain the ID of the newly allocated context. + * @indir_size: On entry, the array size of the user buffer for the + * indirection table, which may be zero, or (for %ETHTOOL_SRSSH), + * %ETH_RXFH_INDIR_NO_CHANGE. On return from %ETHTOOL_GRSSH, + * the array size of the hardware indirection table. + * @key_size: On entry, the array size of the user buffer for the hash key, + * which may be zero. On return from %ETHTOOL_GRSSH, the size of the + * hardware hash key. + * @hfunc: Defines the current RSS hash function used by HW (or to be set to). + * Valid values are one of the %ETH_RSS_HASH_*. + * @rsvd: Reserved for future extensions. + * @rss_config: RX ring/queue index for each hash value i.e., indirection table + * of @indir_size __u32 elements, followed by hash key of @key_size + * bytes. + * + * For %ETHTOOL_GRSSH, a @indir_size and key_size of zero means that only the + * size should be returned. For %ETHTOOL_SRSSH, an @indir_size of + * %ETH_RXFH_INDIR_NO_CHANGE means that indir table setting is not requested + * and a @indir_size of zero means the indir table should be reset to default + * values (if @rss_context == 0) or that the RSS context should be deleted. + * An hfunc of zero means that hash function setting is not requested. + */ +struct ethtool_rxfh { + __u32 cmd; + __u32 rss_context; + __u32 indir_size; + __u32 key_size; + __u8 hfunc; + __u8 rsvd8[3]; + __u32 rsvd32; + __u32 rss_config[0]; +}; +#define ETH_RXFH_CONTEXT_ALLOC 0xffffffff +#define ETH_RXFH_INDIR_NO_CHANGE 0xffffffff + +/** + * struct ethtool_rx_ntuple_flow_spec - specification for RX flow filter + * @flow_type: Type of match to perform, e.g. %TCP_V4_FLOW + * @h_u: Flow field values to match (dependent on @flow_type) + * @m_u: Masks for flow field value bits to be ignored + * @vlan_tag: VLAN tag to match + * @vlan_tag_mask: Mask for VLAN tag bits to be ignored + * @data: Driver-dependent data to match + * @data_mask: Mask for driver-dependent data bits to be ignored + * @action: RX ring/queue index to deliver to (non-negative) or other action + * (negative, e.g. %ETHTOOL_RXNTUPLE_ACTION_DROP) + * + * For flow types %TCP_V4_FLOW, %UDP_V4_FLOW and %SCTP_V4_FLOW, where + * a field value and mask are both zero this is treated as if all mask + * bits are set i.e. the field is ignored. + */ +struct ethtool_rx_ntuple_flow_spec { + __u32 flow_type; + union { + struct ethtool_tcpip4_spec tcp_ip4_spec; + struct ethtool_tcpip4_spec udp_ip4_spec; + struct ethtool_tcpip4_spec sctp_ip4_spec; + struct ethtool_ah_espip4_spec ah_ip4_spec; + struct ethtool_ah_espip4_spec esp_ip4_spec; + struct ethtool_usrip4_spec usr_ip4_spec; + struct ethhdr ether_spec; + __u8 hdata[72]; + } h_u, m_u; + + __u16 vlan_tag; + __u16 vlan_tag_mask; + __u64 data; + __u64 data_mask; + + __s32 action; +#define ETHTOOL_RXNTUPLE_ACTION_DROP (-1) /* drop packet */ +#define ETHTOOL_RXNTUPLE_ACTION_CLEAR (-2) /* clear filter */ +}; + +/** + * struct ethtool_rx_ntuple - command to set or clear RX flow filter + * @cmd: Command number - %ETHTOOL_SRXNTUPLE + * @fs: Flow filter specification + */ +struct ethtool_rx_ntuple { + __u32 cmd; + struct ethtool_rx_ntuple_flow_spec fs; +}; + +#define ETHTOOL_FLASH_MAX_FILENAME 128 +enum ethtool_flash_op_type { + ETHTOOL_FLASH_ALL_REGIONS = 0, +}; + +/* for passing firmware flashing related parameters */ +struct ethtool_flash { + __u32 cmd; + __u32 region; + char data[ETHTOOL_FLASH_MAX_FILENAME]; +}; + +/** + * struct ethtool_dump - used for retrieving, setting device dump + * @cmd: Command number - %ETHTOOL_GET_DUMP_FLAG, %ETHTOOL_GET_DUMP_DATA, or + * %ETHTOOL_SET_DUMP + * @version: FW version of the dump, filled in by driver + * @flag: driver dependent flag for dump setting, filled in by driver during + * get and filled in by ethtool for set operation. + * flag must be initialized by macro ETH_FW_DUMP_DISABLE value when + * firmware dump is disabled. + * @len: length of dump data, used as the length of the user buffer on entry to + * %ETHTOOL_GET_DUMP_DATA and this is returned as dump length by driver + * for %ETHTOOL_GET_DUMP_FLAG command + * @data: data collected for get dump data operation + */ +struct ethtool_dump { + __u32 cmd; + __u32 version; + __u32 flag; + __u32 len; + __u8 data[0]; +}; + +#define ETH_FW_DUMP_DISABLE 0 + +/* for returning and changing feature sets */ + +/** + * struct ethtool_get_features_block - block with state of 32 features + * @available: mask of changeable features + * @requested: mask of features requested to be enabled if possible + * @active: mask of currently enabled features + * @never_changed: mask of features not changeable for any device + */ +struct ethtool_get_features_block { + __u32 available; + __u32 requested; + __u32 active; + __u32 never_changed; +}; + +/** + * struct ethtool_gfeatures - command to get state of device's features + * @cmd: command number = %ETHTOOL_GFEATURES + * @size: On entry, the number of elements in the features[] array; + * on return, the number of elements in features[] needed to hold + * all features + * @features: state of features + */ +struct ethtool_gfeatures { + __u32 cmd; + __u32 size; + struct ethtool_get_features_block features[0]; +}; + +/** + * struct ethtool_set_features_block - block with request for 32 features + * @valid: mask of features to be changed + * @requested: values of features to be changed + */ +struct ethtool_set_features_block { + __u32 valid; + __u32 requested; +}; + +/** + * struct ethtool_sfeatures - command to request change in device's features + * @cmd: command number = %ETHTOOL_SFEATURES + * @size: array size of the features[] array + * @features: feature change masks + */ +struct ethtool_sfeatures { + __u32 cmd; + __u32 size; + struct ethtool_set_features_block features[0]; +}; + +/** + * struct ethtool_ts_info - holds a device's timestamping and PHC association + * @cmd: command number = %ETHTOOL_GET_TS_INFO + * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags + * @phc_index: device index of the associated PHC, or -1 if there is none + * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values + * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values + * + * The bits in the 'tx_types' and 'rx_filters' fields correspond to + * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values, + * respectively. For example, if the device supports HWTSTAMP_TX_ON, + * then (1 << HWTSTAMP_TX_ON) in 'tx_types' will be set. + * + * Drivers should only report the filters they actually support without + * upscaling in the SIOCSHWTSTAMP ioctl. If the SIOCSHWSTAMP request for + * HWTSTAMP_FILTER_V1_SYNC is supported by HWTSTAMP_FILTER_V1_EVENT, then the + * driver should only report HWTSTAMP_FILTER_V1_EVENT in this op. + */ +struct ethtool_ts_info { + __u32 cmd; + __u32 so_timestamping; + __s32 phc_index; + __u32 tx_types; + __u32 tx_reserved[3]; + __u32 rx_filters; + __u32 rx_reserved[3]; +}; + +/* + * %ETHTOOL_SFEATURES changes features present in features[].valid to the + * values of corresponding bits in features[].requested. Bits in .requested + * not set in .valid or not changeable are ignored. + * + * Returns %EINVAL when .valid contains undefined or never-changeable bits + * or size is not equal to required number of features words (32-bit blocks). + * Returns >= 0 if request was completed; bits set in the value mean: + * %ETHTOOL_F_UNSUPPORTED - there were bits set in .valid that are not + * changeable (not present in %ETHTOOL_GFEATURES' features[].available) + * those bits were ignored. + * %ETHTOOL_F_WISH - some or all changes requested were recorded but the + * resulting state of bits masked by .valid is not equal to .requested. + * Probably there are other device-specific constraints on some features + * in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered + * here as though ignored bits were cleared. + * %ETHTOOL_F_COMPAT - some or all changes requested were made by calling + * compatibility functions. Requested offload state cannot be properly + * managed by kernel. + * + * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of + * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands + * for ETH_SS_FEATURES string set. First entry in the table corresponds to least + * significant bit in features[0] fields. Empty strings mark undefined features. + */ +enum ethtool_sfeatures_retval_bits { + ETHTOOL_F_UNSUPPORTED__BIT, + ETHTOOL_F_WISH__BIT, + ETHTOOL_F_COMPAT__BIT, +}; + +#define ETHTOOL_F_UNSUPPORTED (1 << ETHTOOL_F_UNSUPPORTED__BIT) +#define ETHTOOL_F_WISH (1 << ETHTOOL_F_WISH__BIT) +#define ETHTOOL_F_COMPAT (1 << ETHTOOL_F_COMPAT__BIT) + +#define MAX_NUM_QUEUE 4096 + +/** + * struct ethtool_per_queue_op - apply sub command to the queues in mask. + * @cmd: ETHTOOL_PERQUEUE + * @sub_command: the sub command which apply to each queues + * @queue_mask: Bitmap of the queues which sub command apply to + * @data: A complete command structure following for each of the queues addressed + */ +struct ethtool_per_queue_op { + __u32 cmd; + __u32 sub_command; + __u32 queue_mask[__KERNEL_DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; + char data[]; +}; + +/** + * struct ethtool_fecparam - Ethernet forward error correction(fec) parameters + * @cmd: Command number = %ETHTOOL_GFECPARAM or %ETHTOOL_SFECPARAM + * @active_fec: FEC mode which is active on porte + * @fec: Bitmask of supported/configured FEC modes + * @rsvd: Reserved for future extensions. i.e FEC bypass feature. + * + * Drivers should reject a non-zero setting of @autoneg when + * autoneogotiation is disabled (or not supported) for the link. + * + */ +struct ethtool_fecparam { + __u32 cmd; + /* bitmask of FEC modes */ + __u32 active_fec; + __u32 fec; + __u32 reserved; +}; + +/** + * enum ethtool_fec_config_bits - flags definition of ethtool_fec_configuration + * @ETHTOOL_FEC_NONE: FEC mode configuration is not supported + * @ETHTOOL_FEC_AUTO: Default/Best FEC mode provided by driver + * @ETHTOOL_FEC_OFF: No FEC Mode + * @ETHTOOL_FEC_RS: Reed-Solomon Forward Error Detection mode + * @ETHTOOL_FEC_BASER: Base-R/Reed-Solomon Forward Error Detection mode + */ +enum ethtool_fec_config_bits { + ETHTOOL_FEC_NONE_BIT, + ETHTOOL_FEC_AUTO_BIT, + ETHTOOL_FEC_OFF_BIT, + ETHTOOL_FEC_RS_BIT, + ETHTOOL_FEC_BASER_BIT, +}; + +#define ETHTOOL_FEC_NONE (1 << ETHTOOL_FEC_NONE_BIT) +#define ETHTOOL_FEC_AUTO (1 << ETHTOOL_FEC_AUTO_BIT) +#define ETHTOOL_FEC_OFF (1 << ETHTOOL_FEC_OFF_BIT) +#define ETHTOOL_FEC_RS (1 << ETHTOOL_FEC_RS_BIT) +#define ETHTOOL_FEC_BASER (1 << ETHTOOL_FEC_BASER_BIT) + +/* CMDs currently supported */ +#define ETHTOOL_GSET 0x00000001 /* DEPRECATED, Get settings. + * Please use ETHTOOL_GLINKSETTINGS + */ +#define ETHTOOL_SSET 0x00000002 /* DEPRECATED, Set settings. + * Please use ETHTOOL_SLINKSETTINGS + */ +#define ETHTOOL_GDRVINFO 0x00000003 /* Get driver info. */ +#define ETHTOOL_GREGS 0x00000004 /* Get NIC registers. */ +#define ETHTOOL_GWOL 0x00000005 /* Get wake-on-lan options. */ +#define ETHTOOL_SWOL 0x00000006 /* Set wake-on-lan options. */ +#define ETHTOOL_GMSGLVL 0x00000007 /* Get driver message level */ +#define ETHTOOL_SMSGLVL 0x00000008 /* Set driver msg level. */ +#define ETHTOOL_NWAY_RST 0x00000009 /* Restart autonegotiation. */ +/* Get link status for host, i.e. whether the interface *and* the + * physical port (if there is one) are up (ethtool_value). */ +#define ETHTOOL_GLINK 0x0000000a +#define ETHTOOL_GEEPROM 0x0000000b /* Get EEPROM data */ +#define ETHTOOL_SEEPROM 0x0000000c /* Set EEPROM data. */ +#define ETHTOOL_GCOALESCE 0x0000000e /* Get coalesce config */ +#define ETHTOOL_SCOALESCE 0x0000000f /* Set coalesce config. */ +#define ETHTOOL_GRINGPARAM 0x00000010 /* Get ring parameters */ +#define ETHTOOL_SRINGPARAM 0x00000011 /* Set ring parameters. */ +#define ETHTOOL_GPAUSEPARAM 0x00000012 /* Get pause parameters */ +#define ETHTOOL_SPAUSEPARAM 0x00000013 /* Set pause parameters. */ +#define ETHTOOL_GRXCSUM 0x00000014 /* Get RX hw csum enable (ethtool_value) */ +#define ETHTOOL_SRXCSUM 0x00000015 /* Set RX hw csum enable (ethtool_value) */ +#define ETHTOOL_GTXCSUM 0x00000016 /* Get TX hw csum enable (ethtool_value) */ +#define ETHTOOL_STXCSUM 0x00000017 /* Set TX hw csum enable (ethtool_value) */ +#define ETHTOOL_GSG 0x00000018 /* Get scatter-gather enable + * (ethtool_value) */ +#define ETHTOOL_SSG 0x00000019 /* Set scatter-gather enable + * (ethtool_value). */ +#define ETHTOOL_TEST 0x0000001a /* execute NIC self-test. */ +#define ETHTOOL_GSTRINGS 0x0000001b /* get specified string set */ +#define ETHTOOL_PHYS_ID 0x0000001c /* identify the NIC */ +#define ETHTOOL_GSTATS 0x0000001d /* get NIC-specific statistics */ +#define ETHTOOL_GTSO 0x0000001e /* Get TSO enable (ethtool_value) */ +#define ETHTOOL_STSO 0x0000001f /* Set TSO enable (ethtool_value) */ +#define ETHTOOL_GPERMADDR 0x00000020 /* Get permanent hardware address */ +#define ETHTOOL_GUFO 0x00000021 /* Get UFO enable (ethtool_value) */ +#define ETHTOOL_SUFO 0x00000022 /* Set UFO enable (ethtool_value) */ +#define ETHTOOL_GGSO 0x00000023 /* Get GSO enable (ethtool_value) */ +#define ETHTOOL_SGSO 0x00000024 /* Set GSO enable (ethtool_value) */ +#define ETHTOOL_GFLAGS 0x00000025 /* Get flags bitmap(ethtool_value) */ +#define ETHTOOL_SFLAGS 0x00000026 /* Set flags bitmap(ethtool_value) */ +#define ETHTOOL_GPFLAGS 0x00000027 /* Get driver-private flags bitmap */ +#define ETHTOOL_SPFLAGS 0x00000028 /* Set driver-private flags bitmap */ + +#define ETHTOOL_GRXFH 0x00000029 /* Get RX flow hash configuration */ +#define ETHTOOL_SRXFH 0x0000002a /* Set RX flow hash configuration */ +#define ETHTOOL_GGRO 0x0000002b /* Get GRO enable (ethtool_value) */ +#define ETHTOOL_SGRO 0x0000002c /* Set GRO enable (ethtool_value) */ +#define ETHTOOL_GRXRINGS 0x0000002d /* Get RX rings available for LB */ +#define ETHTOOL_GRXCLSRLCNT 0x0000002e /* Get RX class rule count */ +#define ETHTOOL_GRXCLSRULE 0x0000002f /* Get RX classification rule */ +#define ETHTOOL_GRXCLSRLALL 0x00000030 /* Get all RX classification rule */ +#define ETHTOOL_SRXCLSRLDEL 0x00000031 /* Delete RX classification rule */ +#define ETHTOOL_SRXCLSRLINS 0x00000032 /* Insert RX classification rule */ +#define ETHTOOL_FLASHDEV 0x00000033 /* Flash firmware to device */ +#define ETHTOOL_RESET 0x00000034 /* Reset hardware */ +#define ETHTOOL_SRXNTUPLE 0x00000035 /* Add an n-tuple filter to device */ +#define ETHTOOL_GRXNTUPLE 0x00000036 /* deprecated */ +#define ETHTOOL_GSSET_INFO 0x00000037 /* Get string set info */ +#define ETHTOOL_GRXFHINDIR 0x00000038 /* Get RX flow hash indir'n table */ +#define ETHTOOL_SRXFHINDIR 0x00000039 /* Set RX flow hash indir'n table */ + +#define ETHTOOL_GFEATURES 0x0000003a /* Get device offload settings */ +#define ETHTOOL_SFEATURES 0x0000003b /* Change device offload settings */ +#define ETHTOOL_GCHANNELS 0x0000003c /* Get no of channels */ +#define ETHTOOL_SCHANNELS 0x0000003d /* Set no of channels */ +#define ETHTOOL_SET_DUMP 0x0000003e /* Set dump settings */ +#define ETHTOOL_GET_DUMP_FLAG 0x0000003f /* Get dump settings */ +#define ETHTOOL_GET_DUMP_DATA 0x00000040 /* Get dump data */ +#define ETHTOOL_GET_TS_INFO 0x00000041 /* Get time stamping and PHC info */ +#define ETHTOOL_GMODULEINFO 0x00000042 /* Get plug-in module information */ +#define ETHTOOL_GMODULEEEPROM 0x00000043 /* Get plug-in module eeprom */ +#define ETHTOOL_GEEE 0x00000044 /* Get EEE settings */ +#define ETHTOOL_SEEE 0x00000045 /* Set EEE settings */ + +#define ETHTOOL_GRSSH 0x00000046 /* Get RX flow hash configuration */ +#define ETHTOOL_SRSSH 0x00000047 /* Set RX flow hash configuration */ +#define ETHTOOL_GTUNABLE 0x00000048 /* Get tunable configuration */ +#define ETHTOOL_STUNABLE 0x00000049 /* Set tunable configuration */ +#define ETHTOOL_GPHYSTATS 0x0000004a /* get PHY-specific statistics */ + +#define ETHTOOL_PERQUEUE 0x0000004b /* Set per queue options */ + +#define ETHTOOL_GLINKSETTINGS 0x0000004c /* Get ethtool_link_settings */ +#define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */ +#define ETHTOOL_PHY_GTUNABLE 0x0000004e /* Get PHY tunable configuration */ +#define ETHTOOL_PHY_STUNABLE 0x0000004f /* Set PHY tunable configuration */ +#define ETHTOOL_GFECPARAM 0x00000050 /* Get FEC settings */ +#define ETHTOOL_SFECPARAM 0x00000051 /* Set FEC settings */ + +/* compatibility with older code */ +#define SPARC_ETH_GSET ETHTOOL_GSET +#define SPARC_ETH_SSET ETHTOOL_SSET + +/* Link mode bit indices */ +enum ethtool_link_mode_bit_indices { + ETHTOOL_LINK_MODE_10baseT_Half_BIT = 0, + ETHTOOL_LINK_MODE_10baseT_Full_BIT = 1, + ETHTOOL_LINK_MODE_100baseT_Half_BIT = 2, + ETHTOOL_LINK_MODE_100baseT_Full_BIT = 3, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT = 4, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT = 5, + ETHTOOL_LINK_MODE_Autoneg_BIT = 6, + ETHTOOL_LINK_MODE_TP_BIT = 7, + ETHTOOL_LINK_MODE_AUI_BIT = 8, + ETHTOOL_LINK_MODE_MII_BIT = 9, + ETHTOOL_LINK_MODE_FIBRE_BIT = 10, + ETHTOOL_LINK_MODE_BNC_BIT = 11, + ETHTOOL_LINK_MODE_10000baseT_Full_BIT = 12, + ETHTOOL_LINK_MODE_Pause_BIT = 13, + ETHTOOL_LINK_MODE_Asym_Pause_BIT = 14, + ETHTOOL_LINK_MODE_2500baseX_Full_BIT = 15, + ETHTOOL_LINK_MODE_Backplane_BIT = 16, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT = 17, + ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT = 18, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT = 19, + ETHTOOL_LINK_MODE_10000baseR_FEC_BIT = 20, + ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT = 21, + ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT = 22, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT = 23, + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT = 24, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT = 25, + ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT = 26, + ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT = 27, + ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT = 28, + ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT = 29, + ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT = 30, + ETHTOOL_LINK_MODE_25000baseCR_Full_BIT = 31, + ETHTOOL_LINK_MODE_25000baseKR_Full_BIT = 32, + ETHTOOL_LINK_MODE_25000baseSR_Full_BIT = 33, + ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT = 34, + ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT = 35, + ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT = 36, + ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT = 37, + ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT = 38, + ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT = 39, + ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT = 40, + ETHTOOL_LINK_MODE_1000baseX_Full_BIT = 41, + ETHTOOL_LINK_MODE_10000baseCR_Full_BIT = 42, + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT = 43, + ETHTOOL_LINK_MODE_10000baseLR_Full_BIT = 44, + ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT = 45, + ETHTOOL_LINK_MODE_10000baseER_Full_BIT = 46, + ETHTOOL_LINK_MODE_2500baseT_Full_BIT = 47, + ETHTOOL_LINK_MODE_5000baseT_Full_BIT = 48, + + ETHTOOL_LINK_MODE_FEC_NONE_BIT = 49, + ETHTOOL_LINK_MODE_FEC_RS_BIT = 50, + ETHTOOL_LINK_MODE_FEC_BASER_BIT = 51, + + /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit + * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* + * macro for bits > 31. The only way to use indices > 31 is to + * use the new ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. + */ + + __ETHTOOL_LINK_MODE_LAST + = ETHTOOL_LINK_MODE_FEC_BASER_BIT, +}; + +#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ + (1UL << (ETHTOOL_LINK_MODE_ ## base_name ## _BIT)) + +/* DEPRECATED macros. Please migrate to + * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT + * define any new SUPPORTED_* macro for bits > 31. + */ +#define SUPPORTED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) +#define SUPPORTED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) +#define SUPPORTED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) +#define SUPPORTED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) +#define SUPPORTED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) +#define SUPPORTED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) +#define SUPPORTED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) +#define SUPPORTED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) +#define SUPPORTED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) +#define SUPPORTED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) +#define SUPPORTED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) +#define SUPPORTED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) +#define SUPPORTED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) +#define SUPPORTED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) +#define SUPPORTED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) +#define SUPPORTED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) +#define SUPPORTED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) +#define SUPPORTED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) +#define SUPPORTED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) +#define SUPPORTED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) +#define SUPPORTED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) +#define SUPPORTED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) +#define SUPPORTED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) +#define SUPPORTED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) +#define SUPPORTED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) +#define SUPPORTED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) +#define SUPPORTED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) +#define SUPPORTED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) +#define SUPPORTED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) +#define SUPPORTED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) +#define SUPPORTED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) +/* Please do not define any new SUPPORTED_* macro for bits > 31, see + * notice above. + */ + +/* + * DEPRECATED macros. Please migrate to + * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT + * define any new ADERTISE_* macro for bits > 31. + */ +#define ADVERTISED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) +#define ADVERTISED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) +#define ADVERTISED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) +#define ADVERTISED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) +#define ADVERTISED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) +#define ADVERTISED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) +#define ADVERTISED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) +#define ADVERTISED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) +#define ADVERTISED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) +#define ADVERTISED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) +#define ADVERTISED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) +#define ADVERTISED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) +#define ADVERTISED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) +#define ADVERTISED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) +#define ADVERTISED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) +#define ADVERTISED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) +#define ADVERTISED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) +#define ADVERTISED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) +#define ADVERTISED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) +#define ADVERTISED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) +#define ADVERTISED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) +#define ADVERTISED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) +#define ADVERTISED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) +#define ADVERTISED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) +#define ADVERTISED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) +#define ADVERTISED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) +#define ADVERTISED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) +#define ADVERTISED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) +#define ADVERTISED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) +#define ADVERTISED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) +#define ADVERTISED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) +/* Please do not define any new ADVERTISED_* macro for bits > 31, see + * notice above. + */ + +/* The following are all involved in forcing a particular link + * mode for the device for setting things. When getting the + * devices settings, these indicate the current mode and whether + * it was forced up into this mode or autonegotiated. + */ + +/* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal. + * Update drivers/net/phy/phy.c:phy_speed_to_str() and + * drivers/net/bonding/bond_3ad.c:__get_link_speed() when adding new values. + */ +#define SPEED_10 10 +#define SPEED_100 100 +#define SPEED_1000 1000 +#define SPEED_2500 2500 +#define SPEED_5000 5000 +#define SPEED_10000 10000 +#define SPEED_14000 14000 +#define SPEED_20000 20000 +#define SPEED_25000 25000 +#define SPEED_40000 40000 +#define SPEED_50000 50000 +#define SPEED_56000 56000 +#define SPEED_100000 100000 + +#define SPEED_UNKNOWN ((__u32) -1) + +static inline int ethtool_validate_speed(__u32 speed) +{ + return speed <= INT_MAX || speed == SPEED_UNKNOWN; +} + +/* Duplex, half or full. */ +#define DUPLEX_HALF 0x00 +#define DUPLEX_FULL 0x01 +#define DUPLEX_UNKNOWN 0xff + +static inline int ethtool_validate_duplex(__u8 duplex) +{ + switch (duplex) { + case DUPLEX_HALF: + case DUPLEX_FULL: + case DUPLEX_UNKNOWN: + return 1; + } + + return 0; +} + +/* Which connector port. */ +#define PORT_TP 0x00 +#define PORT_AUI 0x01 +#define PORT_MII 0x02 +#define PORT_FIBRE 0x03 +#define PORT_BNC 0x04 +#define PORT_DA 0x05 +#define PORT_NONE 0xef +#define PORT_OTHER 0xff + +/* Which transceiver to use. */ +#define XCVR_INTERNAL 0x00 /* PHY and MAC are in the same package */ +#define XCVR_EXTERNAL 0x01 /* PHY and MAC are in different packages */ +#define XCVR_DUMMY1 0x02 +#define XCVR_DUMMY2 0x03 +#define XCVR_DUMMY3 0x04 + +/* Enable or disable autonegotiation. */ +#define AUTONEG_DISABLE 0x00 +#define AUTONEG_ENABLE 0x01 + +/* MDI or MDI-X status/control - if MDI/MDI_X/AUTO is set then + * the driver is required to renegotiate link + */ +#define ETH_TP_MDI_INVALID 0x00 /* status: unknown; control: unsupported */ +#define ETH_TP_MDI 0x01 /* status: MDI; control: force MDI */ +#define ETH_TP_MDI_X 0x02 /* status: MDI-X; control: force MDI-X */ +#define ETH_TP_MDI_AUTO 0x03 /* control: auto-select */ + +/* Wake-On-Lan options. */ +#define WAKE_PHY (1 << 0) +#define WAKE_UCAST (1 << 1) +#define WAKE_MCAST (1 << 2) +#define WAKE_BCAST (1 << 3) +#define WAKE_ARP (1 << 4) +#define WAKE_MAGIC (1 << 5) +#define WAKE_MAGICSECURE (1 << 6) /* only meaningful if WAKE_MAGIC */ +#define WAKE_FILTER (1 << 7) + +/* L2-L4 network traffic flow types */ +#define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ +#define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */ +#define SCTP_V4_FLOW 0x03 /* hash or spec (sctp_ip4_spec) */ +#define AH_ESP_V4_FLOW 0x04 /* hash only */ +#define TCP_V6_FLOW 0x05 /* hash or spec (tcp_ip6_spec; nfc only) */ +#define UDP_V6_FLOW 0x06 /* hash or spec (udp_ip6_spec; nfc only) */ +#define SCTP_V6_FLOW 0x07 /* hash or spec (sctp_ip6_spec; nfc only) */ +#define AH_ESP_V6_FLOW 0x08 /* hash only */ +#define AH_V4_FLOW 0x09 /* hash or spec (ah_ip4_spec) */ +#define ESP_V4_FLOW 0x0a /* hash or spec (esp_ip4_spec) */ +#define AH_V6_FLOW 0x0b /* hash or spec (ah_ip6_spec; nfc only) */ +#define ESP_V6_FLOW 0x0c /* hash or spec (esp_ip6_spec; nfc only) */ +#define IPV4_USER_FLOW 0x0d /* spec only (usr_ip4_spec) */ +#define IP_USER_FLOW IPV4_USER_FLOW +#define IPV6_USER_FLOW 0x0e /* spec only (usr_ip6_spec; nfc only) */ +#define IPV4_FLOW 0x10 /* hash only */ +#define IPV6_FLOW 0x11 /* hash only */ +#define ETHER_FLOW 0x12 /* spec only (ether_spec) */ +/* Flag to enable additional fields in struct ethtool_rx_flow_spec */ +#define FLOW_EXT 0x80000000 +#define FLOW_MAC_EXT 0x40000000 +/* Flag to enable RSS spreading of traffic matching rule (nfc only) */ +#define FLOW_RSS 0x20000000 + +/* L3-L4 network traffic flow hash options */ +#define RXH_L2DA (1 << 1) +#define RXH_VLAN (1 << 2) +#define RXH_L3_PROTO (1 << 3) +#define RXH_IP_SRC (1 << 4) +#define RXH_IP_DST (1 << 5) +#define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */ +#define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */ +#define RXH_DISCARD (1 << 31) + +#define RX_CLS_FLOW_DISC 0xffffffffffffffffULL +#define RX_CLS_FLOW_WAKE 0xfffffffffffffffeULL + +/* Special RX classification rule insert location values */ +#define RX_CLS_LOC_SPECIAL 0x80000000 /* flag */ +#define RX_CLS_LOC_ANY 0xffffffff +#define RX_CLS_LOC_FIRST 0xfffffffe +#define RX_CLS_LOC_LAST 0xfffffffd + +/* EEPROM Standards for plug in modules */ +#define ETH_MODULE_SFF_8079 0x1 +#define ETH_MODULE_SFF_8079_LEN 256 +#define ETH_MODULE_SFF_8472 0x2 +#define ETH_MODULE_SFF_8472_LEN 512 +#define ETH_MODULE_SFF_8636 0x3 +#define ETH_MODULE_SFF_8636_LEN 256 +#define ETH_MODULE_SFF_8436 0x4 +#define ETH_MODULE_SFF_8436_LEN 256 + +/* Reset flags */ +/* The reset() operation must clear the flags for the components which + * were actually reset. On successful return, the flags indicate the + * components which were not reset, either because they do not exist + * in the hardware or because they cannot be reset independently. The + * driver must never reset any components that were not requested. + */ +enum ethtool_reset_flags { + /* These flags represent components dedicated to the interface + * the command is addressed to. Shift any flag left by + * ETH_RESET_SHARED_SHIFT to reset a shared component of the + * same type. + */ + ETH_RESET_MGMT = 1 << 0, /* Management processor */ + ETH_RESET_IRQ = 1 << 1, /* Interrupt requester */ + ETH_RESET_DMA = 1 << 2, /* DMA engine */ + ETH_RESET_FILTER = 1 << 3, /* Filtering/flow direction */ + ETH_RESET_OFFLOAD = 1 << 4, /* Protocol offload */ + ETH_RESET_MAC = 1 << 5, /* Media access controller */ + ETH_RESET_PHY = 1 << 6, /* Transceiver/PHY */ + ETH_RESET_RAM = 1 << 7, /* RAM shared between + * multiple components */ + ETH_RESET_AP = 1 << 8, /* Application processor */ + + ETH_RESET_DEDICATED = 0x0000ffff, /* All components dedicated to + * this interface */ + ETH_RESET_ALL = 0xffffffff, /* All components used by this + * interface, even if shared */ +}; +#define ETH_RESET_SHARED_SHIFT 16 + + +/** + * struct ethtool_link_settings - link control and status + * + * IMPORTANT, Backward compatibility notice: When implementing new + * user-space tools, please first try %ETHTOOL_GLINKSETTINGS, and + * if it succeeds use %ETHTOOL_SLINKSETTINGS to change link + * settings; do not use %ETHTOOL_SSET if %ETHTOOL_GLINKSETTINGS + * succeeded: stick to %ETHTOOL_GLINKSETTINGS/%SLINKSETTINGS in + * that case. Conversely, if %ETHTOOL_GLINKSETTINGS fails, use + * %ETHTOOL_GSET to query and %ETHTOOL_SSET to change link + * settings; do not use %ETHTOOL_SLINKSETTINGS if + * %ETHTOOL_GLINKSETTINGS failed: stick to + * %ETHTOOL_GSET/%ETHTOOL_SSET in that case. + * + * @cmd: Command number = %ETHTOOL_GLINKSETTINGS or %ETHTOOL_SLINKSETTINGS + * @speed: Link speed (Mbps) + * @duplex: Duplex mode; one of %DUPLEX_* + * @port: Physical connector type; one of %PORT_* + * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not + * applicable. For clause 45 PHYs this is the PRTAD. + * @autoneg: Enable/disable autonegotiation and auto-detection; + * either %AUTONEG_DISABLE or %AUTONEG_ENABLE + * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO + * protocols supported by the interface; 0 if unknown. + * Read-only. + * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of + * %ETH_TP_MDI_*. If the status is unknown or not applicable, the + * value will be %ETH_TP_MDI_INVALID. Read-only. + * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of + * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads + * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected. + * When written successfully, the link should be renegotiated if + * necessary. + * @link_mode_masks_nwords: Number of 32-bit words for each of the + * supported, advertising, lp_advertising link mode bitmaps. For + * %ETHTOOL_GLINKSETTINGS: on entry, number of words passed by user + * (>= 0); on return, if handshake in progress, negative if + * request size unsupported by kernel: absolute value indicates + * kernel expected size and all the other fields but cmd + * are 0; otherwise (handshake completed), strictly positive + * to indicate size used by kernel and cmd field stays + * %ETHTOOL_GLINKSETTINGS, all other fields populated by driver. For + * %ETHTOOL_SLINKSETTINGS: must be valid on entry, ie. a positive + * value returned previously by %ETHTOOL_GLINKSETTINGS, otherwise + * refused. For drivers: ignore this field (use kernel's + * __ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will + * be overwritten by kernel. + * @supported: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features for which the interface + * supports autonegotiation or auto-detection. Read-only. + * @advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features that are advertised through + * autonegotiation or enabled for auto-detection. + * @lp_advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, and other + * link features that the link partner advertised through + * autonegotiation; 0 if unknown or not applicable. Read-only. + * @transceiver: Used to distinguish different possible PHY types, + * reported consistently by PHYLIB. Read-only. + * + * If autonegotiation is disabled, the speed and @duplex represent the + * fixed link mode and are writable if the driver supports multiple + * link modes. If it is enabled then they are read-only; if the link + * is up they represent the negotiated link mode; if the link is down, + * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and + * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode. + * + * Some hardware interfaces may have multiple PHYs and/or physical + * connectors fitted or do not allow the driver to detect which are + * fitted. For these interfaces @port and/or @phy_address may be + * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE. + * Otherwise, attempts to write different values may be ignored or + * rejected. + * + * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt + * are not available in %ethtool_link_settings. These fields will be + * always set to zero in %ETHTOOL_GSET reply and %ETHTOOL_SSET will + * fail if any of them is set to non-zero value. + * + * Users should assume that all fields not marked read-only are + * writable and subject to validation by the driver. They should use + * %ETHTOOL_GLINKSETTINGS to get the current values before making specific + * changes and then applying them with %ETHTOOL_SLINKSETTINGS. + * + * Drivers that implement %get_link_ksettings and/or + * %set_link_ksettings should ignore the @cmd + * and @link_mode_masks_nwords fields (any change to them overwritten + * by kernel), and rely only on kernel's internal + * %__ETHTOOL_LINK_MODE_MASK_NBITS and + * %ethtool_link_mode_mask_t. Drivers that implement + * %set_link_ksettings() should validate all fields other than @cmd + * and @link_mode_masks_nwords that are not described as read-only or + * deprecated, and must ignore all fields described as read-only. + */ +struct ethtool_link_settings { + __u32 cmd; + __u32 speed; + __u8 duplex; + __u8 port; + __u8 phy_address; + __u8 autoneg; + __u8 mdio_support; + __u8 eth_tp_mdix; + __u8 eth_tp_mdix_ctrl; + __s8 link_mode_masks_nwords; + __u8 transceiver; + __u8 reserved1[3]; + __u32 reserved[7]; + __u32 link_mode_masks[0]; + /* layout of link_mode_masks fields: + * __u32 map_supported[link_mode_masks_nwords]; + * __u32 map_advertising[link_mode_masks_nwords]; + * __u32 map_lp_advertising[link_mode_masks_nwords]; + */ +}; +#endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/src/shared/linux/libbpf.h b/src/shared/linux/libbpf.h deleted file mode 100644 index 391eee5a4e..0000000000 --- a/src/shared/linux/libbpf.h +++ /dev/null @@ -1,207 +0,0 @@ -/* eBPF mini library */ -#ifndef __LIBBPF_H -#define __LIBBPF_H - -#include <linux/bpf.h> - -struct bpf_insn; - -/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ - -#define BPF_ALU64_REG(OP, DST, SRC) \ - ((struct bpf_insn) { \ - .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = 0, \ - .imm = 0 }) - -#define BPF_ALU32_REG(OP, DST, SRC) \ - ((struct bpf_insn) { \ - .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = 0, \ - .imm = 0 }) - -/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ - -#define BPF_ALU64_IMM(OP, DST, IMM) \ - ((struct bpf_insn) { \ - .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ - .dst_reg = DST, \ - .src_reg = 0, \ - .off = 0, \ - .imm = IMM }) - -#define BPF_ALU32_IMM(OP, DST, IMM) \ - ((struct bpf_insn) { \ - .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ - .dst_reg = DST, \ - .src_reg = 0, \ - .off = 0, \ - .imm = IMM }) - -/* Short form of mov, dst_reg = src_reg */ - -#define BPF_MOV64_REG(DST, SRC) \ - ((struct bpf_insn) { \ - .code = BPF_ALU64 | BPF_MOV | BPF_X, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = 0, \ - .imm = 0 }) - -#define BPF_MOV32_REG(DST, SRC) \ - ((struct bpf_insn) { \ - .code = BPF_ALU | BPF_MOV | BPF_X, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = 0, \ - .imm = 0 }) - -/* Short form of mov, dst_reg = imm32 */ - -#define BPF_MOV64_IMM(DST, IMM) \ - ((struct bpf_insn) { \ - .code = BPF_ALU64 | BPF_MOV | BPF_K, \ - .dst_reg = DST, \ - .src_reg = 0, \ - .off = 0, \ - .imm = IMM }) - -#define BPF_MOV32_IMM(DST, IMM) \ - ((struct bpf_insn) { \ - .code = BPF_ALU | BPF_MOV | BPF_K, \ - .dst_reg = DST, \ - .src_reg = 0, \ - .off = 0, \ - .imm = IMM }) - -/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ -#define BPF_LD_IMM64(DST, IMM) \ - BPF_LD_IMM64_RAW(DST, 0, IMM) - -#define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ - ((struct bpf_insn) { \ - .code = BPF_LD | BPF_DW | BPF_IMM, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = 0, \ - .imm = (__u32) (IMM) }), \ - ((struct bpf_insn) { \ - .code = 0, /* zero is reserved opcode */ \ - .dst_reg = 0, \ - .src_reg = 0, \ - .off = 0, \ - .imm = ((__u64) (IMM)) >> 32 }) - -#ifndef BPF_PSEUDO_MAP_FD -# define BPF_PSEUDO_MAP_FD 1 -#endif - -/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ -#define BPF_LD_MAP_FD(DST, MAP_FD) \ - BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) - -/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ - -#define BPF_LD_ABS(SIZE, IMM) \ - ((struct bpf_insn) { \ - .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ - .dst_reg = 0, \ - .src_reg = 0, \ - .off = 0, \ - .imm = IMM }) - -/* Memory load, dst_reg = *(uint *) (src_reg + off16) */ - -#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ - ((struct bpf_insn) { \ - .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = OFF, \ - .imm = 0 }) - -/* Memory store, *(uint *) (dst_reg + off16) = src_reg */ - -#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ - ((struct bpf_insn) { \ - .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = OFF, \ - .imm = 0 }) - -/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ - -#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ - ((struct bpf_insn) { \ - .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = OFF, \ - .imm = 0 }) - -/* Memory store, *(uint *) (dst_reg + off16) = imm32 */ - -#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ - ((struct bpf_insn) { \ - .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ - .dst_reg = DST, \ - .src_reg = 0, \ - .off = OFF, \ - .imm = IMM }) - -/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ - -#define BPF_JMP_REG(OP, DST, SRC, OFF) \ - ((struct bpf_insn) { \ - .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = OFF, \ - .imm = 0 }) - -/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ - -#define BPF_JMP_IMM(OP, DST, IMM, OFF) \ - ((struct bpf_insn) { \ - .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ - .dst_reg = DST, \ - .src_reg = 0, \ - .off = OFF, \ - .imm = IMM }) - -/* Unconditional jumps */ - -#define BPF_JMP_A(OFF) \ - ((struct bpf_insn) { \ - .code = BPF_JMP | BPF_JA, \ - .dst_reg = 0, \ - .src_reg = 0, \ - .off = OFF, \ - .imm = 0 }) - -/* Raw code statement block */ - -#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ - ((struct bpf_insn) { \ - .code = CODE, \ - .dst_reg = DST, \ - .src_reg = SRC, \ - .off = OFF, \ - .imm = IMM }) - -/* Program exit */ - -#define BPF_EXIT_INSN() \ - ((struct bpf_insn) { \ - .code = BPF_JMP | BPF_EXIT, \ - .dst_reg = 0, \ - .src_reg = 0, \ - .off = 0, \ - .imm = 0 }) - -#endif diff --git a/src/shared/linux/netdevice.h b/src/shared/linux/netdevice.h new file mode 100644 index 0000000000..f3770c5b0f --- /dev/null +++ b/src/shared/linux/netdevice.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions for the Interfaces handler. + * + * Version: @(#)dev.h 1.0.10 08/12/93 + * + * Authors: Ross Biro + * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> + * Corey Minyard <wf-rch!minyard@relay.EU.net> + * Donald J. Becker, <becker@cesdis.gsfc.nasa.gov> + * Alan Cox, <alan@lxorguk.ukuu.org.uk> + * Bjorn Ekwall. <bj0rn@blox.se> + * Pekka Riikonen <priikone@poseidon.pspt.fi> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Moved to /usr/include/linux for NET3 + */ +#ifndef _UAPI_LINUX_NETDEVICE_H +#define _UAPI_LINUX_NETDEVICE_H + +#include <linux/if.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_link.h> + + +#define MAX_ADDR_LEN 32 /* Largest hardware address length */ + +/* Initial net device group. All devices belong to group 0 by default. */ +#define INIT_NETDEV_GROUP 0 + + +/* interface name assignment types (sysfs name_assign_type attribute) */ +#define NET_NAME_UNKNOWN 0 /* unknown origin (not exposed to userspace) */ +#define NET_NAME_ENUM 1 /* enumerated by kernel */ +#define NET_NAME_PREDICTABLE 2 /* predictably named by the kernel */ +#define NET_NAME_USER 3 /* provided by user-space */ +#define NET_NAME_RENAMED 4 /* renamed by user-space */ + +/* Media selection options. */ +enum { + IF_PORT_UNKNOWN = 0, + IF_PORT_10BASE2, + IF_PORT_10BASET, + IF_PORT_AUI, + IF_PORT_100BASET, + IF_PORT_100BASETX, + IF_PORT_100BASEFX +}; + +/* hardware address assignment types */ +#define NET_ADDR_PERM 0 /* address is permanent (default) */ +#define NET_ADDR_RANDOM 1 /* address is generated randomly */ +#define NET_ADDR_STOLEN 2 /* address is stolen from other device */ +#define NET_ADDR_SET 3 /* address is set using + * dev_set_mac_address() */ + +#endif /* _UAPI_LINUX_NETDEVICE_H */ |