Andrey Ignatovbpf: Sync bpf.h to tools/539764d8 years agoHistory
2781 lines · 104.9 KB · C
RawDownload
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note *//* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */#ifndef _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 (64-bit) */#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 /* jmp encodings */#define BPF_JNE		0x50	/* jump != */#define BPF_JLT		0xa0	/* LT is unsigned, '<' */#define BPF_JLE		0xb0	/* LE is unsigned, '<=' */#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */#define BPF_JSLT	0xc0	/* SLT is signed, '<' */#define BPF_JSLE	0xd0	/* SLE is signed, '<=' */#define BPF_CALL	0x80	/* function call */#define BPF_EXIT	0x90	/* function return */ /* Register numbers */enum {	BPF_REG_0 = 0,	BPF_REG_1,	BPF_REG_2,	BPF_REG_3,	BPF_REG_4,	BPF_REG_5,	BPF_REG_6,	BPF_REG_7,	BPF_REG_8,	BPF_REG_9,	BPF_REG_10,	__MAX_BPF_REG,}; /* BPF has 10 general purpose 64-bit registers and stack frame. */#define MAX_BPF_REG	__MAX_BPF_REG struct bpf_insn {	__u8	code;		/* opcode */	__u8	dst_reg:4;	/* dest register */	__u8	src_reg:4;	/* source register */	__s16	off;		/* signed offset */	__s32	imm;		/* signed immediate constant */}; /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */struct bpf_lpm_trie_key {	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */	__u8	data[0];	/* Arbitrary size */}; struct bpf_cgroup_storage_key {	__u64	cgroup_inode_id;	/* cgroup inode id */	__u32	attach_type;		/* program attach type */}; /* BPF syscall commands, see bpf(2) man-page for details. */enum bpf_cmd {	BPF_MAP_CREATE,	BPF_MAP_LOOKUP_ELEM,	BPF_MAP_UPDATE_ELEM,	BPF_MAP_DELETE_ELEM,	BPF_MAP_GET_NEXT_KEY,	BPF_PROG_LOAD,	BPF_OBJ_PIN,	BPF_OBJ_GET,	BPF_PROG_ATTACH,	BPF_PROG_DETACH,	BPF_PROG_TEST_RUN,	BPF_PROG_GET_NEXT_ID,	BPF_MAP_GET_NEXT_ID,	BPF_PROG_GET_FD_BY_ID,	BPF_MAP_GET_FD_BY_ID,	BPF_OBJ_GET_INFO_BY_FD,	BPF_PROG_QUERY,	BPF_RAW_TRACEPOINT_OPEN,	BPF_BTF_LOAD,	BPF_BTF_GET_FD_BY_ID,	BPF_TASK_FD_QUERY,}; enum bpf_map_type {	BPF_MAP_TYPE_UNSPEC,	BPF_MAP_TYPE_HASH,	BPF_MAP_TYPE_ARRAY,	BPF_MAP_TYPE_PROG_ARRAY,	BPF_MAP_TYPE_PERF_EVENT_ARRAY,	BPF_MAP_TYPE_PERCPU_HASH,	BPF_MAP_TYPE_PERCPU_ARRAY,	BPF_MAP_TYPE_STACK_TRACE,	BPF_MAP_TYPE_CGROUP_ARRAY,	BPF_MAP_TYPE_LRU_HASH,	BPF_MAP_TYPE_LRU_PERCPU_HASH,	BPF_MAP_TYPE_LPM_TRIE,	BPF_MAP_TYPE_ARRAY_OF_MAPS,	BPF_MAP_TYPE_HASH_OF_MAPS,	BPF_MAP_TYPE_DEVMAP,	BPF_MAP_TYPE_SOCKMAP,	BPF_MAP_TYPE_CPUMAP,	BPF_MAP_TYPE_XSKMAP,	BPF_MAP_TYPE_SOCKHASH,	BPF_MAP_TYPE_CGROUP_STORAGE,	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,}; enum bpf_prog_type {	BPF_PROG_TYPE_UNSPEC,	BPF_PROG_TYPE_SOCKET_FILTER,	BPF_PROG_TYPE_KPROBE,	BPF_PROG_TYPE_SCHED_CLS,	BPF_PROG_TYPE_SCHED_ACT,	BPF_PROG_TYPE_TRACEPOINT,	BPF_PROG_TYPE_XDP,	BPF_PROG_TYPE_PERF_EVENT,	BPF_PROG_TYPE_CGROUP_SKB,	BPF_PROG_TYPE_CGROUP_SOCK,	BPF_PROG_TYPE_LWT_IN,	BPF_PROG_TYPE_LWT_OUT,	BPF_PROG_TYPE_LWT_XMIT,	BPF_PROG_TYPE_SOCK_OPS,	BPF_PROG_TYPE_SK_SKB,	BPF_PROG_TYPE_CGROUP_DEVICE,	BPF_PROG_TYPE_SK_MSG,	BPF_PROG_TYPE_RAW_TRACEPOINT,	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,	BPF_PROG_TYPE_LWT_SEG6LOCAL,	BPF_PROG_TYPE_LIRC_MODE2,	BPF_PROG_TYPE_SK_REUSEPORT,}; enum bpf_attach_type {	BPF_CGROUP_INET_INGRESS,	BPF_CGROUP_INET_EGRESS,	BPF_CGROUP_INET_SOCK_CREATE,	BPF_CGROUP_SOCK_OPS,	BPF_SK_SKB_STREAM_PARSER,	BPF_SK_SKB_STREAM_VERDICT,	BPF_CGROUP_DEVICE,	BPF_SK_MSG_VERDICT,	BPF_CGROUP_INET4_BIND,	BPF_CGROUP_INET6_BIND,	BPF_CGROUP_INET4_CONNECT,	BPF_CGROUP_INET6_CONNECT,	BPF_CGROUP_INET4_POST_BIND,	BPF_CGROUP_INET6_POST_BIND,	BPF_CGROUP_UDP4_SENDMSG,	BPF_CGROUP_UDP6_SENDMSG,	BPF_LIRC_MODE2,	__MAX_BPF_ATTACH_TYPE}; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command * * NONE(default): No further bpf programs allowed in the subtree. * * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, * the program in this cgroup yields to sub-cgroup program. * * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, * that cgroup program gets run in addition to the program in this cgroup. * * Only one program is allowed to be attached to a cgroup with * NONE or BPF_F_ALLOW_OVERRIDE flag. * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will * release old program and attach the new one. Attach flags has to match. * * Multiple programs are allowed to be attached to a cgroup with * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order * (those that were attached first, run first) * The programs of sub-cgroup are executed first, then programs of * this cgroup and then programs of parent cgroup. * When children program makes decision (like picking TCP CA or sock bind) * parent program has a chance to override it. * * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. * A cgroup with NONE doesn't allow any programs in sub-cgroups. * Ex1: * cgrp1 (MULTI progs A, B) -> *    cgrp2 (OVERRIDE prog C) -> *      cgrp3 (MULTI prog D) -> *        cgrp4 (OVERRIDE prog E) -> *          cgrp5 (NONE prog F) * the event in cgrp5 triggers execution of F,D,A,B in that order. * if prog F is detached, the execution is E,D,A,B * if prog F and D are detached, the execution is E,A,B * if prog F, E and D are detached, the execution is C,A,B * * All eligible programs are executed regardless of return code from * earlier programs. */#define BPF_F_ALLOW_OVERRIDE	(1U << 0)#define BPF_F_ALLOW_MULTI	(1U << 1) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, * and NET_IP_ALIGN defined to 2. */#define BPF_F_STRICT_ALIGNMENT	(1U << 0) /* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */#define BPF_PSEUDO_MAP_FD	1 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative * offset to another bpf function */#define BPF_PSEUDO_CALL		1 /* flags for BPF_MAP_UPDATE_ELEM command */#define BPF_ANY		0 /* create new element or update existing */#define BPF_NOEXIST	1 /* create new element if it didn't exist */#define BPF_EXIST	2 /* update existing element */ /* flags for BPF_MAP_CREATE command */#define BPF_F_NO_PREALLOC	(1U << 0)/* Instead of having one common LRU list in the * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list * which can scale and perform better. * Note, the LRU nodes (including free nodes) cannot be moved * across different LRU lists. */#define BPF_F_NO_COMMON_LRU	(1U << 1)/* Specify numa node during map creation */#define BPF_F_NUMA_NODE		(1U << 2) /* flags for BPF_PROG_QUERY */#define BPF_F_QUERY_EFFECTIVE	(1U << 0) #define BPF_OBJ_NAME_LEN 16U /* Flags for accessing BPF object */#define BPF_F_RDONLY		(1U << 3)#define BPF_F_WRONLY		(1U << 4) /* Flag for stack_map, store build_id+offset instead of pointer */#define BPF_F_STACK_BUILD_ID	(1U << 5) enum bpf_stack_build_id_status {	/* user space need an empty entry to identify end of a trace */	BPF_STACK_BUILD_ID_EMPTY = 0,	/* with valid build_id and offset */	BPF_STACK_BUILD_ID_VALID = 1,	/* couldn't get build_id, fallback to ip */	BPF_STACK_BUILD_ID_IP = 2,}; #define BPF_BUILD_ID_SIZE 20struct bpf_stack_build_id {	__s32		status;	unsigned char	build_id[BPF_BUILD_ID_SIZE];	union {		__u64	offset;		__u64	ip;	};}; union bpf_attr {	struct { /* anonymous struct used by BPF_MAP_CREATE command */		__u32	map_type;	/* one of enum bpf_map_type */		__u32	key_size;	/* size of key in bytes */		__u32	value_size;	/* size of value in bytes */		__u32	max_entries;	/* max number of entries in a map */		__u32	map_flags;	/* BPF_MAP_CREATE related					 * flags defined above.					 */		__u32	inner_map_fd;	/* fd pointing to the inner map */		__u32	numa_node;	/* numa node (effective only if					 * BPF_F_NUMA_NODE is set).					 */		char	map_name[BPF_OBJ_NAME_LEN];		__u32	map_ifindex;	/* ifindex of netdev to create on */		__u32	btf_fd;		/* fd pointing to a BTF type data */		__u32	btf_key_type_id;	/* BTF type_id of the key */		__u32	btf_value_type_id;	/* BTF type_id of the value */	}; 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */		__u32		map_fd;		__aligned_u64	key;		union {			__aligned_u64 value;			__aligned_u64 next_key;		};		__u64		flags;	}; 	struct { /* anonymous struct used by BPF_PROG_LOAD command */		__u32		prog_type;	/* one of enum bpf_prog_type */		__u32		insn_cnt;		__aligned_u64	insns;		__aligned_u64	license;		__u32		log_level;	/* verbosity level of verifier */		__u32		log_size;	/* size of user buffer */		__aligned_u64	log_buf;	/* user supplied buffer */		__u32		kern_version;	/* checked when prog_type=kprobe */		__u32		prog_flags;		char		prog_name[BPF_OBJ_NAME_LEN];		__u32		prog_ifindex;	/* ifindex of netdev to prep for */		/* For some prog types expected attach type must be known at		 * load time to verify attach type specific parts of prog		 * (context accesses, allowed helpers, etc).		 */		__u32		expected_attach_type;	}; 	struct { /* anonymous struct used by BPF_OBJ_* commands */		__aligned_u64	pathname;		__u32		bpf_fd;		__u32		file_flags;	}; 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */		__u32		target_fd;	/* container object to attach to */		__u32		attach_bpf_fd;	/* eBPF program to attach */		__u32		attach_type;		__u32		attach_flags;	}; 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */		__u32		prog_fd;		__u32		retval;		__u32		data_size_in;		__u32		data_size_out;		__aligned_u64	data_in;		__aligned_u64	data_out;		__u32		repeat;		__u32		duration;	} test; 	struct { /* anonymous struct used by BPF_*_GET_*_ID */		union {			__u32		start_id;			__u32		prog_id;			__u32		map_id;			__u32		btf_id;		};		__u32		next_id;		__u32		open_flags;	}; 	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */		__u32		bpf_fd;		__u32		info_len;		__aligned_u64	info;	} info; 	struct { /* anonymous struct used by BPF_PROG_QUERY command */		__u32		target_fd;	/* container object to query */		__u32		attach_type;		__u32		query_flags;		__u32		attach_flags;		__aligned_u64	prog_ids;		__u32		prog_cnt;	} query; 	struct {		__u64 name;		__u32 prog_fd;	} raw_tracepoint; 	struct { /* anonymous struct for BPF_BTF_LOAD */		__aligned_u64	btf;		__aligned_u64	btf_log_buf;		__u32		btf_size;		__u32		btf_log_size;		__u32		btf_log_level;	}; 	struct {		__u32		pid;		/* input: pid */		__u32		fd;		/* input: fd */		__u32		flags;		/* input: flags */		__u32		buf_len;	/* input/output: buf len */		__aligned_u64	buf;		/* input/output:						 *   tp_name for tracepoint						 *   symbol for kprobe						 *   filename for uprobe						 */		__u32		prog_id;	/* output: prod_id */		__u32		fd_type;	/* output: BPF_FD_TYPE_* */		__u64		probe_offset;	/* output: probe_offset */		__u64		probe_addr;	/* output: probe_addr */	} task_fd_query;} __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF * developers about the multiple available eBPF helper functions. It can be * parsed and used to produce a manual page. The workflow is the following, * and requires the rst2man utility: * *     $ ./scripts/bpf_helpers_doc.py \ *             --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst *     $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 *     $ man /tmp/bpf-helpers.7 * * Note that in order to produce this external documentation, some RST * formatting is used in the descriptions to get "bold" and "italics" in * manual pages. Also note that the few trailing white spaces are * intentional, removing them would break paragraphs for rst2man. * * Start of BPF helper function descriptions: * * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) * 	Description * 		Perform a lookup in *map* for an entry associated to *key*. * 	Return * 		Map value associated to *key*, or **NULL** if no entry was * 		found. * * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) * 	Description * 		Add or update the value of the entry associated to *key* in * 		*map* with *value*. *flags* is one of: * * 		**BPF_NOEXIST** * 			The entry for *key* must not exist in the map. * 		**BPF_EXIST** * 			The entry for *key* must already exist in the map. * 		**BPF_ANY** * 			No condition on the existence of the entry for *key*. * * 		Flag value **BPF_NOEXIST** cannot be used for maps of types * 		**BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY**  (all * 		elements always exist), the helper would return an error. * 	Return * 		0 on success, or a negative error in case of failure. * * int bpf_map_delete_elem(struct bpf_map *map, const void *key) * 	Description * 		Delete entry with *key* from *map*. * 	Return * 		0 on success, or a negative error in case of failure. * * int bpf_probe_read(void *dst, u32 size, const void *src) * 	Description * 		For tracing programs, safely attempt to read *size* bytes from * 		address *src* and store the data in *dst*. * 	Return * 		0 on success, or a negative error in case of failure. * * u64 bpf_ktime_get_ns(void) * 	Description * 		Return the time elapsed since system boot, in nanoseconds. * 	Return * 		Current *ktime*. * * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) * 	Description * 		This helper is a "printk()-like" facility for debugging. It * 		prints a message defined by format *fmt* (of size *fmt_size*) * 		to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if * 		available. It can take up to three additional **u64** * 		arguments (as an eBPF helpers, the total number of arguments is * 		limited to five). * * 		Each time the helper is called, it appends a line to the trace. * 		The format of the trace is customizable, and the exact output * 		one will get depends on the options set in * 		*\/sys/kernel/debug/tracing/trace_options* (see also the * 		*README* file under the same directory). However, it usually * 		defaults to something like: * * 		:: * * 			telnet-470   [001] .N.. 419421.045894: 0x00000001: <formatted msg> * * 		In the above: * * 			* ``telnet`` is the name of the current task. * 			* ``470`` is the PID of the current task. * 			* ``001`` is the CPU number on which the task is * 			  running.

Lines 1–500 of 2781.

Keyboard shortcuts

General

Show keyboard shortcuts
?
Focus the current search
/

Issues and pull requests

Open filters
f

Issues, pull requests and Inbox

Select next item
j↓
Select previous item
k↑
Open selected item
Enter
Dismiss filters or clear selection
Esc

Repository code

Go to file
t