bpf.h 145.7 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
2 3 4 5 6 7 8 9 10 11
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 */
#ifndef _UAPI__LINUX_BPF_H__
#define _UAPI__LINUX_BPF_H__

#include <linux/types.h>
12
#include <linux/bpf_common.h>
13 14 15 16

/* Extended instruction set based on top of classic BPF */

/* instruction classes */
17
#define BPF_JMP32	0x06	/* jmp mode in word width */
18 19 20
#define BPF_ALU64	0x07	/* alu mode in double word width */

/* ld/ldx fields */
21
#define BPF_DW		0x18	/* double word (64-bit) */
22 23 24 25 26 27 28 29 30 31 32 33 34
#define BPF_XADD	0xc0	/* exclusive add */

/* alu/jmp fields */
#define BPF_MOV		0xb0	/* mov reg to reg */
#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */

/* change endianness of a register */
#define BPF_END		0xd0	/* flags for endianness conversion: */
#define BPF_TO_LE	0x00	/* convert to little-endian */
#define BPF_TO_BE	0x08	/* convert to big-endian */
#define BPF_FROM_LE	BPF_TO_LE
#define BPF_FROM_BE	BPF_TO_BE

35
/* jmp encodings */
36
#define BPF_JNE		0x50	/* jump != */
37 38
#define BPF_JLT		0xa0	/* LT is unsigned, '<' */
#define BPF_JLE		0xb0	/* LE is unsigned, '<=' */
39 40
#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
41 42
#define BPF_JSLT	0xc0	/* SLT is signed, '<' */
#define BPF_JSLE	0xd0	/* SLE is signed, '<=' */
43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72
#define BPF_CALL	0x80	/* function call */
#define BPF_EXIT	0x90	/* function return */

/* Register numbers */
enum {
	BPF_REG_0 = 0,
	BPF_REG_1,
	BPF_REG_2,
	BPF_REG_3,
	BPF_REG_4,
	BPF_REG_5,
	BPF_REG_6,
	BPF_REG_7,
	BPF_REG_8,
	BPF_REG_9,
	BPF_REG_10,
	__MAX_BPF_REG,
};

/* BPF has 10 general purpose 64-bit registers and stack frame. */
#define MAX_BPF_REG	__MAX_BPF_REG

struct bpf_insn {
	__u8	code;		/* opcode */
	__u8	dst_reg:4;	/* dest register */
	__u8	src_reg:4;	/* source register */
	__s16	off;		/* signed offset */
	__s32	imm;		/* signed immediate constant */
};

73 74 75
/* 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 */
76
	__u8	data[];	/* Arbitrary size */
77 78
};

79 80 81 82 83
struct bpf_cgroup_storage_key {
	__u64	cgroup_inode_id;	/* cgroup inode id */
	__u32	attach_type;		/* program attach type */
};

84
/* BPF syscall commands, see bpf(2) man-page for details. */
85 86
enum bpf_cmd {
	BPF_MAP_CREATE,
87 88 89 90
	BPF_MAP_LOOKUP_ELEM,
	BPF_MAP_UPDATE_ELEM,
	BPF_MAP_DELETE_ELEM,
	BPF_MAP_GET_NEXT_KEY,
91
	BPF_PROG_LOAD,
92 93
	BPF_OBJ_PIN,
	BPF_OBJ_GET,
94 95
	BPF_PROG_ATTACH,
	BPF_PROG_DETACH,
96
	BPF_PROG_TEST_RUN,
97 98
	BPF_PROG_GET_NEXT_ID,
	BPF_MAP_GET_NEXT_ID,
99
	BPF_PROG_GET_FD_BY_ID,
M
Martin KaFai Lau 已提交
100
	BPF_MAP_GET_FD_BY_ID,
101
	BPF_OBJ_GET_INFO_BY_FD,
102
	BPF_PROG_QUERY,
103
	BPF_RAW_TRACEPOINT_OPEN,
104
	BPF_BTF_LOAD,
M
Martin KaFai Lau 已提交
105
	BPF_BTF_GET_FD_BY_ID,
106
	BPF_TASK_FD_QUERY,
107
	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
108
	BPF_MAP_FREEZE,
109
	BPF_BTF_GET_NEXT_ID,
110
	BPF_MAP_LOOKUP_BATCH,
111
	BPF_MAP_LOOKUP_AND_DELETE_BATCH,
112 113
	BPF_MAP_UPDATE_BATCH,
	BPF_MAP_DELETE_BATCH,
114
	BPF_LINK_CREATE,
115
	BPF_LINK_UPDATE,
116 117 118 119
};

enum bpf_map_type {
	BPF_MAP_TYPE_UNSPEC,
120
	BPF_MAP_TYPE_HASH,
121
	BPF_MAP_TYPE_ARRAY,
122
	BPF_MAP_TYPE_PROG_ARRAY,
123
	BPF_MAP_TYPE_PERF_EVENT_ARRAY,
124
	BPF_MAP_TYPE_PERCPU_HASH,
125
	BPF_MAP_TYPE_PERCPU_ARRAY,
126
	BPF_MAP_TYPE_STACK_TRACE,
127
	BPF_MAP_TYPE_CGROUP_ARRAY,
M
Martin KaFai Lau 已提交
128
	BPF_MAP_TYPE_LRU_HASH,
129
	BPF_MAP_TYPE_LRU_PERCPU_HASH,
130
	BPF_MAP_TYPE_LPM_TRIE,
131
	BPF_MAP_TYPE_ARRAY_OF_MAPS,
M
Martin KaFai Lau 已提交
132
	BPF_MAP_TYPE_HASH_OF_MAPS,
133
	BPF_MAP_TYPE_DEVMAP,
134
	BPF_MAP_TYPE_SOCKMAP,
135
	BPF_MAP_TYPE_CPUMAP,
136
	BPF_MAP_TYPE_XSKMAP,
137
	BPF_MAP_TYPE_SOCKHASH,
138
	BPF_MAP_TYPE_CGROUP_STORAGE,
139
	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
140
	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
M
Mauricio Vasquez B 已提交
141 142
	BPF_MAP_TYPE_QUEUE,
	BPF_MAP_TYPE_STACK,
143
	BPF_MAP_TYPE_SK_STORAGE,
144
	BPF_MAP_TYPE_DEVMAP_HASH,
145
	BPF_MAP_TYPE_STRUCT_OPS,
146 147
};

148 149 150 151 152 153 154 155
/* 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.
 */
156 157
enum bpf_prog_type {
	BPF_PROG_TYPE_UNSPEC,
158
	BPF_PROG_TYPE_SOCKET_FILTER,
159
	BPF_PROG_TYPE_KPROBE,
160
	BPF_PROG_TYPE_SCHED_CLS,
161
	BPF_PROG_TYPE_SCHED_ACT,
162
	BPF_PROG_TYPE_TRACEPOINT,
163
	BPF_PROG_TYPE_XDP,
164
	BPF_PROG_TYPE_PERF_EVENT,
165
	BPF_PROG_TYPE_CGROUP_SKB,
166
	BPF_PROG_TYPE_CGROUP_SOCK,
167 168 169
	BPF_PROG_TYPE_LWT_IN,
	BPF_PROG_TYPE_LWT_OUT,
	BPF_PROG_TYPE_LWT_XMIT,
L
Lawrence Brakmo 已提交
170
	BPF_PROG_TYPE_SOCK_OPS,
171
	BPF_PROG_TYPE_SK_SKB,
172
	BPF_PROG_TYPE_CGROUP_DEVICE,
173
	BPF_PROG_TYPE_SK_MSG,
174
	BPF_PROG_TYPE_RAW_TRACEPOINT,
A
Andrey Ignatov 已提交
175
	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
176
	BPF_PROG_TYPE_LWT_SEG6LOCAL,
177
	BPF_PROG_TYPE_LIRC_MODE2,
178
	BPF_PROG_TYPE_SK_REUSEPORT,
179
	BPF_PROG_TYPE_FLOW_DISSECTOR,
A
Andrey Ignatov 已提交
180
	BPF_PROG_TYPE_CGROUP_SYSCTL,
181
	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
182
	BPF_PROG_TYPE_CGROUP_SOCKOPT,
183
	BPF_PROG_TYPE_TRACING,
184
	BPF_PROG_TYPE_STRUCT_OPS,
185
	BPF_PROG_TYPE_EXT,
K
KP Singh 已提交
186
	BPF_PROG_TYPE_LSM,
187 188
};

189 190 191
enum bpf_attach_type {
	BPF_CGROUP_INET_INGRESS,
	BPF_CGROUP_INET_EGRESS,
192
	BPF_CGROUP_INET_SOCK_CREATE,
L
Lawrence Brakmo 已提交
193
	BPF_CGROUP_SOCK_OPS,
194 195
	BPF_SK_SKB_STREAM_PARSER,
	BPF_SK_SKB_STREAM_VERDICT,
196
	BPF_CGROUP_DEVICE,
197
	BPF_SK_MSG_VERDICT,
A
Andrey Ignatov 已提交
198 199
	BPF_CGROUP_INET4_BIND,
	BPF_CGROUP_INET6_BIND,
A
Andrey Ignatov 已提交
200 201
	BPF_CGROUP_INET4_CONNECT,
	BPF_CGROUP_INET6_CONNECT,
A
Andrey Ignatov 已提交
202 203
	BPF_CGROUP_INET4_POST_BIND,
	BPF_CGROUP_INET6_POST_BIND,
A
Andrey Ignatov 已提交
204 205
	BPF_CGROUP_UDP4_SENDMSG,
	BPF_CGROUP_UDP6_SENDMSG,
206
	BPF_LIRC_MODE2,
207
	BPF_FLOW_DISSECTOR,
A
Andrey Ignatov 已提交
208
	BPF_CGROUP_SYSCTL,
D
Daniel Borkmann 已提交
209 210
	BPF_CGROUP_UDP4_RECVMSG,
	BPF_CGROUP_UDP6_RECVMSG,
211 212
	BPF_CGROUP_GETSOCKOPT,
	BPF_CGROUP_SETSOCKOPT,
213
	BPF_TRACE_RAW_TP,
A
Alexei Starovoitov 已提交
214 215
	BPF_TRACE_FENTRY,
	BPF_TRACE_FEXIT,
K
KP Singh 已提交
216
	BPF_MODIFY_RETURN,
K
KP Singh 已提交
217
	BPF_LSM_MAC,
218 219 220 221 222
	__MAX_BPF_ATTACH_TYPE
};

#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE

223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245
/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
 *
 * NONE(default): No further bpf programs allowed in the subtree.
 *
 * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
 * the program in this cgroup yields to sub-cgroup program.
 *
 * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
 * that cgroup program gets run in addition to the program in this cgroup.
 *
 * Only one program is allowed to be attached to a cgroup with
 * NONE or BPF_F_ALLOW_OVERRIDE flag.
 * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
 * release old program and attach the new one. Attach flags has to match.
 *
 * Multiple programs are allowed to be attached to a cgroup with
 * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
 * (those that were attached first, run first)
 * The programs of sub-cgroup are executed first, then programs of
 * this cgroup and then programs of parent cgroup.
 * When children program makes decision (like picking TCP CA or sock bind)
 * parent program has a chance to override it.
 *
246 247 248 249 250
 * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of
 * programs for a cgroup. Though it's possible to replace an old program at
 * any position by also specifying BPF_F_REPLACE flag and position itself in
 * replace_bpf_fd attribute. Old program at this position will be released.
 *
251 252 253 254 255 256 257 258 259 260 261 262 263 264 265
 * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
 * A cgroup with NONE doesn't allow any programs in sub-cgroups.
 * Ex1:
 * cgrp1 (MULTI progs A, B) ->
 *    cgrp2 (OVERRIDE prog C) ->
 *      cgrp3 (MULTI prog D) ->
 *        cgrp4 (OVERRIDE prog E) ->
 *          cgrp5 (NONE prog F)
 * the event in cgrp5 triggers execution of F,D,A,B in that order.
 * if prog F is detached, the execution is E,D,A,B
 * if prog F and D are detached, the execution is E,A,B
 * if prog F, E and D are detached, the execution is C,A,B
 *
 * All eligible programs are executed regardless of return code from
 * earlier programs.
266 267
 */
#define BPF_F_ALLOW_OVERRIDE	(1U << 0)
268
#define BPF_F_ALLOW_MULTI	(1U << 1)
269
#define BPF_F_REPLACE		(1U << 2)
270

271 272 273 274 275 276 277
/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
 * verifier will perform strict alignment checking as if the kernel
 * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
 * and NET_IP_ALIGN defined to 2.
 */
#define BPF_F_STRICT_ALIGNMENT	(1U << 0)

D
David Miller 已提交
278 279 280 281 282 283 284 285 286 287 288 289 290 291
/* 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)

292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose.
 * Verifier does sub-register def/use analysis and identifies instructions whose
 * def only matters for low 32-bit, high 32-bit is never referenced later
 * through implicit zero extension. Therefore verifier notifies JIT back-ends
 * that it is safe to ignore clearing high 32-bit for these instructions. This
 * saves some back-ends a lot of code-gen. However such optimization is not
 * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends
 * hence hasn't used verifier's analysis result. But, we really want to have a
 * way to be able to verify the correctness of the described optimization on
 * x86_64 on which testsuites are frequently exercised.
 *
 * So, this flag is introduced. Once it is set, verifier will randomize high
 * 32-bit for those instructions who has been identified as safe to ignore them.
 * Then, if verifier is not doing correct analysis, such randomization will
 * regress tests to expose bugs.
 */
#define BPF_F_TEST_RND_HI32	(1U << 2)

310 311 312
/* The verifier internal test flag. Behavior is undefined */
#define BPF_F_TEST_STATE_FREQ	(1U << 3)

313 314 315 316 317 318 319 320 321 322 323
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
 * two extensions:
 *
 * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
 * insn[0].imm:      map fd              map fd
 * insn[1].imm:      0                   offset into value
 * insn[0].off:      0                   0
 * insn[1].off:      0                   0
 * ldimm64 rewrite:  address of map      address of map[0]+offset
 * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
 */
324
#define BPF_PSEUDO_MAP_FD	1
325
#define BPF_PSEUDO_MAP_VALUE	2
326

327 328 329 330 331
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
 * offset to another bpf function
 */
#define BPF_PSEUDO_CALL		1

332
/* flags for BPF_MAP_UPDATE_ELEM command */
333 334 335 336 337 338
enum {
	BPF_ANY		= 0, /* create new element or update existing */
	BPF_NOEXIST	= 1, /* create new element if it didn't exist */
	BPF_EXIST	= 2, /* update existing element */
	BPF_F_LOCK	= 4, /* spin_lock-ed map_lookup/map_update */
};
339

340
/* flags for BPF_MAP_CREATE command */
341 342
enum {
	BPF_F_NO_PREALLOC	= (1U << 0),
M
Martin KaFai Lau 已提交
343
/* Instead of having one common LRU list in the
344
 * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
M
Martin KaFai Lau 已提交
345 346 347 348
 * which can scale and perform better.
 * Note, the LRU nodes (including free nodes) cannot be moved
 * across different LRU lists.
 */
349
	BPF_F_NO_COMMON_LRU	= (1U << 1),
350
/* Specify numa node during map creation */
351
	BPF_F_NUMA_NODE		= (1U << 2),
352

353
/* Flags for accessing BPF object from syscall side. */
354 355
	BPF_F_RDONLY		= (1U << 3),
	BPF_F_WRONLY		= (1U << 4),
356

357
/* Flag for stack_map, store build_id+offset instead of pointer */
358
	BPF_F_STACK_BUILD_ID	= (1U << 5),
359

360
/* Zero-initialize hash function seed. This should only be used for testing. */
361
	BPF_F_ZERO_SEED		= (1U << 6),
362

363
/* Flags for accessing BPF object from program side. */
364 365
	BPF_F_RDONLY_PROG	= (1U << 7),
	BPF_F_WRONLY_PROG	= (1U << 8),
366

367
/* Clone map from listener for newly accepted socket */
368
	BPF_F_CLONE		= (1U << 9),
369

370
/* Enable memory-mapping BPF map */
371 372
	BPF_F_MMAPABLE		= (1U << 10),
};
373

374 375 376 377 378 379
/* Flags for BPF_PROG_QUERY. */

/* Query effective (directly attached + inherited from ancestor cgroups)
 * programs that will be executed for events within a cgroup.
 * attach_flags with this flag are returned only for directly attached programs.
 */
380 381
#define BPF_F_QUERY_EFFECTIVE	(1U << 0)

382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400
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;
	};
};

401 402
#define BPF_OBJ_NAME_LEN 16U

403 404 405 406 407 408
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 */
409 410 411
		__u32	map_flags;	/* BPF_MAP_CREATE related
					 * flags defined above.
					 */
412
		__u32	inner_map_fd;	/* fd pointing to the inner map */
413 414 415
		__u32	numa_node;	/* numa node (effective only if
					 * BPF_F_NUMA_NODE is set).
					 */
416
		char	map_name[BPF_OBJ_NAME_LEN];
417
		__u32	map_ifindex;	/* ifindex of netdev to create on */
418
		__u32	btf_fd;		/* fd pointing to a BTF type data */
419 420
		__u32	btf_key_type_id;	/* BTF type_id of the key */
		__u32	btf_value_type_id;	/* BTF type_id of the value */
421 422 423 424
		__u32	btf_vmlinux_value_type_id;/* BTF type_id of a kernel-
						   * struct stored as the
						   * map value
						   */
425
	};
426 427 428 429 430 431 432 433

	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
		__u32		map_fd;
		__aligned_u64	key;
		union {
			__aligned_u64 value;
			__aligned_u64 next_key;
		};
434
		__u64		flags;
435
	};
436

437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
	struct { /* struct used by BPF_MAP_*_BATCH commands */
		__aligned_u64	in_batch;	/* start batch,
						 * NULL to start from beginning
						 */
		__aligned_u64	out_batch;	/* output: next start batch */
		__aligned_u64	keys;
		__aligned_u64	values;
		__u32		count;		/* input/output:
						 * input: # of key/value
						 * elements
						 * output: # of filled elements
						 */
		__u32		map_fd;
		__u64		elem_flags;
		__u64		flags;
	} batch;

454 455 456 457 458
	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;
459 460 461
		__u32		log_level;	/* verbosity level of verifier */
		__u32		log_size;	/* size of user buffer */
		__aligned_u64	log_buf;	/* user supplied buffer */
462
		__u32		kern_version;	/* not used */
463
		__u32		prog_flags;
464
		char		prog_name[BPF_OBJ_NAME_LEN];
465
		__u32		prog_ifindex;	/* ifindex of netdev to prep for */
466 467 468 469 470
		/* 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;
Y
Yonghong Song 已提交
471 472 473 474
		__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 */
M
Martin KaFai Lau 已提交
475 476 477
		__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 */
478
		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
479
		__u32		attach_prog_fd; /* 0 to attach to vmlinux */
480
	};
481 482 483 484

	struct { /* anonymous struct used by BPF_OBJ_* commands */
		__aligned_u64	pathname;
		__u32		bpf_fd;
485
		__u32		file_flags;
486
	};
487 488 489 490 491

	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;
492
		__u32		attach_flags;
493 494 495 496
		__u32		replace_bpf_fd;	/* previously attached eBPF
						 * program to replace if
						 * BPF_F_REPLACE is used
						 */
497
	};
498 499 500 501

	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
		__u32		prog_fd;
		__u32		retval;
502 503 504 505 506
		__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.
						 */
507 508 509 510
		__aligned_u64	data_in;
		__aligned_u64	data_out;
		__u32		repeat;
		__u32		duration;
511 512 513 514 515 516 517
		__u32		ctx_size_in;	/* input: len of ctx_in */
		__u32		ctx_size_out;	/* input/output: len of ctx_out
						 *   returns ENOSPC if ctx_out
						 *   is too small.
						 */
		__aligned_u64	ctx_in;
		__aligned_u64	ctx_out;
518
	} test;
519

520 521 522 523
	struct { /* anonymous struct used by BPF_*_GET_*_ID */
		union {
			__u32		start_id;
			__u32		prog_id;
M
Martin KaFai Lau 已提交
524
			__u32		map_id;
M
Martin KaFai Lau 已提交
525
			__u32		btf_id;
526
		};
527
		__u32		next_id;
528
		__u32		open_flags;
529
	};
530 531 532 533 534 535

	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
		__u32		bpf_fd;
		__u32		info_len;
		__aligned_u64	info;
	} info;
536 537 538 539 540 541 542 543 544

	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;
545

546
	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
547 548 549
		__u64 name;
		__u32 prog_fd;
	} raw_tracepoint;
550 551 552 553 554 555 556 557

	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;
	};
558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573

	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;
574 575 576 577 578 579 580

	struct { /* struct used by BPF_LINK_CREATE command */
		__u32		prog_fd;	/* eBPF program to attach */
		__u32		target_fd;	/* object to attach to */
		__u32		attach_type;	/* attach type */
		__u32		flags;		/* extra flags */
	} link_create;
581 582 583 584 585 586 587 588 589 590 591

	struct { /* struct used by BPF_LINK_UPDATE command */
		__u32		link_fd;	/* link fd */
		/* new program fd to update link with */
		__u32		new_prog_fd;
		__u32		flags;		/* extra flags */
		/* expected link's program fd; is specified only if
		 * BPF_F_REPLACE flag is set in flags */
		__u32		old_prog_fd;
	} link_update;

592 593
} __attribute__((aligned(8)));

594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609
/* 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:
610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641
 *
 * 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.
 *
642
 * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
643 644
 * 	Description
 * 		For tracing programs, safely attempt to read *size* bytes from
645 646 647 648
 * 		kernel space address *unsafe_ptr* and store the data in *dst*.
 *
 * 		Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
 * 		instead.
649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * u64 bpf_ktime_get_ns(void)
 * 	Description
 * 		Return the time elapsed since system boot, in nanoseconds.
 * 	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.
668 669
 * 		Lines are discarded while *\/sys/kernel/debug/tracing/trace* is
 * 		open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this.
670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716
 * 		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.
 *
717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737
 * 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.
 *
738 739 740 741 742 743 744 745 746
 * 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).
 *
747
 * 		A call to this helper is susceptible to change the underlying
748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771
 * 		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.
 *
772
 * 		A call to this helper is susceptible to change the underlying
773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803
 * 		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.
 *
804
 * 		A call to this helper is susceptible to change the underlying
805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858
 * 		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.
 *
859
 * 		A call to this helper is susceptible to change the underlying
860 861 862 863 864 865
 * 		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.
866 867 868 869 870 871 872 873 874 875 876 877 878
 *
 * u64 bpf_get_current_pid_tgid(void)
 * 	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
 * 		A 64-bit integer containing the current GID and UID, and
 * 		created as such: *current_gid* **<< 32 \|** *current_uid*.
 *
A
Andrii Nakryiko 已提交
879
 * int bpf_get_current_comm(void *buf, u32 size_of_buf)
880 881 882 883 884 885 886 887 888 889
 * 	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.
 *
890 891 892 893 894 895 896 897 898 899 900
 * 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
901
 * 		*Documentation/admin-guide/cgroup-v1/net_cls.rst*.
902 903 904 905 906 907 908 909 910 911 912 913 914 915
 *
 * 		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.
 *
916 917 918 919 920 921 922 923
 * 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**.
 *
924
 * 		A call to this helper is susceptible to change the underlying
925 926 927 928 929 930 931 932 933 934 935
 * 		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*.
 *
936
 * 		A call to this helper is susceptible to change the underlying
937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031
 * 		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.
 *
1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049
 * 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
1050
 * 		**bpf_perf_event_read**\ () in general. The latter has some ABI
1051 1052
 * 		quirks where error and counter value are used as a return code
 * 		(which is wrong to do since ranges may overlap). This issue is
1053 1054 1055
 * 		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
1056 1057 1058 1059 1060
 * 		**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.
 *
1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074
 * 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.
 *
1075 1076 1077
 * 		The same effect can also be attained with the more generic
 * 		**bpf_redirect_map**\ (), which uses a BPF map to store the
 * 		redirect target instead of providing it directly to the helper.
1078 1079 1080 1081 1082 1083
 * 	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.
 *
1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107
 * 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.
 *
A
Andrii Nakryiko 已提交
1108
 * int bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152
 * 	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.
 *
A
Andrii Nakryiko 已提交
1153
 * int bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len)
1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169
 * 	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.
 *
A
Andrii Nakryiko 已提交
1170
 * int bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags)
1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211
 * 	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.
 *
1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238
 * 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.
 *
A
Andrii Nakryiko 已提交
1239
 * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
 * 	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.
 *
A
Andrii Nakryiko 已提交
1257
 * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size)
1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285
 * 	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.
 *
1286
 * 		A call to this helper is susceptible to change the underlying
1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320
 * 		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.
 *
1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331
 * 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.
 *
1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347
 * 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.
 *
1348 1349 1350
 * u64 bpf_get_current_task(void)
 * 	Return
 * 		A pointer to the current task struct.
1351
 *
1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382
 * 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.
 *
1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398
 * 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*.
 *
1399
 * 		A call to this helper is susceptible to change the underlying
1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434
 * 		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.
 *
1435
 * 		A call to this helper is susceptible to change the underlying
1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473
 * 		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.
 *
1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486
 * 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.
 *
1487
 * 		A call to this helper is susceptible to change the underlying
1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501
 * 		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.
 *
1502
 * 		A call to this helper is susceptible to change the underlying
1503 1504 1505 1506 1507 1508 1509
 * 		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.
 *
1510
 * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
1511
 * 	Description
1512 1513 1514
 * 		Copy a NUL terminated string from an unsafe kernel address
 * 		*unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
 * 		more details.
1515
 *
1516 1517
 * 		Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
 * 		instead.
1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529
 * 	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
1530 1531
 * 		networking traffic statistics as it provides a global socket
 * 		identifier that can be assumed unique.
1532 1533 1534 1535
 * 	Return
 * 		A 8-byte long non-decreasing number on success, or 0 if the
 * 		socket field is missing inside *skb*.
 *
1536 1537 1538
 * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
 * 	Description
 * 		Equivalent to bpf_get_socket_cookie() helper that accepts
1539
 * 		*skb*, but gets socket from **struct bpf_sock_addr** context.
1540 1541 1542 1543 1544 1545
 * 	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
1546
 * 		*skb*, but gets socket from **struct bpf_sock_ops** context.
1547 1548 1549
 * 	Return
 * 		A 8-byte long non-decreasing number.
 *
1550 1551 1552 1553 1554 1555 1556 1557
 * 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).
 *
1558 1559 1560 1561 1562 1563 1564
 * 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
 *
A
Andrii Nakryiko 已提交
1565
 * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586
 * 	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.
 *
1587
 * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
1588 1589 1590 1591
 * 	Description
 * 		Grow or shrink the room for data in the packet associated to
 * 		*skb* by *len_diff*, and according to the selected *mode*.
 *
1592 1593 1594 1595
 *		There are two supported modes at this time:
 *
 *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
 *		  (room space is added or removed below the layer 2 header).
1596 1597 1598 1599
 *
 * 		* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
 * 		  (room space is added or removed below the layer 3 header).
 *
1600
 *		The following flags are supported at this time:
1601 1602 1603
 *
 *		* **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size.
 *		  Adjusting mss in this way is not allowed for datagrams.
1604
 *
1605 1606
 *		* **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**,
 *		  **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**:
1607 1608 1609
 *		  Any new space is reserved to hold a tunnel header.
 *		  Configure skb offsets and other fields accordingly.
 *
1610 1611
 *		* **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**,
 *		  **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**:
1612 1613
 *		  Use with ENCAP_L3 flags to further specify the tunnel type.
 *
1614
 *		* **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*):
1615
 *		  Use with ENCAP_L3/L4 flags to further specify the tunnel
1616
 *		  type; *len* is the length of the inner MAC header.
1617
 *
1618
 * 		A call to this helper is susceptible to change the underlying
1619 1620 1621 1622 1623 1624 1625
 * 		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.
 *
1626 1627 1628 1629 1630 1631 1632 1633 1634
 * 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).
 *
1635 1636 1637 1638 1639
 * 		The lower two bits of *flags* are used as the return code if
 * 		the map lookup fails. This is so that the return value can be
 * 		one of the XDP program return codes up to XDP_TX, as chosen by
 * 		the caller. Any higher bits in the *flags* argument must be
 * 		unset.
1640
 *
1641 1642
 * 		See also bpf_redirect(), which only supports redirecting to an
 * 		ifindex, but doesn't require a map to do so.
1643
 * 	Return
1644
 * 		**XDP_REDIRECT** on success, or the value of the two lower bits
J
Jakub Wilk 已提交
1645
 * 		of the *flags* argument on error.
1646
 *
A
Andrii Nakryiko 已提交
1647
 * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags)
1648 1649 1650 1651 1652 1653 1654 1655 1656 1657
 * 	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.
 *
1658
 * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676
 * 	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.
 *
1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697
 * 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.
 *
1698
 * 		A call to this helper is susceptible to change the underlying
1699 1700 1701 1702 1703 1704
 * 		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.
1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755
 *
 * 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.
 *
1756
 * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
1757 1758 1759 1760 1761 1762 1763 1764 1765 1766
 * 	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.
 *
A
Andrii Nakryiko 已提交
1767
 * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785
 * 	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.
 *
1786
 * int bpf_override_return(struct pt_regs *regs, u64 rc)
1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810
 * 	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
 *
1811
 * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval)
1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826
 * 	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.
 *
1827
 * 		*argval* is a flag array which can combine these flags:
1828 1829 1830 1831
 *
 * 		* **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)
1832
 * 		* **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT)
1833
 *
1834 1835 1836 1837 1838 1839 1840
 * 		Therefore, this function can be used to clear a callback flag by
 * 		setting the appropriate bit to zero. e.g. to disable the RTO
 * 		callback:
 *
 * 		**bpf_sock_ops_cb_flags_set(bpf_sock,**
 * 			**bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)**
 *
1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854
 * 		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).
 *
1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940
 * 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).
 *
1941
 * 		A call to this helper is susceptible to change the underlying
1942 1943 1944 1945 1946 1947 1948 1949 1950 1951
 * 		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.
 *
1952
 * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len)
1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967
 * 	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.
1968 1969 1970 1971 1972 1973 1974
 *
 * 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.
 *
1975
 * 		A call to this helper is susceptible to change the underlying
1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997
 * 		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.
Y
Yonghong Song 已提交
1998
 *
A
Andrii Nakryiko 已提交
1999
 * int bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags)
Y
Yonghong Song 已提交
2000
 * 	Description
2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027
 * 		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>
Y
Yonghong Song 已提交
2028
 * 	Return
2029 2030
 * 		A non-negative value equal to or less than *size* on success,
 * 		or a negative error in case of failure.
2031
 *
A
Andrii Nakryiko 已提交
2032
 * int bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header)
2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053
 * 	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.
 *
2054 2055 2056 2057 2058 2059
 * 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
D
David Ahern 已提交
2060 2061 2062
 *		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
2063 2064
 *		is set to metric from route (IPv4/IPv6 only), and ifindex
 *		is set to the device index of the nexthop from the FIB lookup.
2065
 *
2066 2067 2068
 *		*plen* argument is the size of the passed in struct.
 *		*flags* argument can be a combination of one or more of the
 *		following values:
2069
 *
2070 2071 2072 2073 2074 2075
 *		**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).
2076
 *
2077 2078 2079
 *		*ctx* is either **struct xdp_md** for XDP programs or
 *		**struct sk_buff** tc cls_act programs.
 *	Return
2080 2081 2082
 *		* < 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
2083
 *		  packet is not forwarded or needs assist from full stack
2084
 *
A
Andrii Nakryiko 已提交
2085
 * int bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130
 *	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.
2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146
 *
 * 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.
2147 2148 2149
 *		**BPF_LWT_ENCAP_IP**
 *			IP encapsulation (GRE/GUE/IPIP/etc). The outer header
 *			must be IPv4 or IPv6, followed by zero or more
2150 2151 2152 2153 2154
 *			additional headers, up to **LWT_BPF_MAX_HEADROOM**
 *			total bytes in all prepended headers. Please note that
 *			if **skb_is_gso**\ (*skb*) is true, no more than two
 *			headers can be prepended, and the inner header, if
 *			present, should be either GRE or UDP/GUE.
2155
 *
2156 2157 2158 2159
 *		**BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs
 *		of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can
 *		be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and
 *		**BPF_PROG_TYPE_LWT_XMIT**.
2160
 *
2161
 * 		A call to this helper is susceptible to change the underlying
2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175
 * 		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.
 *
2176
 * 		A call to this helper is susceptible to change the underlying
2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191
 * 		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).
 *
2192
 * 		A call to this helper is susceptible to change the underlying
2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214
 * 		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.
2215
 *			Type of *param*: **struct ipv6_sr_hdr**.
2216 2217 2218
 *		**SEG6_LOCAL_ACTION_END_B6_ENCAP**
 *			End.B6.Encap action: Endpoint bound to an SRv6
 *			encapsulation policy.
2219
 *			Type of *param*: **struct ipv6_sr_hdr**.
2220
 *
2221
 * 		A call to this helper is susceptible to change the underlying
2222 2223 2224 2225 2226 2227
 * 		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.
2228
 *
2229
 * int bpf_rc_repeat(void *ctx)
2230 2231
 *	Description
 *		This helper is used in programs implementing IR decoding, to
2232 2233 2234
 *		report a successfully decoded repeat key message. This delays
 *		the generation of a key up event for previously generated
 *		key down event.
2235
 *
2236 2237
 *		Some IR protocols like NEC have a special IR message for
 *		repeating last button, for when a button is held down.
2238 2239 2240 2241 2242 2243 2244 2245 2246 2247
 *
 *		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
 *
2248
 * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
2249 2250
 *	Description
 *		This helper is used in programs implementing IR decoding, to
2251 2252 2253 2254 2255 2256 2257
 *		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**\ ().
2258
 *
2259 2260
 *		Some protocols include a toggle bit, in case the button	was
 *		released and pressed again between consecutive scancodes.
2261 2262 2263 2264
 *
 *		The *ctx* should point to the lirc sample as passed into
 *		the program.
 *
2265 2266 2267
 *		The *protocol* is the decoded protocol number (see
 *		**enum rc_proto** for some predefined values).
 *
2268 2269 2270 2271 2272
 *		This helper is only available is the kernel was compiled with
 *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
 *		"**y**".
 *	Return
 *		0
2273
 *
2274
 * u64 bpf_skb_cgroup_id(struct sk_buff *skb)
2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288
 * 	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.
2289 2290 2291 2292 2293
 *
 * 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.
2294
 *
2295
 * void *bpf_get_local_storage(void *map, u64 flags)
2296 2297 2298 2299 2300 2301 2302
 *	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.
 *
2303 2304
 *		Depending on the BPF program type, a local storage area
 *		can be shared between multiple instances of the BPF program,
2305 2306 2307
 *		running simultaneously.
 *
 *		A user should care about the synchronization by himself.
2308
 *		For example, by using the **BPF_STX_XADD** instruction to alter
2309 2310
 *		the shared data.
 *	Return
2311
 *		A pointer to the local storage area.
2312 2313 2314
 *
 * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
 *	Description
2315 2316 2317 2318
 *		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.
2319 2320
 *	Return
 *		0 on success, or a negative error in case of failure.
2321
 *
2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339
 * 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.
 *
2340
 * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
2341 2342 2343
 *	Description
 *		Look for TCP socket matching *tuple*, optionally in a child
 *		network namespace *netns*. The return value must be checked,
2344
 *		and if non-**NULL**, released via **bpf_sk_release**\ ().
2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356
 *
 *		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.
 *
2357 2358 2359 2360 2361 2362 2363 2364
 *		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.
2365 2366 2367 2368 2369 2370 2371
 *
 *		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
2372 2373
 *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
 *		For sockets with reuseport option, the **struct bpf_sock**
2374 2375
 *		result is from *reuse*\ **->socks**\ [] using the hash of the
 *		tuple.
2376
 *
2377
 * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
2378 2379 2380
 *	Description
 *		Look for UDP socket matching *tuple*, optionally in a child
 *		network namespace *netns*. The return value must be checked,
2381
 *		and if non-**NULL**, released via **bpf_sk_release**\ ().
2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393
 *
 *		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.
 *
2394 2395 2396 2397 2398 2399 2400 2401
 *		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.
2402 2403 2404 2405 2406 2407 2408
 *
 *		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
2409 2410
 *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
 *		For sockets with reuseport option, the **struct bpf_sock**
2411 2412
 *		result is from *reuse*\ **->socks**\ [] using the hash of the
 *		tuple.
2413
 *
2414
 * int bpf_sk_release(struct bpf_sock *sock)
2415
 *	Description
2416 2417 2418
 *		Release the reference held by *sock*. *sock* must be a
 *		non-**NULL** pointer that was returned from
 *		**bpf_sk_lookup_xxx**\ ().
2419 2420
 *	Return
 *		0 on success, or a negative error in case of failure.
2421
 *
2422 2423 2424 2425 2426 2427 2428 2429 2430 2431
 * 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.
 *
2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443
 * 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.
 *
A
Andrii Nakryiko 已提交
2444
 * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
2445
 *	Description
2446
 *		For socket policies, insert *len* bytes into *msg* at offset
2447 2448 2449
 *		*start*.
 *
 *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
2450
 *		*msg* it may want to insert metadata or options into the *msg*.
2451 2452 2453 2454 2455 2456 2457 2458
 *		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.
2459
 *
A
Andrii Nakryiko 已提交
2460
 * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
2461
 *	Description
A
Andrii Nakryiko 已提交
2462
 *		Will remove *len* bytes from a *msg* starting at byte *start*.
2463 2464 2465 2466
 *		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
2467
 *		invalid either due to *start* byte not being valid part of *msg*
2468 2469
 *		payload and/or *pop* value being to large.
 *	Return
2470
 *		0 on success, or a negative error in case of failure.
2471 2472 2473 2474 2475
 *
 * 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.
2476
 *
2477 2478 2479 2480 2481 2482
 *		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**".
2483
 *	Return
2484
 *		0
2485
 *
2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540
 * int bpf_spin_lock(struct bpf_spin_lock *lock)
 *	Description
 *		Acquire a spinlock represented by the pointer *lock*, which is
 *		stored as part of a value of a map. Taking the lock allows to
 *		safely update the rest of the fields in that value. The
 *		spinlock can (and must) later be released with a call to
 *		**bpf_spin_unlock**\ (\ *lock*\ ).
 *
 *		Spinlocks in BPF programs come with a number of restrictions
 *		and constraints:
 *
 *		* **bpf_spin_lock** objects are only allowed inside maps of
 *		  types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
 *		  list could be extended in the future).
 *		* BTF description of the map is mandatory.
 *		* The BPF program can take ONE lock at a time, since taking two
 *		  or more could cause dead locks.
 *		* Only one **struct bpf_spin_lock** is allowed per map element.
 *		* When the lock is taken, calls (either BPF to BPF or helpers)
 *		  are not allowed.
 *		* The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
 *		  allowed inside a spinlock-ed region.
 *		* The BPF program MUST call **bpf_spin_unlock**\ () to release
 *		  the lock, on all execution paths, before it returns.
 *		* The BPF program can access **struct bpf_spin_lock** only via
 *		  the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
 *		  helpers. Loading or storing data into the **struct
 *		  bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
 *		* To use the **bpf_spin_lock**\ () helper, the BTF description
 *		  of the map value must be a struct and have **struct
 *		  bpf_spin_lock** *anyname*\ **;** field at the top level.
 *		  Nested lock inside another struct is not allowed.
 *		* The **struct bpf_spin_lock** *lock* field in a map value must
 *		  be aligned on a multiple of 4 bytes in that value.
 *		* Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
 *		  the **bpf_spin_lock** field to user space.
 *		* Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
 *		  a BPF program, do not update the **bpf_spin_lock** field.
 *		* **bpf_spin_lock** cannot be on the stack or inside a
 *		  networking packet (it can only be inside of a map values).
 *		* **bpf_spin_lock** is available to root only.
 *		* Tracing programs and socket filter programs cannot use
 *		  **bpf_spin_lock**\ () due to insufficient preemption checks
 *		  (but this may change in the future).
 *		* **bpf_spin_lock** is not allowed in inner maps of map-in-map.
 *	Return
 *		0
 *
 * int bpf_spin_unlock(struct bpf_spin_lock *lock)
 *	Description
 *		Release the *lock* previously locked by a call to
 *		**bpf_spin_lock**\ (\ *lock*\ ).
 *	Return
 *		0
 *
2541 2542 2543
 * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
 *	Description
 *		This helper gets a **struct bpf_sock** pointer such
2544
 *		that all the fields in this **bpf_sock** can be accessed.
2545
 *	Return
2546
 *		A **struct bpf_sock** pointer on success, or **NULL** in
2547
 *		case of failure.
2548 2549 2550 2551 2552 2553
 *
 * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
 *	Description
 *		This helper gets a **struct bpf_tcp_sock** pointer from a
 *		**struct bpf_sock** pointer.
 *	Return
2554
 *		A **struct bpf_tcp_sock** pointer on success, or **NULL** in
2555
 *		case of failure.
B
brakmo 已提交
2556
 *
A
Andrii Nakryiko 已提交
2557
 * int bpf_skb_ecn_set_ce(struct sk_buff *skb)
2558 2559 2560 2561 2562 2563 2564 2565
 *	Description
 *		Set ECN (Explicit Congestion Notification) field of IP header
 *		to **CE** (Congestion Encountered) if current value is **ECT**
 *		(ECN Capable Transport). Otherwise, do nothing. Works with IPv6
 *		and IPv4.
 *	Return
 *		1 if the **CE** flag is set (either by the current helper call
 *		or because it was already present), 0 if it is not set.
2566 2567 2568
 *
 * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
 *	Description
2569 2570
 *		Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
 *		**bpf_sk_release**\ () is unnecessary and not allowed.
2571
 *	Return
2572
 *		A **struct bpf_sock** pointer on success, or **NULL** in
2573
 *		case of failure.
L
Lorenz Bauer 已提交
2574 2575 2576 2577 2578 2579 2580
 *
 * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
 *	Description
 *		Look for TCP socket matching *tuple*, optionally in a child
 *		network namespace *netns*. The return value must be checked,
 *		and if non-**NULL**, released via **bpf_sk_release**\ ().
 *
2581 2582 2583 2584
 *		This function is identical to **bpf_sk_lookup_tcp**\ (), except
 *		that it also returns timewait or request sockets. Use
 *		**bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the
 *		full structure.
L
Lorenz Bauer 已提交
2585 2586 2587 2588 2589 2590
 *
 *		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**
2591 2592
 *		result is from *reuse*\ **->socks**\ [] using the hash of the
 *		tuple.
2593 2594 2595
 *
 * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
 * 	Description
2596 2597
 * 		Check whether *iph* and *th* contain a valid SYN cookie ACK for
 * 		the listening socket in *sk*.
2598
 *
2599 2600 2601
 * 		*iph* points to the start of the IPv4 or IPv6 header, while
 * 		*iph_len* contains **sizeof**\ (**struct iphdr**) or
 * 		**sizeof**\ (**struct ip6hdr**).
2602
 *
2603 2604
 * 		*th* points to the start of the TCP header, while *th_len*
 * 		contains **sizeof**\ (**struct tcphdr**).
2605 2606
 *
 * 	Return
2607 2608
 * 		0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
 * 		error otherwise.
2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624
 *
 * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
 *	Description
 *		Get name of sysctl in /proc/sys/ and copy it into provided by
 *		program buffer *buf* of size *buf_len*.
 *
 *		The buffer is always NUL terminated, unless it's zero-sized.
 *
 *		If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is
 *		copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name
 *		only (e.g. "tcp_mem").
 *	Return
 *		Number of character copied (not including the trailing NUL).
 *
 *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
 *		truncated name in this case).
2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643
 *
 * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
 *	Description
 *		Get current value of sysctl as it is presented in /proc/sys
 *		(incl. newline, etc), and copy it as a string into provided
 *		by program buffer *buf* of size *buf_len*.
 *
 *		The whole value is copied, no matter what file position user
 *		space issued e.g. sys_read at.
 *
 *		The buffer is always NUL terminated, unless it's zero-sized.
 *	Return
 *		Number of character copied (not including the trailing NUL).
 *
 *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
 *		truncated name in this case).
 *
 *		**-EINVAL** if current value was unavailable, e.g. because
 *		sysctl is uninitialized and read returns -EIO for it.
2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677
 *
 * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
 *	Description
 *		Get new value being written by user space to sysctl (before
 *		the actual write happens) and copy it as a string into
 *		provided by program buffer *buf* of size *buf_len*.
 *
 *		User space may write new value at file position > 0.
 *
 *		The buffer is always NUL terminated, unless it's zero-sized.
 *	Return
 *		Number of character copied (not including the trailing NUL).
 *
 *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
 *		truncated name in this case).
 *
 *		**-EINVAL** if sysctl is being read.
 *
 * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
 *	Description
 *		Override new value being written by user space to sysctl with
 *		value provided by program in buffer *buf* of size *buf_len*.
 *
 *		*buf* should contain a string in same form as provided by user
 *		space on sysctl write.
 *
 *		User space may write new value at file position > 0. To override
 *		the whole sysctl value file position should be set to zero.
 *	Return
 *		0 on success.
 *
 *		**-E2BIG** if the *buf_len* is too big.
 *
 *		**-EINVAL** if sysctl is being read.
2678 2679 2680 2681 2682 2683 2684 2685
 *
 * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
 *	Description
 *		Convert the initial part of the string from buffer *buf* of
 *		size *buf_len* to a long integer according to the given base
 *		and save the result in *res*.
 *
 *		The string may begin with an arbitrary amount of white space
2686 2687
 *		(as determined by **isspace**\ (3)) followed by a single
 *		optional '**-**' sign.
2688 2689 2690 2691 2692
 *
 *		Five least significant bits of *flags* encode base, other bits
 *		are currently unused.
 *
 *		Base must be either 8, 10, 16 or 0 to detect it automatically
2693
 *		similar to user space **strtol**\ (3).
2694 2695
 *	Return
 *		Number of characters consumed on success. Must be positive but
2696
 *		no more than *buf_len*.
2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709
 *
 *		**-EINVAL** if no valid digits were found or unsupported base
 *		was provided.
 *
 *		**-ERANGE** if resulting value was out of range.
 *
 * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
 *	Description
 *		Convert the initial part of the string from buffer *buf* of
 *		size *buf_len* to an unsigned long integer according to the
 *		given base and save the result in *res*.
 *
 *		The string may begin with an arbitrary amount of white space
2710
 *		(as determined by **isspace**\ (3)).
2711 2712 2713 2714 2715
 *
 *		Five least significant bits of *flags* encode base, other bits
 *		are currently unused.
 *
 *		Base must be either 8, 10, 16 or 0 to detect it automatically
2716
 *		similar to user space **strtoul**\ (3).
2717 2718
 *	Return
 *		Number of characters consumed on success. Must be positive but
2719
 *		no more than *buf_len*.
2720 2721 2722 2723 2724
 *
 *		**-EINVAL** if no valid digits were found or unsupported base
 *		was provided.
 *
 *		**-ERANGE** if resulting value was out of range.
2725 2726 2727
 *
 * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
 *	Description
2728
 *		Get a bpf-local-storage from a *sk*.
2729 2730 2731 2732
 *
 *		Logically, it could be thought of getting the value from
 *		a *map* with *sk* as the **key**.  From this
 *		perspective,  the usage is not much different from
2733 2734 2735
 *		**bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this
 *		helper enforces the key must be a full socket and the map must
 *		be a **BPF_MAP_TYPE_SK_STORAGE** also.
2736 2737
 *
 *		Underneath, the value is stored locally at *sk* instead of
2738 2739 2740
 *		the *map*.  The *map* is used as the bpf-local-storage
 *		"type". The bpf-local-storage "type" (i.e. the *map*) is
 *		searched against all bpf-local-storages residing at *sk*.
2741
 *
2742
 *		An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
2743 2744
 *		used such that a new bpf-local-storage will be
 *		created if one does not exist.  *value* can be used
2745
 *		together with **BPF_SK_STORAGE_GET_F_CREATE** to specify
2746
 *		the initial value of a bpf-local-storage.  If *value* is
2747
 *		**NULL**, the new bpf-local-storage will be zero initialized.
2748 2749 2750 2751 2752 2753 2754 2755
 *	Return
 *		A bpf-local-storage pointer is returned on success.
 *
 *		**NULL** if not found or there was an error in adding
 *		a new bpf-local-storage.
 *
 * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
 *	Description
2756
 *		Delete a bpf-local-storage from a *sk*.
2757 2758 2759 2760
 *	Return
 *		0 on success.
 *
 *		**-ENOENT** if the bpf-local-storage cannot be found.
2761 2762 2763
 *
 * int bpf_send_signal(u32 sig)
 *	Description
2764 2765
 *		Send signal *sig* to the process of the current task.
 *		The signal may be delivered to any of this process's threads.
2766 2767 2768 2769 2770 2771 2772 2773 2774 2775
 *	Return
 *		0 on success or successfully queued.
 *
 *		**-EBUSY** if work queue under nmi is full.
 *
 *		**-EINVAL** if *sig* is invalid.
 *
 *		**-EPERM** if no permission to send the *sig*.
 *
 *		**-EAGAIN** if bpf program can try again.
2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802
 *
 * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
 *	Description
 *		Try to issue a SYN cookie for the packet with corresponding
 *		IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
 *
 *		*iph* points to the start of the IPv4 or IPv6 header, while
 *		*iph_len* contains **sizeof**\ (**struct iphdr**) or
 *		**sizeof**\ (**struct ip6hdr**).
 *
 *		*th* points to the start of the TCP header, while *th_len*
 *		contains the length of the TCP header.
 *
 *	Return
 *		On success, lower 32 bits hold the generated SYN cookie in
 *		followed by 16 bits which hold the MSS value for that cookie,
 *		and the top 16 bits are unused.
 *
 *		On failure, the returned value is one of the following:
 *
 *		**-EINVAL** SYN cookie cannot be issued due to error
 *
 *		**-ENOENT** SYN cookie should not be issued (no SYN flood)
 *
 *		**-EOPNOTSUPP** kernel configuration does not enable SYN cookies
 *
 *		**-EPROTONOSUPPORT** IP packet version is not 4 or 6
2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826
 *
 * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
 * 	Description
 * 		Write raw *data* blob into a special BPF perf event held by
 * 		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
 * 		event must have the following attributes: **PERF_SAMPLE_RAW**
 * 		as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
 * 		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
 *
 * 		The *flags* are used to indicate the index in *map* for which
 * 		the value must be put, masked with **BPF_F_INDEX_MASK**.
 * 		Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
 * 		to indicate that the index of the current CPU core should be
 * 		used.
 *
 * 		The value to write, of *size*, is passed through eBPF stack and
 * 		pointed by *data*.
 *
 * 		*ctx* is a pointer to in-kernel struct sk_buff.
 *
 * 		This helper is similar to **bpf_perf_event_output**\ () but
 * 		restricted to raw_tracepoint bpf programs.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892
 *
 * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
 * 	Description
 * 		Safely attempt to read *size* bytes from user space address
 * 		*unsafe_ptr* and store the data in *dst*.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
 * 	Description
 * 		Safely attempt to read *size* bytes from kernel space address
 * 		*unsafe_ptr* and store the data in *dst*.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
 * 	Description
 * 		Copy a NUL terminated string from an unsafe user address
 * 		*unsafe_ptr* to *dst*. The *size* should include the
 * 		terminating NUL byte. In case the string length is smaller than
 * 		*size*, the target is not padded with further NUL bytes. If the
 * 		string length is larger than *size*, just *size*-1 bytes are
 * 		copied and the last byte is set to NUL.
 *
 * 		On success, 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_user_str(buf, sizeof(buf),
 * 				                                  ctx->di);
 *
 * 				// Consume buf, for example push it to
 * 				// userspace via bpf_perf_event_output(); we
 * 				// can use res (the string length) as event
 * 				// size, after checking its boundaries.
 * 			}
 *
 * 		In comparison, using **bpf_probe_read_user()** helper here
 * 		instead to read the string would require to estimate the length
 * 		at compile time, and would often result in copying more memory
 * 		than necessary.
 *
 * 		Another useful use case is when parsing individual process
 * 		arguments or individual environment variables navigating
 * 		*current*\ **->mm->arg_start** and *current*\
 * 		**->mm->env_start**: using this helper and the return value,
 * 		one can quickly iterate at the right offset of the memory area.
 * 	Return
 * 		On success, the strictly positive length of the string,
 * 		including the trailing NUL character. On error, a negative
 * 		value.
 *
 * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
 * 	Description
 * 		Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
 * 		to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
 * 	Return
 * 		On success, the strictly positive length of the string,	including
 * 		the trailing NUL character. On error, a negative value.
2893 2894 2895 2896 2897 2898 2899 2900
 *
 * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
 *	Description
 *		Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
 *		*rcv_nxt* is the ack_seq to be sent out.
 *	Return
 *		0 on success, or a negative error in case of failure.
 *
2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913
 * int bpf_send_signal_thread(u32 sig)
 *	Description
 *		Send signal *sig* to the thread corresponding to the current task.
 *	Return
 *		0 on success or successfully queued.
 *
 *		**-EBUSY** if work queue under nmi is full.
 *
 *		**-EINVAL** if *sig* is invalid.
 *
 *		**-EPERM** if no permission to send the *sig*.
 *
 *		**-EAGAIN** if bpf program can try again.
M
Martin KaFai Lau 已提交
2914 2915 2916 2917 2918 2919
 *
 * u64 bpf_jiffies64(void)
 *	Description
 *		Obtain the 64bit jiffies
 *	Return
 *		The 64 bit jiffies
2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938
 *
 * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
 *	Description
 *		For an eBPF program attached to a perf event, retrieve the
 *		branch records (struct perf_branch_entry) associated to *ctx*
 *		and store it in	the buffer pointed by *buf* up to size
 *		*size* bytes.
 *	Return
 *		On success, number of bytes written to *buf*. On error, a
 *		negative value.
 *
 *		The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
 *		instead	return the number of bytes required to store all the
 *		branch entries. If this flag is set, *buf* may be NULL.
 *
 *		**-EINVAL** if arguments invalid or **size** not a multiple
 *		of sizeof(struct perf_branch_entry).
 *
 *		**-ENOENT** if architecture does not support branch records.
2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951
 *
 * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
 *	Description
 *		Returns 0 on success, values for *pid* and *tgid* as seen from the current
 *		*namespace* will be returned in *nsdata*.
 *
 *		On failure, the returned value is one of the following:
 *
 *		**-EINVAL** if dev and inum supplied don't match dev_t and inode number
 *              with nsfs of current task, or if dev conversion to dev_t lost high bits.
 *
 *		**-ENOENT** if pidns does not exists for the current task.
 *
2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974
 * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
 *	Description
 *		Write raw *data* blob into a special BPF perf event held by
 *		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
 *		event must have the following attributes: **PERF_SAMPLE_RAW**
 *		as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
 *		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
 *
 *		The *flags* are used to indicate the index in *map* for which
 *		the value must be put, masked with **BPF_F_INDEX_MASK**.
 *		Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
 *		to indicate that the index of the current CPU core should be
 *		used.
 *
 *		The value to write, of *size*, is passed through eBPF stack and
 *		pointed by *data*.
 *
 *		*ctx* is a pointer to in-kernel struct xdp_buff.
 *
 *		This helper is similar to **bpf_perf_eventoutput**\ () but
 *		restricted to raw_tracepoint bpf programs.
 *	Return
 *		0 on success, or a negative error in case of failure.
2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987
 *
 * u64 bpf_get_netns_cookie(void *ctx)
 * 	Description
 * 		Retrieve the cookie (generated by the kernel) of the network
 * 		namespace the input *ctx* is associated with. The network
 * 		namespace cookie remains stable for its lifetime and provides
 * 		a global identifier that can be assumed unique. If *ctx* is
 * 		NULL, then the helper returns the cookie for the initial
 * 		network namespace. The cookie itself is very similar to that
 * 		of bpf_get_socket_cookie() helper, but for network namespaces
 * 		instead of sockets.
 * 	Return
 * 		A 8-byte long opaque number.
2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005
 *
 * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level)
 * 	Description
 * 		Return id of cgroup v2 that is ancestor of the cgroup associated
 * 		with the current task at the *ancestor_level*. The root cgroup
 * 		is at *ancestor_level* zero and each step down the hierarchy
 * 		increments the level. If *ancestor_level* == level of cgroup
 * 		associated with the current task, then return value will be the
 * 		same as that of **bpf_get_current_cgroup_id**\ ().
 *
 * 		The helper is useful to implement policies based on cgroups
 * 		that are upper in hierarchy than immediate cgroup associated
 * 		with the current task.
 *
 * 		The format of returned id and helper limitations are same as in
 * 		**bpf_get_current_cgroup_id**\ ().
 * 	Return
 * 		The id is returned or 0 in case the id could not be retrieved.
J
Joe Stringer 已提交
3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027
 *
 * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
 *	Description
 *		Assign the *sk* to the *skb*. When combined with appropriate
 *		routing configuration to receive the packet towards the socket,
 *		will cause *skb* to be delivered to the specified socket.
 *		Subsequent redirection of *skb* via  **bpf_redirect**\ (),
 *		**bpf_clone_redirect**\ () or other methods outside of BPF may
 *		interfere with successful delivery to the socket.
 *
 *		This operation is only valid from TC ingress path.
 *
 *		The *flags* argument must be zero.
 *	Return
 *		0 on success, or a negative errno in case of failure.
 *
 *		* **-EINVAL**		Unsupported flags specified.
 *		* **-ENOENT**		Socket is unavailable for assignment.
 *		* **-ENETUNREACH**	Socket is unreachable (wrong netns).
 *		* **-EOPNOTSUPP**	Unsupported operation, for example a
 *					call from outside of TC ingress.
 *		* **-ESOCKTNOSUPPORT**	Socket type not supported (reuseport).
3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071
 */
#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),		\
3072
	FN(get_numa_node_id),		\
3073
	FN(skb_change_head),		\
3074
	FN(xdp_adjust_head),		\
3075
	FN(probe_read_str),		\
3076
	FN(get_socket_cookie),		\
3077
	FN(get_socket_uid),		\
3078
	FN(set_hash),			\
3079
	FN(setsockopt),			\
3080
	FN(skb_adjust_room),		\
3081 3082 3083
	FN(redirect_map),		\
	FN(sk_redirect_map),		\
	FN(sock_map_update),		\
3084
	FN(xdp_adjust_meta),		\
3085
	FN(perf_event_read_value),	\
3086
	FN(perf_prog_read_value),	\
3087
	FN(getsockopt),			\
3088
	FN(override_return),		\
3089
	FN(sock_ops_cb_flags_set),	\
3090
	FN(msg_redirect_map),		\
3091
	FN(msg_apply_bytes),		\
3092
	FN(msg_cork_bytes),		\
A
Andrey Ignatov 已提交
3093
	FN(msg_pull_data),		\
3094
	FN(bind),			\
3095
	FN(xdp_adjust_tail),		\
Y
Yonghong Song 已提交
3096
	FN(skb_get_xfrm_state),		\
3097
	FN(get_stack),			\
3098
	FN(skb_load_bytes_relative),	\
3099 3100 3101
	FN(fib_lookup),			\
	FN(sock_hash_update),		\
	FN(msg_redirect_hash),		\
3102 3103 3104 3105
	FN(sk_redirect_hash),		\
	FN(lwt_push_encap),		\
	FN(lwt_seg6_store_bytes),	\
	FN(lwt_seg6_adjust_srh),	\
3106 3107
	FN(lwt_seg6_action),		\
	FN(rc_repeat),			\
3108
	FN(rc_keydown),			\
3109
	FN(skb_cgroup_id),		\
3110
	FN(get_current_cgroup_id),	\
3111
	FN(get_local_storage),		\
3112
	FN(sk_select_reuseport),	\
3113 3114 3115
	FN(skb_ancestor_cgroup_id),	\
	FN(sk_lookup_tcp),		\
	FN(sk_lookup_udp),		\
M
Mauricio Vasquez B 已提交
3116 3117 3118
	FN(sk_release),			\
	FN(map_push_elem),		\
	FN(map_pop_elem),		\
3119
	FN(map_peek_elem),		\
3120
	FN(msg_push_data),		\
3121
	FN(msg_pop_data),		\
3122 3123
	FN(rc_pointer_rel),		\
	FN(spin_lock),			\
3124
	FN(spin_unlock),		\
3125
	FN(sk_fullsock),		\
B
brakmo 已提交
3126
	FN(tcp_sock),			\
3127
	FN(skb_ecn_set_ce),		\
L
Lorenz Bauer 已提交
3128
	FN(get_listener_sock),		\
3129
	FN(skc_lookup_tcp),		\
3130
	FN(tcp_check_syncookie),	\
3131
	FN(sysctl_get_name),		\
3132 3133
	FN(sysctl_get_current_value),	\
	FN(sysctl_get_new_value),	\
3134 3135
	FN(sysctl_set_new_value),	\
	FN(strtol),			\
3136 3137
	FN(strtoul),			\
	FN(sk_storage_get),		\
3138
	FN(sk_storage_delete),		\
3139
	FN(send_signal),		\
3140
	FN(tcp_gen_syncookie),		\
3141 3142 3143 3144
	FN(skb_output),			\
	FN(probe_read_user),		\
	FN(probe_read_kernel),		\
	FN(probe_read_user_str),	\
3145
	FN(probe_read_kernel_str),	\
3146
	FN(tcp_send_ack),		\
M
Martin KaFai Lau 已提交
3147
	FN(send_signal_thread),		\
3148
	FN(jiffies64),			\
3149
	FN(read_branch_records),	\
3150
	FN(get_ns_current_pid_tgid),	\
3151
	FN(xdp_output),			\
3152
	FN(get_netns_cookie),		\
J
Joe Stringer 已提交
3153 3154
	FN(get_current_ancestor_cgroup_id),	\
	FN(sk_assign),
3155

3156 3157 3158
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
 * function eBPF program intends to call
 */
3159
#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
3160
enum bpf_func_id {
3161
	__BPF_FUNC_MAPPER(__BPF_ENUM_FN)
3162 3163
	__BPF_FUNC_MAX_ID,
};
3164
#undef __BPF_ENUM_FN
3165

3166 3167 3168
/* All flags used by eBPF helper functions, placed here. */

/* BPF_FUNC_skb_store_bytes flags. */
3169 3170 3171 3172
enum {
	BPF_F_RECOMPUTE_CSUM		= (1ULL << 0),
	BPF_F_INVALIDATE_HASH		= (1ULL << 1),
};
3173 3174 3175 3176

/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
 * First 4 bits are for passing the header field size.
 */
3177 3178 3179
enum {
	BPF_F_HDR_FIELD_MASK		= 0xfULL,
};
3180 3181

/* BPF_FUNC_l4_csum_replace flags. */
3182 3183 3184 3185 3186
enum {
	BPF_F_PSEUDO_HDR		= (1ULL << 4),
	BPF_F_MARK_MANGLED_0		= (1ULL << 5),
	BPF_F_MARK_ENFORCE		= (1ULL << 6),
};
3187 3188

/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
3189 3190 3191
enum {
	BPF_F_INGRESS			= (1ULL << 0),
};
3192

3193
/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
3194 3195 3196
enum {
	BPF_F_TUNINFO_IPV6		= (1ULL << 0),
};
3197

Y
Yonghong Song 已提交
3198
/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
3199 3200 3201
enum {
	BPF_F_SKIP_FIELD_MASK		= 0xffULL,
	BPF_F_USER_STACK		= (1ULL << 8),
Y
Yonghong Song 已提交
3202
/* flags used by BPF_FUNC_get_stackid only. */
3203 3204
	BPF_F_FAST_STACK_CMP		= (1ULL << 9),
	BPF_F_REUSE_STACKID		= (1ULL << 10),
Y
Yonghong Song 已提交
3205
/* flags used by BPF_FUNC_get_stack only. */
3206 3207
	BPF_F_USER_BUILD_ID		= (1ULL << 11),
};
3208

3209
/* BPF_FUNC_skb_set_tunnel_key flags. */
3210 3211 3212 3213 3214
enum {
	BPF_F_ZERO_CSUM_TX		= (1ULL << 1),
	BPF_F_DONT_FRAGMENT		= (1ULL << 2),
	BPF_F_SEQ_NUMBER		= (1ULL << 3),
};
3215

3216 3217 3218
/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
 * BPF_FUNC_perf_event_read_value flags.
 */
3219 3220 3221
enum {
	BPF_F_INDEX_MASK		= 0xffffffffULL,
	BPF_F_CURRENT_CPU		= BPF_F_INDEX_MASK,
3222
/* BPF_FUNC_perf_event_output for sk_buff input context. */
3223 3224
	BPF_F_CTXLEN_MASK		= (0xfffffULL << 32),
};
3225

3226
/* Current network namespace */
3227 3228 3229
enum {
	BPF_F_CURRENT_NETNS		= (-1L),
};
3230

3231
/* BPF_FUNC_skb_adjust_room flags. */
3232 3233 3234 3235 3236 3237 3238
enum {
	BPF_F_ADJ_ROOM_FIXED_GSO	= (1ULL << 0),
	BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	= (1ULL << 1),
	BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	= (1ULL << 2),
	BPF_F_ADJ_ROOM_ENCAP_L4_GRE	= (1ULL << 3),
	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),
};
3239

3240 3241 3242 3243
enum {
	BPF_ADJ_ROOM_ENCAP_L2_MASK	= 0xff,
	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	= 56,
};
3244

3245
#define BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
3246 3247
					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
3248

3249
/* BPF_FUNC_sysctl_get_name flags. */
3250 3251 3252
enum {
	BPF_F_SYSCTL_BASE_NAME		= (1ULL << 0),
};
3253

3254
/* BPF_FUNC_sk_storage_get flags */
3255 3256 3257
enum {
	BPF_SK_STORAGE_GET_F_CREATE	= (1ULL << 0),
};
3258

3259
/* BPF_FUNC_read_branch_records flags. */
3260 3261 3262
enum {
	BPF_F_GET_BRANCH_RECORDS_SIZE	= (1ULL << 0),
};
3263

3264 3265 3266
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
	BPF_ADJ_ROOM_NET,
3267
	BPF_ADJ_ROOM_MAC,
3268 3269
};

3270 3271 3272 3273 3274 3275
/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
enum bpf_hdr_start_off {
	BPF_HDR_START_MAC,
	BPF_HDR_START_NET,
};

3276 3277 3278
/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */
enum bpf_lwt_encap_mode {
	BPF_LWT_ENCAP_SEG6,
3279 3280
	BPF_LWT_ENCAP_SEG6_INLINE,
	BPF_LWT_ENCAP_IP,
3281 3282
};

3283 3284 3285 3286 3287 3288
#define __bpf_md_ptr(type, name)	\
union {					\
	type name;			\
	__u64 :64;			\
} __attribute__((aligned(8)))

3289 3290 3291 3292 3293 3294 3295 3296
/* 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;
3297 3298 3299
	__u32 protocol;
	__u32 vlan_present;
	__u32 vlan_tci;
3300
	__u32 vlan_proto;
3301
	__u32 priority;
3302 3303
	__u32 ingress_ifindex;
	__u32 ifindex;
3304 3305
	__u32 tc_index;
	__u32 cb[5];
3306
	__u32 hash;
3307
	__u32 tc_classid;
A
Alexei Starovoitov 已提交
3308 3309
	__u32 data;
	__u32 data_end;
3310
	__u32 napi_id;
3311

3312
	/* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
3313 3314 3315 3316 3317 3318 3319
	__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 */
3320 3321 3322
	/* ... here. */

	__u32 data_meta;
3323
	__bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
3324
	__u64 tstamp;
3325
	__u32 wire_len;
3326
	__u32 gso_segs;
3327
	__bpf_md_ptr(struct bpf_sock *, sk);
3328
	__u32 gso_size;
3329 3330
};

3331 3332
struct bpf_tunnel_key {
	__u32 tunnel_id;
3333 3334 3335 3336 3337 3338
	union {
		__u32 remote_ipv4;
		__u32 remote_ipv6[4];
	};
	__u8 tunnel_tos;
	__u8 tunnel_ttl;
3339
	__u16 tunnel_ext;	/* Padding, future use. */
3340
	__u32 tunnel_label;
3341 3342
};

3343 3344 3345 3346 3347 3348 3349
/* 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;
3350
	__u16 ext;	/* Padding, future use. */
3351 3352 3353 3354 3355 3356
	union {
		__u32 remote_ipv4;	/* Stored in network byte order */
		__u32 remote_ipv6[4];	/* Stored in network byte order */
	};
};

3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369
/* Generic BPF return codes which all BPF program types may support.
 * The values are binary compatible with their TC_ACT_* counter-part to
 * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
 * programs.
 *
 * XDP is handled seprately, see XDP_*.
 */
enum bpf_ret_code {
	BPF_OK = 0,
	/* 1 reserved */
	BPF_DROP = 2,
	/* 3-6 reserved */
	BPF_REDIRECT = 7,
3370 3371 3372 3373 3374 3375 3376 3377 3378
	/* >127 are reserved for prog type specific return codes.
	 *
	 * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and
	 *    BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been
	 *    changed and should be routed based on its new L3 header.
	 *    (This is an L3 redirect, as opposed to L2 redirect
	 *    represented by BPF_REDIRECT above).
	 */
	BPF_LWT_REROUTE = 128,
3379 3380
};

3381 3382
struct bpf_sock {
	__u32 bound_dev_if;
3383 3384 3385
	__u32 family;
	__u32 type;
	__u32 protocol;
3386 3387
	__u32 mark;
	__u32 priority;
3388 3389 3390 3391 3392 3393 3394 3395
	/* IP address also allows 1 and 2 bytes access */
	__u32 src_ip4;
	__u32 src_ip6[4];
	__u32 src_port;		/* host byte order */
	__u32 dst_port;		/* network byte order */
	__u32 dst_ip4;
	__u32 dst_ip6[4];
	__u32 state;
3396 3397
};

3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434
struct bpf_tcp_sock {
	__u32 snd_cwnd;		/* Sending congestion window		*/
	__u32 srtt_us;		/* smoothed round trip time << 3 in usecs */
	__u32 rtt_min;
	__u32 snd_ssthresh;	/* Slow start size threshold		*/
	__u32 rcv_nxt;		/* What we want to receive next		*/
	__u32 snd_nxt;		/* Next sequence we send		*/
	__u32 snd_una;		/* First byte we want an ack for	*/
	__u32 mss_cache;	/* Cached effective mss, not including SACKS */
	__u32 ecn_flags;	/* ECN status bits.			*/
	__u32 rate_delivered;	/* saved rate sample: packets delivered */
	__u32 rate_interval_us;	/* saved rate sample: time elapsed */
	__u32 packets_out;	/* Packets which are "in flight"	*/
	__u32 retrans_out;	/* Retransmitted packets out		*/
	__u32 total_retrans;	/* Total retransmits for entire connection */
	__u32 segs_in;		/* RFC4898 tcpEStatsPerfSegsIn
				 * total number of segments in.
				 */
	__u32 data_segs_in;	/* RFC4898 tcpEStatsPerfDataSegsIn
				 * total number of data segments in.
				 */
	__u32 segs_out;		/* RFC4898 tcpEStatsPerfSegsOut
				 * The total number of segments sent.
				 */
	__u32 data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
				 * total number of data segments sent.
				 */
	__u32 lost_out;		/* Lost packets			*/
	__u32 sacked_out;	/* SACK'd packets			*/
	__u64 bytes_received;	/* RFC4898 tcpEStatsAppHCThruOctetsReceived
				 * sum(delta(rcv_nxt)), or how many bytes
				 * were acked.
				 */
	__u64 bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
				 * sum(delta(snd_una)), or how many bytes
				 * were acked.
				 */
3435 3436 3437 3438 3439
	__u32 dsack_dups;	/* RFC4898 tcpEStatsStackDSACKDups
				 * total number of DSACK blocks received
				 */
	__u32 delivered;	/* Total data packets delivered incl. rexmits */
	__u32 delivered_ce;	/* Like the above but only ECE marked packets */
3440
	__u32 icsk_retransmits;	/* Number of unrecovered [RTO] timeouts */
3441 3442
};

3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459
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;
	};
};

3460 3461 3462 3463
struct bpf_xdp_sock {
	__u32 queue_id;
};

3464 3465
#define XDP_PACKET_HEADROOM 256

3466 3467
/* User return codes for XDP prog type.
 * A valid XDP program must return one of these defined values. All other
3468 3469
 * return codes are reserved for future use. Unknown return codes will
 * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
3470 3471 3472 3473 3474
 */
enum xdp_action {
	XDP_ABORTED = 0,
	XDP_DROP,
	XDP_PASS,
3475
	XDP_TX,
3476
	XDP_REDIRECT,
3477 3478 3479 3480 3481 3482 3483 3484
};

/* 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;
3485
	__u32 data_meta;
3486
	/* Below access go through struct xdp_rxq_info */
3487 3488
	__u32 ingress_ifindex; /* rxq->dev->ifindex */
	__u32 rx_queue_index;  /* rxq->queue_index  */
3489 3490
};

3491
enum sk_action {
3492 3493
	SK_DROP = 0,
	SK_PASS,
3494 3495
};

3496 3497 3498 3499
/* user accessible metadata for SK_MSG packet hook, new fields must
 * be added to the end of this structure
 */
struct sk_msg_md {
3500 3501
	__bpf_md_ptr(void *, data);
	__bpf_md_ptr(void *, data_end);
3502 3503 3504 3505 3506 3507 3508 3509

	__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 */
3510
	__u32 size;		/* Total size of sk_msg */
3511 3512
};

3513 3514 3515 3516 3517
struct sk_reuseport_md {
	/*
	 * Start of directly accessible data. It begins from
	 * the tcp/udp header.
	 */
3518 3519 3520
	__bpf_md_ptr(void *, data);
	/* End of directly accessible data */
	__bpf_md_ptr(void *, data_end);
3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537
	/*
	 * 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 */
};

3538 3539 3540 3541 3542 3543 3544 3545 3546 3547
#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;
3548 3549 3550 3551
	__u64 load_time;	/* ns since boottime */
	__u32 created_by_uid;
	__u32 nr_map_ids;
	__aligned_u64 map_ids;
3552
	char name[BPF_OBJ_NAME_LEN];
3553
	__u32 ifindex;
3554
	__u32 gpl_compatible:1;
3555
	__u32 :31; /* alignment pad */
3556 3557
	__u64 netns_dev;
	__u64 netns_ino;
3558
	__u32 nr_jited_ksyms;
3559
	__u32 nr_jited_func_lens;
3560
	__aligned_u64 jited_ksyms;
3561
	__aligned_u64 jited_func_lens;
Y
Yonghong Song 已提交
3562 3563 3564
	__u32 btf_id;
	__u32 func_info_rec_size;
	__aligned_u64 func_info;
3565 3566
	__u32 nr_func_info;
	__u32 nr_line_info;
M
Martin KaFai Lau 已提交
3567 3568
	__aligned_u64 line_info;
	__aligned_u64 jited_line_info;
3569
	__u32 nr_jited_line_info;
M
Martin KaFai Lau 已提交
3570 3571
	__u32 line_info_rec_size;
	__u32 jited_line_info_rec_size;
3572 3573
	__u32 nr_prog_tags;
	__aligned_u64 prog_tags;
3574 3575
	__u64 run_time_ns;
	__u64 run_cnt;
3576 3577 3578 3579 3580 3581 3582 3583 3584
} __attribute__((aligned(8)));

struct bpf_map_info {
	__u32 type;
	__u32 id;
	__u32 key_size;
	__u32 value_size;
	__u32 max_entries;
	__u32 map_flags;
3585
	char  name[BPF_OBJ_NAME_LEN];
3586
	__u32 ifindex;
3587
	__u32 btf_vmlinux_value_type_id;
3588 3589
	__u64 netns_dev;
	__u64 netns_ino;
M
Martin KaFai Lau 已提交
3590
	__u32 btf_id;
3591 3592
	__u32 btf_key_type_id;
	__u32 btf_value_type_id;
3593 3594
} __attribute__((aligned(8)));

3595 3596 3597 3598 3599 3600
struct bpf_btf_info {
	__aligned_u64 btf;
	__u32 btf_size;
	__u32 id;
} __attribute__((aligned(8)));

A
Andrey Ignatov 已提交
3601 3602 3603 3604 3605 3606 3607 3608 3609
/* 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.
				 */
3610
	__u32 user_ip6[4];	/* Allows 1,2,4,8-byte read and 4,8-byte write.
A
Andrey Ignatov 已提交
3611 3612 3613 3614 3615 3616 3617 3618
				 * 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 */
3619
	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read and 4-byte write.
A
Andrey Ignatov 已提交
3620 3621
				 * Stored in network byte order.
				 */
3622
	__u32 msg_src_ip6[4];	/* Allows 1,2,4,8-byte read and 4,8-byte write.
A
Andrey Ignatov 已提交
3623 3624
				 * Stored in network byte order.
				 */
3625
	__bpf_md_ptr(struct bpf_sock *, sk);
A
Andrey Ignatov 已提交
3626 3627
};

L
Lawrence Brakmo 已提交
3628 3629 3630 3631 3632 3633 3634 3635 3636
/* User bpf_sock_ops struct to access socket values and specify request ops
 * and their replies.
 * Some of this fields are in network (bigendian) byte order and may need
 * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h).
 * New fields can only be added at the end of this structure
 */
struct bpf_sock_ops {
	__u32 op;
	union {
3637 3638 3639
		__u32 args[4];		/* Optionally passed to bpf program */
		__u32 reply;		/* Returned by bpf program	    */
		__u32 replylong[4];	/* Optionally returned by bpf prog  */
L
Lawrence Brakmo 已提交
3640 3641 3642 3643 3644 3645 3646 3647
	};
	__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 */
3648 3649 3650 3651 3652 3653
	__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 */
3654
	__u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */
3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676
	__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;
3677
	__bpf_md_ptr(struct bpf_sock *, sk);
L
Lawrence Brakmo 已提交
3678 3679
};

3680
/* Definitions for bpf_sock_ops_cb_flags */
3681 3682 3683 3684 3685 3686 3687 3688
enum {
	BPF_SOCK_OPS_RTO_CB_FLAG	= (1<<0),
	BPF_SOCK_OPS_RETRANS_CB_FLAG	= (1<<1),
	BPF_SOCK_OPS_STATE_CB_FLAG	= (1<<2),
	BPF_SOCK_OPS_RTT_CB_FLAG	= (1<<3),
/* Mask of all currently supported cb flags */
	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0xF,
};
3689

L
Lawrence Brakmo 已提交
3690 3691 3692 3693 3694
/* List of known BPF sock_ops operators.
 * New entries can only be added at the end
 */
enum {
	BPF_SOCK_OPS_VOID,
3695 3696 3697
	BPF_SOCK_OPS_TIMEOUT_INIT,	/* Should return SYN-RTO value to use or
					 * -1 if default value should be used
					 */
3698 3699 3700 3701
	BPF_SOCK_OPS_RWND_INIT,		/* Should return initial advertized
					 * window (in packets) or -1 if default
					 * value should be used
					 */
3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712
	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
						 */
3713 3714 3715
	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
					 * needs ECN
					 */
3716 3717 3718 3719 3720 3721 3722
	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
					 */
L
Lawrence Brakmo 已提交
3723 3724 3725 3726 3727
	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
					 */
3728 3729 3730 3731 3732 3733
	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)
					 */
L
Lawrence Brakmo 已提交
3734 3735 3736 3737
	BPF_SOCK_OPS_STATE_CB,		/* Called when TCP changes state.
					 * Arg1: old_state
					 * Arg2: new_state
					 */
3738 3739 3740
	BPF_SOCK_OPS_TCP_LISTEN_CB,	/* Called on listen(2), right after
					 * socket transition to LISTEN state.
					 */
3741 3742
	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
					 */
L
Lawrence Brakmo 已提交
3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764
};

/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
 * changes between the TCP and BPF versions. Ideally this should never happen.
 * If it does, we need to add code to convert them before calling
 * the BPF sock_ops function.
 */
enum {
	BPF_TCP_ESTABLISHED = 1,
	BPF_TCP_SYN_SENT,
	BPF_TCP_SYN_RECV,
	BPF_TCP_FIN_WAIT1,
	BPF_TCP_FIN_WAIT2,
	BPF_TCP_TIME_WAIT,
	BPF_TCP_CLOSE,
	BPF_TCP_CLOSE_WAIT,
	BPF_TCP_LAST_ACK,
	BPF_TCP_LISTEN,
	BPF_TCP_CLOSING,	/* Now a valid state */
	BPF_TCP_NEW_SYN_RECV,

	BPF_TCP_MAX_STATES	/* Leave at the end! */
L
Lawrence Brakmo 已提交
3765 3766
};

3767 3768 3769 3770
enum {
	TCP_BPF_IW		= 1001,	/* Set TCP initial congestion window */
	TCP_BPF_SNDCWND_CLAMP	= 1002,	/* Set sndcwnd_clamp */
};
3771

3772 3773 3774 3775 3776 3777
struct bpf_perf_event_value {
	__u64 counter;
	__u64 enabled;
	__u64 running;
};

3778 3779 3780 3781 3782
enum {
	BPF_DEVCG_ACC_MKNOD	= (1ULL << 0),
	BPF_DEVCG_ACC_READ	= (1ULL << 1),
	BPF_DEVCG_ACC_WRITE	= (1ULL << 2),
};
3783

3784 3785 3786 3787
enum {
	BPF_DEVCG_DEV_BLOCK	= (1ULL << 0),
	BPF_DEVCG_DEV_CHAR	= (1ULL << 1),
};
3788 3789

struct bpf_cgroup_dev_ctx {
3790 3791
	/* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
	__u32 access_type;
3792 3793 3794 3795
	__u32 major;
	__u32 minor;
};

3796 3797 3798 3799
struct bpf_raw_tracepoint_args {
	__u64 args[0];
};

3800 3801 3802
/* DIRECT:  Skip the FIB rules and go to FIB table associated with device
 * OUTPUT:  Do lookup from egress perspective; default is ingress
 */
3803 3804 3805 3806
enum {
	BPF_FIB_LOOKUP_DIRECT  = (1U << 0),
	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
};
3807

3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819
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 */
};

3820
struct bpf_fib_lookup {
D
David Ahern 已提交
3821 3822 3823 3824
	/* input:  network family for lookup (AF_INET, AF_INET6)
	 * output: network family of egress nexthop
	 */
	__u8	family;
3825 3826 3827 3828 3829 3830 3831 3832

	/* 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;
3833 3834 3835 3836 3837

	/* input: L3 device index for lookup
	 * output: device index from FIB lookup
	 */
	__u32	ifindex;
3838 3839 3840 3841

	union {
		/* inputs to lookup */
		__u8	tos;		/* AF_INET  */
3842
		__be32	flowinfo;	/* AF_INET6, flow_label + priority */
3843

D
David Ahern 已提交
3844 3845
		/* output: metric of fib result (IPv4/IPv6 only) */
		__u32	rt_metric;
3846 3847 3848 3849 3850 3851 3852
	};

	union {
		__be32		ipv4_src;
		__u32		ipv6_src[4];  /* in6_addr; network order */
	};

D
David Ahern 已提交
3853 3854 3855
	/* 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
3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868
	 */
	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 */
};

3869 3870 3871 3872 3873 3874 3875 3876 3877
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 */
};

3878 3879 3880 3881 3882
enum {
	BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG		= (1U << 0),
	BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL		= (1U << 1),
	BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP		= (1U << 2),
};
3883

3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904
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 */
		};
	};
3905
	__u32	flags;
3906
	__be32	flow_label;
3907 3908
};

Y
Yonghong Song 已提交
3909
struct bpf_func_info {
3910
	__u32	insn_off;
Y
Yonghong Song 已提交
3911 3912 3913
	__u32	type_id;
};

M
Martin KaFai Lau 已提交
3914 3915 3916 3917 3918 3919 3920 3921 3922 3923
#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;
};

3924 3925 3926
struct bpf_spin_lock {
	__u32	val;
};
A
Andrey Ignatov 已提交
3927 3928 3929 3930 3931

struct bpf_sysctl {
	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
				 * Allows 1,2,4-byte read, but no write.
				 */
3932 3933 3934
	__u32	file_pos;	/* Sysctl file position to read from, write to.
				 * Allows 1,2,4-byte read an 4-byte write.
				 */
A
Andrey Ignatov 已提交
3935 3936
};

3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947
struct bpf_sockopt {
	__bpf_md_ptr(struct bpf_sock *, sk);
	__bpf_md_ptr(void *, optval);
	__bpf_md_ptr(void *, optval_end);

	__s32	level;
	__s32	optname;
	__s32	optlen;
	__s32	retval;
};

3948 3949 3950 3951
struct bpf_pidns_info {
	__u32 pid;
	__u32 tgid;
};
3952
#endif /* _UAPI__LINUX_BPF_H__ */