bpf.h 28.3 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32
/* 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>
#include <linux/bpf_common.h>

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

/* instruction classes */
#define BPF_ALU64	0x07	/* alu mode in double word width */

/* ld/ldx fields */
#define BPF_DW		0x18	/* double word */
#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

33
/* jmp encodings */
34
#define BPF_JNE		0x50	/* jump != */
35 36
#define BPF_JLT		0xa0	/* LT is unsigned, '<' */
#define BPF_JLE		0xb0	/* LE is unsigned, '<=' */
37 38
#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
39 40
#define BPF_JSLT	0xc0	/* SLT is signed, '<' */
#define BPF_JSLE	0xd0	/* SLE is signed, '<=' */
41 42 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
#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 */
};

71 72 73 74 75 76
/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
struct bpf_lpm_trie_key {
	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */
	__u8	data[0];	/* Arbitrary size */
};

77 78 79 80 81 82 83 84 85 86
/* BPF syscall commands, see bpf(2) man-page for details. */
enum bpf_cmd {
	BPF_MAP_CREATE,
	BPF_MAP_LOOKUP_ELEM,
	BPF_MAP_UPDATE_ELEM,
	BPF_MAP_DELETE_ELEM,
	BPF_MAP_GET_NEXT_KEY,
	BPF_PROG_LOAD,
	BPF_OBJ_PIN,
	BPF_OBJ_GET,
87 88
	BPF_PROG_ATTACH,
	BPF_PROG_DETACH,
89
	BPF_PROG_TEST_RUN,
M
Martin KaFai Lau 已提交
90 91 92 93 94
	BPF_PROG_GET_NEXT_ID,
	BPF_MAP_GET_NEXT_ID,
	BPF_PROG_GET_FD_BY_ID,
	BPF_MAP_GET_FD_BY_ID,
	BPF_OBJ_GET_INFO_BY_FD,
A
Alexei Starovoitov 已提交
95
	BPF_PROG_QUERY,
96 97 98 99 100 101 102 103 104 105 106
};

enum bpf_map_type {
	BPF_MAP_TYPE_UNSPEC,
	BPF_MAP_TYPE_HASH,
	BPF_MAP_TYPE_ARRAY,
	BPF_MAP_TYPE_PROG_ARRAY,
	BPF_MAP_TYPE_PERF_EVENT_ARRAY,
	BPF_MAP_TYPE_PERCPU_HASH,
	BPF_MAP_TYPE_PERCPU_ARRAY,
	BPF_MAP_TYPE_STACK_TRACE,
107
	BPF_MAP_TYPE_CGROUP_ARRAY,
108 109
	BPF_MAP_TYPE_LRU_HASH,
	BPF_MAP_TYPE_LRU_PERCPU_HASH,
110
	BPF_MAP_TYPE_LPM_TRIE,
M
Martin KaFai Lau 已提交
111 112
	BPF_MAP_TYPE_ARRAY_OF_MAPS,
	BPF_MAP_TYPE_HASH_OF_MAPS,
J
John Fastabend 已提交
113
	BPF_MAP_TYPE_DEVMAP,
J
John Fastabend 已提交
114
	BPF_MAP_TYPE_SOCKMAP,
115 116 117 118 119 120 121 122 123
};

enum bpf_prog_type {
	BPF_PROG_TYPE_UNSPEC,
	BPF_PROG_TYPE_SOCKET_FILTER,
	BPF_PROG_TYPE_KPROBE,
	BPF_PROG_TYPE_SCHED_CLS,
	BPF_PROG_TYPE_SCHED_ACT,
	BPF_PROG_TYPE_TRACEPOINT,
124
	BPF_PROG_TYPE_XDP,
125 126 127 128 129 130
	BPF_PROG_TYPE_PERF_EVENT,
	BPF_PROG_TYPE_CGROUP_SKB,
	BPF_PROG_TYPE_CGROUP_SOCK,
	BPF_PROG_TYPE_LWT_IN,
	BPF_PROG_TYPE_LWT_OUT,
	BPF_PROG_TYPE_LWT_XMIT,
131
	BPF_PROG_TYPE_SOCK_OPS,
J
John Fastabend 已提交
132
	BPF_PROG_TYPE_SK_SKB,
133 134
};

135 136 137 138
enum bpf_attach_type {
	BPF_CGROUP_INET_INGRESS,
	BPF_CGROUP_INET_EGRESS,
	BPF_CGROUP_INET_SOCK_CREATE,
139
	BPF_CGROUP_SOCK_OPS,
140 141
	BPF_SK_SKB_STREAM_PARSER,
	BPF_SK_SKB_STREAM_VERDICT,
142 143 144 145 146
	__MAX_BPF_ATTACH_TYPE
};

#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE

A
Alexei Starovoitov 已提交
147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184
/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
 *
 * NONE(default): No further bpf programs allowed in the subtree.
 *
 * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
 * the program in this cgroup yields to sub-cgroup program.
 *
 * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
 * that cgroup program gets run in addition to the program in this cgroup.
 *
 * Only one program is allowed to be attached to a cgroup with
 * NONE or BPF_F_ALLOW_OVERRIDE flag.
 * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
 * release old program and attach the new one. Attach flags has to match.
 *
 * Multiple programs are allowed to be attached to a cgroup with
 * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
 * (those that were attached first, run first)
 * The programs of sub-cgroup are executed first, then programs of
 * this cgroup and then programs of parent cgroup.
 * When children program makes decision (like picking TCP CA or sock bind)
 * parent program has a chance to override it.
 *
 * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
 * A cgroup with NONE doesn't allow any programs in sub-cgroups.
 * Ex1:
 * cgrp1 (MULTI progs A, B) ->
 *    cgrp2 (OVERRIDE prog C) ->
 *      cgrp3 (MULTI prog D) ->
 *        cgrp4 (OVERRIDE prog E) ->
 *          cgrp5 (NONE prog F)
 * the event in cgrp5 triggers execution of F,D,A,B in that order.
 * if prog F is detached, the execution is E,D,A,B
 * if prog F and D are detached, the execution is E,A,B
 * if prog F, E and D are detached, the execution is C,A,B
 *
 * All eligible programs are executed regardless of return code from
 * earlier programs.
185 186
 */
#define BPF_F_ALLOW_OVERRIDE	(1U << 0)
A
Alexei Starovoitov 已提交
187
#define BPF_F_ALLOW_MULTI	(1U << 1)
188

189 190 191 192 193 194 195
/* 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)

196 197 198 199 200 201 202
#define BPF_PSEUDO_MAP_FD	1

/* flags for BPF_MAP_UPDATE_ELEM command */
#define BPF_ANY		0 /* create new element or update existing */
#define BPF_NOEXIST	1 /* create new element if it didn't exist */
#define BPF_EXIST	2 /* update existing element */

203
/* flags for BPF_MAP_CREATE command */
204
#define BPF_F_NO_PREALLOC	(1U << 0)
205 206 207 208 209 210 211
/* Instead of having one common LRU list in the
 * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
 * which can scale and perform better.
 * Note, the LRU nodes (including free nodes) cannot be moved
 * across different LRU lists.
 */
#define BPF_F_NO_COMMON_LRU	(1U << 1)
212 213
/* Specify numa node during map creation */
#define BPF_F_NUMA_NODE		(1U << 2)
214

A
Alexei Starovoitov 已提交
215 216 217
/* flags for BPF_PROG_QUERY */
#define BPF_F_QUERY_EFFECTIVE	(1U << 0)

218 219
#define BPF_OBJ_NAME_LEN 16U

220 221 222 223 224 225
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 */
226 227 228
		__u32	map_flags;	/* BPF_MAP_CREATE related
					 * flags defined above.
					 */
M
Martin KaFai Lau 已提交
229
		__u32	inner_map_fd;	/* fd pointing to the inner map */
230 231 232
		__u32	numa_node;	/* numa node (effective only if
					 * BPF_F_NUMA_NODE is set).
					 */
233
		__u8	map_name[BPF_OBJ_NAME_LEN];
234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254
	};

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

	struct { /* anonymous struct used by BPF_PROG_LOAD command */
		__u32		prog_type;	/* one of enum bpf_prog_type */
		__u32		insn_cnt;
		__aligned_u64	insns;
		__aligned_u64	license;
		__u32		log_level;	/* verbosity level of verifier */
		__u32		log_size;	/* size of user buffer */
		__aligned_u64	log_buf;	/* user supplied buffer */
		__u32		kern_version;	/* checked when prog_type=kprobe */
255
		__u32		prog_flags;
256
		__u8		prog_name[BPF_OBJ_NAME_LEN];
257 258 259 260 261 262
	};

	struct { /* anonymous struct used by BPF_OBJ_* commands */
		__aligned_u64	pathname;
		__u32		bpf_fd;
	};
263 264 265 266 267

	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;
268
		__u32		attach_flags;
269
	};
270 271 272 273 274 275 276 277 278 279 280

	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
		__u32		prog_fd;
		__u32		retval;
		__u32		data_size_in;
		__u32		data_size_out;
		__aligned_u64	data_in;
		__aligned_u64	data_out;
		__u32		repeat;
		__u32		duration;
	} test;
M
Martin KaFai Lau 已提交
281 282 283 284 285 286 287 288 289 290 291 292 293 294 295

	struct { /* anonymous struct used by BPF_*_GET_*_ID */
		union {
			__u32		start_id;
			__u32		prog_id;
			__u32		map_id;
		};
		__u32		next_id;
	};

	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */
		__u32		bpf_fd;
		__u32		info_len;
		__aligned_u64	info;
	} info;
A
Alexei Starovoitov 已提交
296 297 298 299 300 301 302 303 304

	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;
305 306
} __attribute__((aligned(8)));

307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408
/* BPF helper function descriptions:
 *
 * void *bpf_map_lookup_elem(&map, &key)
 *     Return: Map value or NULL
 *
 * int bpf_map_update_elem(&map, &key, &value, flags)
 *     Return: 0 on success or negative error
 *
 * int bpf_map_delete_elem(&map, &key)
 *     Return: 0 on success or negative error
 *
 * int bpf_probe_read(void *dst, int size, void *src)
 *     Return: 0 on success or negative error
 *
 * u64 bpf_ktime_get_ns(void)
 *     Return: current ktime
 *
 * int bpf_trace_printk(const char *fmt, int fmt_size, ...)
 *     Return: length of buffer written or negative error
 *
 * u32 bpf_prandom_u32(void)
 *     Return: random value
 *
 * u32 bpf_raw_smp_processor_id(void)
 *     Return: SMP processor ID
 *
 * int bpf_skb_store_bytes(skb, offset, from, len, flags)
 *     store bytes into packet
 *     @skb: pointer to skb
 *     @offset: offset within packet from skb->mac_header
 *     @from: pointer where to copy bytes from
 *     @len: number of bytes to store into packet
 *     @flags: bit 0 - if true, recompute skb->csum
 *             other bits - reserved
 *     Return: 0 on success or negative error
 *
 * int bpf_l3_csum_replace(skb, offset, from, to, flags)
 *     recompute IP checksum
 *     @skb: pointer to skb
 *     @offset: offset within packet where IP checksum is located
 *     @from: old value of header field
 *     @to: new value of header field
 *     @flags: bits 0-3 - size of header field
 *             other bits - reserved
 *     Return: 0 on success or negative error
 *
 * int bpf_l4_csum_replace(skb, offset, from, to, flags)
 *     recompute TCP/UDP checksum
 *     @skb: pointer to skb
 *     @offset: offset within packet where TCP/UDP checksum is located
 *     @from: old value of header field
 *     @to: new value of header field
 *     @flags: bits 0-3 - size of header field
 *             bit 4 - is pseudo header
 *             other bits - reserved
 *     Return: 0 on success or negative error
 *
 * int bpf_tail_call(ctx, prog_array_map, index)
 *     jump into another BPF program
 *     @ctx: context pointer passed to next program
 *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
 *     @index: index inside array that selects specific program to run
 *     Return: 0 on success or negative error
 *
 * int bpf_clone_redirect(skb, ifindex, flags)
 *     redirect to another netdev
 *     @skb: pointer to skb
 *     @ifindex: ifindex of the net device
 *     @flags: bit 0 - if set, redirect to ingress instead of egress
 *             other bits - reserved
 *     Return: 0 on success or negative error
 *
 * u64 bpf_get_current_pid_tgid(void)
 *     Return: current->tgid << 32 | current->pid
 *
 * u64 bpf_get_current_uid_gid(void)
 *     Return: current_gid << 32 | current_uid
 *
 * int bpf_get_current_comm(char *buf, int size_of_buf)
 *     stores current->comm into buf
 *     Return: 0 on success or negative error
 *
 * u32 bpf_get_cgroup_classid(skb)
 *     retrieve a proc's classid
 *     @skb: pointer to skb
 *     Return: classid if != 0
 *
 * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci)
 *     Return: 0 on success or negative error
 *
 * int bpf_skb_vlan_pop(skb)
 *     Return: 0 on success or negative error
 *
 * int bpf_skb_get_tunnel_key(skb, key, size, flags)
 * int bpf_skb_set_tunnel_key(skb, key, size, flags)
 *     retrieve or populate tunnel metadata
 *     @skb: pointer to skb
 *     @key: pointer to 'struct bpf_tunnel_key'
 *     @size: size of 'struct bpf_tunnel_key'
 *     @flags: room for future extensions
 *     Return: 0 on success or negative error
 *
409 410 411 412 413
 * u64 bpf_perf_event_read(map, flags)
 *     read perf event counter value
 *     @map: pointer to perf_event_array map
 *     @flags: index of event in the map or bitmask flags
 *     Return: value of perf event counter read or error code
414 415 416 417
 *
 * int bpf_redirect(ifindex, flags)
 *     redirect to another netdev
 *     @ifindex: ifindex of the net device
418 419 420 421 422 423 424 425 426 427 428 429 430 431
 *     @flags:
 *	  cls_bpf:
 *          bit 0 - if set, redirect to ingress instead of egress
 *          other bits - reserved
 *	  xdp_bpf:
 *	    all bits - reserved
 *     Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
 *	       xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
 * int bpf_redirect_map(map, key, flags)
 *     redirect to endpoint in map
 *     @map: pointer to dev map
 *     @key: index in map to lookup
 *     @flags: --
 *     Return: XDP_REDIRECT on success or XDP_ABORT on error
432 433 434 435 436 437
 *
 * u32 bpf_get_route_realm(skb)
 *     retrieve a dst's tclassid
 *     @skb: pointer to skb
 *     Return: realm if != 0
 *
438
 * int bpf_perf_event_output(ctx, map, flags, data, size)
439 440 441
 *     output perf raw sample
 *     @ctx: struct pt_regs*
 *     @map: pointer to perf_event_array map
442
 *     @flags: index of event in the map or bitmask flags
443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576
 *     @data: data on stack to be output as raw data
 *     @size: size of data
 *     Return: 0 on success or negative error
 *
 * int bpf_get_stackid(ctx, map, flags)
 *     walk user or kernel stack and return id
 *     @ctx: struct pt_regs*
 *     @map: pointer to stack_trace map
 *     @flags: bits 0-7 - numer of stack frames to skip
 *             bit 8 - collect user stack instead of kernel
 *             bit 9 - compare stacks by hash only
 *             bit 10 - if two different stacks hash into the same stackid
 *                      discard old
 *             other bits - reserved
 *     Return: >= 0 stackid on success or negative error
 *
 * s64 bpf_csum_diff(from, from_size, to, to_size, seed)
 *     calculate csum diff
 *     @from: raw from buffer
 *     @from_size: length of from buffer
 *     @to: raw to buffer
 *     @to_size: length of to buffer
 *     @seed: optional seed
 *     Return: csum result or negative error code
 *
 * int bpf_skb_get_tunnel_opt(skb, opt, size)
 *     retrieve tunnel options metadata
 *     @skb: pointer to skb
 *     @opt: pointer to raw tunnel option data
 *     @size: size of @opt
 *     Return: option size
 *
 * int bpf_skb_set_tunnel_opt(skb, opt, size)
 *     populate tunnel options metadata
 *     @skb: pointer to skb
 *     @opt: pointer to raw tunnel option data
 *     @size: size of @opt
 *     Return: 0 on success or negative error
 *
 * int bpf_skb_change_proto(skb, proto, flags)
 *     Change protocol of the skb. Currently supported is v4 -> v6,
 *     v6 -> v4 transitions. The helper will also resize the skb. eBPF
 *     program is expected to fill the new headers via skb_store_bytes
 *     and lX_csum_replace.
 *     @skb: pointer to skb
 *     @proto: new skb->protocol type
 *     @flags: reserved
 *     Return: 0 on success or negative error
 *
 * int bpf_skb_change_type(skb, type)
 *     Change packet type of skb.
 *     @skb: pointer to skb
 *     @type: new skb->pkt_type type
 *     Return: 0 on success or negative error
 *
 * int bpf_skb_under_cgroup(skb, map, index)
 *     Check cgroup2 membership of skb
 *     @skb: pointer to skb
 *     @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
 *     @index: index of the cgroup in the bpf_map
 *     Return:
 *       == 0 skb failed the cgroup2 descendant test
 *       == 1 skb succeeded the cgroup2 descendant test
 *        < 0 error
 *
 * u32 bpf_get_hash_recalc(skb)
 *     Retrieve and possibly recalculate skb->hash.
 *     @skb: pointer to skb
 *     Return: hash
 *
 * u64 bpf_get_current_task(void)
 *     Returns current task_struct
 *     Return: current
 *
 * int bpf_probe_write_user(void *dst, void *src, int len)
 *     safely attempt to write to a location
 *     @dst: destination address in userspace
 *     @src: source address on stack
 *     @len: number of bytes to copy
 *     Return: 0 on success or negative error
 *
 * int bpf_current_task_under_cgroup(map, index)
 *     Check cgroup2 membership of current task
 *     @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
 *     @index: index of the cgroup in the bpf_map
 *     Return:
 *       == 0 current failed the cgroup2 descendant test
 *       == 1 current succeeded the cgroup2 descendant test
 *        < 0 error
 *
 * int bpf_skb_change_tail(skb, len, flags)
 *     The helper will resize the skb to the given new size, to be used f.e.
 *     with control messages.
 *     @skb: pointer to skb
 *     @len: new skb length
 *     @flags: reserved
 *     Return: 0 on success or negative error
 *
 * int bpf_skb_pull_data(skb, len)
 *     The helper will pull in non-linear data in case the skb is non-linear
 *     and not all of len are part of the linear section. Only needed for
 *     read/write with direct packet access.
 *     @skb: pointer to skb
 *     @len: len to make read/writeable
 *     Return: 0 on success or negative error
 *
 * s64 bpf_csum_update(skb, csum)
 *     Adds csum into skb->csum in case of CHECKSUM_COMPLETE.
 *     @skb: pointer to skb
 *     @csum: csum to add
 *     Return: csum on success or negative error
 *
 * void bpf_set_hash_invalid(skb)
 *     Invalidate current skb->hash.
 *     @skb: pointer to skb
 *
 * int bpf_get_numa_node_id()
 *     Return: Id of current NUMA node.
 *
 * int bpf_skb_change_head()
 *     Grows headroom of skb and adjusts MAC header offset accordingly.
 *     Will extends/reallocae as required automatically.
 *     May change skb data pointer and will thus invalidate any check
 *     performed for direct packet access.
 *     @skb: pointer to skb
 *     @len: length of header to be pushed in front
 *     @flags: Flags (unused for now)
 *     Return: 0 on success or negative error
 *
 * int bpf_xdp_adjust_head(xdp_md, delta)
 *     Adjust the xdp_md.data by delta
 *     @xdp_md: pointer to xdp_md
 *     @delta: An positive/negative integer to be added to xdp_md.data
 *     Return: 0 on success or negative on error
577 578 579 580 581 582 583 584 585 586 587 588
 *
 * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
 *     Copy a NUL terminated string from unsafe address. In case the string
 *     length is smaller than size, the target is not padded with further NUL
 *     bytes. In case the string length is larger than size, just count-1
 *     bytes are copied and the last byte is set to NUL.
 *     @dst: destination address
 *     @size: maximum number of bytes to copy, including the trailing NUL
 *     @unsafe_ptr: unsafe address
 *     Return:
 *       > 0 length of the string including the trailing NUL on success
 *       < 0 error
589
 *
A
Alexander Alemayhu 已提交
590
 * u64 bpf_get_socket_cookie(skb)
591 592 593 594 595 596 597 598
 *     Get the cookie for the socket stored inside sk_buff.
 *     @skb: pointer to skb
 *     Return: 8 Bytes non-decreasing number on success or 0 if the socket
 *     field is missing inside sk_buff
 *
 * u32 bpf_get_socket_uid(skb)
 *     Get the owner uid of the socket stored inside sk_buff.
 *     @skb: pointer to skb
599
 *     Return: uid of the socket owner on success or overflowuid if failed.
600 601 602 603 604
 *
 * u32 bpf_set_hash(skb, hash)
 *     Set full skb->hash.
 *     @skb: pointer to skb
 *     @hash: hash to set
605 606 607 608 609 610 611 612 613 614 615
 *
 * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen)
 *     Calls setsockopt. Not all opts are available, only those with
 *     integer optvals plus TCP_CONGESTION.
 *     Supported levels: SOL_SOCKET and IPROTO_TCP
 *     @bpf_socket: pointer to bpf_socket
 *     @level: SOL_SOCKET or IPROTO_TCP
 *     @optname: option name
 *     @optval: pointer to option value
 *     @optlen: length of optval in byes
 *     Return: 0 or negative error
616 617 618 619 620 621 622 623
 *
 * int bpf_skb_adjust_room(skb, len_diff, mode, flags)
 *     Grow or shrink room in sk_buff.
 *     @skb: pointer to skb
 *     @len_diff: (signed) amount of room to grow/shrink
 *     @mode: operation mode (enum bpf_adj_room_mode)
 *     @flags: reserved for future use
 *     Return: 0 on success or negative error code
J
John Fastabend 已提交
624 625 626 627 628 629 630 631 632
 *
 * int bpf_sk_redirect_map(map, key, flags)
 *     Redirect skb to a sock in map using key as a lookup key for the
 *     sock in map.
 *     @map: pointer to sockmap
 *     @key: key to lookup sock in map
 *     @flags: reserved for future use
 *     Return: SK_REDIRECT
 *
633
 * int bpf_sock_map_update(skops, map, key, flags)
J
John Fastabend 已提交
634 635 636 637
 *	@skops: pointer to bpf_sock_ops
 *	@map: pointer to sockmap to update
 *	@key: key to insert/update sock in map
 *	@flags: same flags as map update elem
638 639 640 641 642 643
 *
 * int bpf_xdp_adjust_meta(xdp_md, delta)
 *     Adjust the xdp_md.data_meta by delta
 *     @xdp_md: pointer to xdp_md
 *     @delta: An positive/negative integer to be added to xdp_md.data_meta
 *     Return: 0 on success or negative on error
644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689
 */
#define __BPF_FUNC_MAPPER(FN)		\
	FN(unspec),			\
	FN(map_lookup_elem),		\
	FN(map_update_elem),		\
	FN(map_delete_elem),		\
	FN(probe_read),			\
	FN(ktime_get_ns),		\
	FN(trace_printk),		\
	FN(get_prandom_u32),		\
	FN(get_smp_processor_id),	\
	FN(skb_store_bytes),		\
	FN(l3_csum_replace),		\
	FN(l4_csum_replace),		\
	FN(tail_call),			\
	FN(clone_redirect),		\
	FN(get_current_pid_tgid),	\
	FN(get_current_uid_gid),	\
	FN(get_current_comm),		\
	FN(get_cgroup_classid),		\
	FN(skb_vlan_push),		\
	FN(skb_vlan_pop),		\
	FN(skb_get_tunnel_key),		\
	FN(skb_set_tunnel_key),		\
	FN(perf_event_read),		\
	FN(redirect),			\
	FN(get_route_realm),		\
	FN(perf_event_output),		\
	FN(skb_load_bytes),		\
	FN(get_stackid),		\
	FN(csum_diff),			\
	FN(skb_get_tunnel_opt),		\
	FN(skb_set_tunnel_opt),		\
	FN(skb_change_proto),		\
	FN(skb_change_type),		\
	FN(skb_under_cgroup),		\
	FN(get_hash_recalc),		\
	FN(get_current_task),		\
	FN(probe_write_user),		\
	FN(current_task_under_cgroup),	\
	FN(skb_change_tail),		\
	FN(skb_pull_data),		\
	FN(csum_update),		\
	FN(set_hash_invalid),		\
	FN(get_numa_node_id),		\
	FN(skb_change_head),		\
690
	FN(xdp_adjust_head),		\
691
	FN(probe_read_str),		\
692
	FN(get_socket_cookie),		\
693
	FN(get_socket_uid),		\
694
	FN(set_hash),			\
695
	FN(setsockopt),			\
696
	FN(skb_adjust_room),		\
J
John Fastabend 已提交
697 698
	FN(redirect_map),		\
	FN(sk_redirect_map),		\
699
	FN(sock_map_update),		\
700 701
	FN(xdp_adjust_meta),		\
	FN(perf_event_read_value),
702

703 704 705
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
 * function eBPF program intends to call
 */
706
#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
707
enum bpf_func_id {
708
	__BPF_FUNC_MAPPER(__BPF_ENUM_FN)
709 710
	__BPF_FUNC_MAX_ID,
};
711
#undef __BPF_ENUM_FN
712 713 714 715 716 717 718 719 720 721 722 723 724 725 726

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

/* BPF_FUNC_skb_store_bytes flags. */
#define BPF_F_RECOMPUTE_CSUM		(1ULL << 0)
#define BPF_F_INVALIDATE_HASH		(1ULL << 1)

/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
 * First 4 bits are for passing the header field size.
 */
#define BPF_F_HDR_FIELD_MASK		0xfULL

/* BPF_FUNC_l4_csum_replace flags. */
#define BPF_F_PSEUDO_HDR		(1ULL << 4)
#define BPF_F_MARK_MANGLED_0		(1ULL << 5)
727
#define BPF_F_MARK_ENFORCE		(1ULL << 6)
728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744

/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
#define BPF_F_INGRESS			(1ULL << 0)

/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
#define BPF_F_TUNINFO_IPV6		(1ULL << 0)

/* BPF_FUNC_get_stackid flags. */
#define BPF_F_SKIP_FIELD_MASK		0xffULL
#define BPF_F_USER_STACK		(1ULL << 8)
#define BPF_F_FAST_STACK_CMP		(1ULL << 9)
#define BPF_F_REUSE_STACKID		(1ULL << 10)

/* BPF_FUNC_skb_set_tunnel_key flags. */
#define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
#define BPF_F_DONT_FRAGMENT		(1ULL << 2)

745
/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
746 747
#define BPF_F_INDEX_MASK		0xffffffffULL
#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
748 749
/* BPF_FUNC_perf_event_output for sk_buff input context. */
#define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
750

751 752
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
753
	BPF_ADJ_ROOM_NET,
754 755
};

756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
/* user accessible mirror of in-kernel sk_buff.
 * new fields can only be added to the end of this structure
 */
struct __sk_buff {
	__u32 len;
	__u32 pkt_type;
	__u32 mark;
	__u32 queue_mapping;
	__u32 protocol;
	__u32 vlan_present;
	__u32 vlan_tci;
	__u32 vlan_proto;
	__u32 priority;
	__u32 ingress_ifindex;
	__u32 ifindex;
	__u32 tc_index;
	__u32 cb[5];
	__u32 hash;
	__u32 tc_classid;
	__u32 data;
	__u32 data_end;
777
	__u32 napi_id;
J
John Fastabend 已提交
778

779
	/* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
J
John Fastabend 已提交
780 781 782 783 784 785 786
	__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 */
787 788 789
	/* ... here. */

	__u32 data_meta;
790 791 792 793 794 795 796 797 798 799 800 801 802 803
};

struct bpf_tunnel_key {
	__u32 tunnel_id;
	union {
		__u32 remote_ipv4;
		__u32 remote_ipv6[4];
	};
	__u8 tunnel_tos;
	__u8 tunnel_ttl;
	__u16 tunnel_ext;
	__u32 tunnel_label;
};

804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824
/* Generic BPF return codes which all BPF program types may support.
 * The values are binary compatible with their TC_ACT_* counter-part to
 * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
 * programs.
 *
 * XDP is handled seprately, see XDP_*.
 */
enum bpf_ret_code {
	BPF_OK = 0,
	/* 1 reserved */
	BPF_DROP = 2,
	/* 3-6 reserved */
	BPF_REDIRECT = 7,
	/* >127 are reserved for prog type specific return codes */
};

struct bpf_sock {
	__u32 bound_dev_if;
	__u32 family;
	__u32 type;
	__u32 protocol;
825 826
	__u32 mark;
	__u32 priority;
827 828 829 830
};

#define XDP_PACKET_HEADROOM 256

831 832
/* User return codes for XDP prog type.
 * A valid XDP program must return one of these defined values. All other
833 834
 * return codes are reserved for future use. Unknown return codes will
 * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
835 836 837 838 839 840
 */
enum xdp_action {
	XDP_ABORTED = 0,
	XDP_DROP,
	XDP_PASS,
	XDP_TX,
841
	XDP_REDIRECT,
842 843 844 845 846 847 848 849
};

/* 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;
850
	__u32 data_meta;
851 852
};

J
John Fastabend 已提交
853 854 855 856 857 858
enum sk_action {
	SK_ABORTED = 0,
	SK_DROP,
	SK_REDIRECT,
};

M
Martin KaFai Lau 已提交
859 860 861 862 863 864 865 866 867 868
#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;
869 870 871 872 873
	__u64 load_time;	/* ns since boottime */
	__u32 created_by_uid;
	__u32 nr_map_ids;
	__aligned_u64 map_ids;
	__u8  name[BPF_OBJ_NAME_LEN];
M
Martin KaFai Lau 已提交
874 875 876 877 878 879 880 881 882
} __attribute__((aligned(8)));

struct bpf_map_info {
	__u32 type;
	__u32 id;
	__u32 key_size;
	__u32 value_size;
	__u32 max_entries;
	__u32 map_flags;
883
	__u8  name[BPF_OBJ_NAME_LEN];
M
Martin KaFai Lau 已提交
884 885
} __attribute__((aligned(8)));

886 887
/* User bpf_sock_ops struct to access socket values and specify request ops
 * and their replies.
888 889
 * 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).
890 891 892 893 894 895 896 897 898
 * New fields can only be added at the end of this structure
 */
struct bpf_sock_ops {
	__u32 op;
	union {
		__u32 reply;
		__u32 replylong[4];
	};
	__u32 family;
899 900 901 902 903 904
	__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 */
905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937
};

/* List of known BPF sock_ops operators.
 * New entries can only be added at the end
 */
enum {
	BPF_SOCK_OPS_VOID,
	BPF_SOCK_OPS_TIMEOUT_INIT,	/* Should return SYN-RTO value to use or
					 * -1 if default value should be used
					 */
	BPF_SOCK_OPS_RWND_INIT,		/* Should return initial advertized
					 * window (in packets) or -1 if default
					 * value should be used
					 */
	BPF_SOCK_OPS_TCP_CONNECT_CB,	/* Calls BPF program right before an
					 * active connection is initialized
					 */
	BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB,	/* Calls BPF program when an
						 * active connection is
						 * established
						 */
	BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,	/* Calls BPF program when a
						 * passive connection is
						 * established
						 */
	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
					 * needs ECN
					 */
};

#define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
#define TCP_BPF_SNDCWND_CLAMP	1002	/* Set sndcwnd_clamp */

938
#endif /* _UAPI__LINUX_BPF_H__ */