alistair23-linux/include/uapi/linux/bpf.h

/* 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 */
};

/* 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,
};

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,
};

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,
};

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,
	__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 20
struct bpf_stack_build_id {
	__s32		status;
	unsigned char	build_id[BPF_BUILD_ID_SIZE];
	union {
		__u64	offset;
		__u64	ip;
	};
};

union bpf_attr {
	struct { /* anonymous struct used by BPF_MAP_CREATE command */
		__u32	map_type;	/* one of enum bpf_map_type */
		__u32	key_size;	/* size of key in bytes */
		__u32	value_size;	/* size of value in bytes */
		__u32	max_entries;	/* max number of entries in a map */
		__u32	map_flags;	/* BPF_MAP_CREATE related
					 * flags defined above.
					 */
		__u32	inner_map_fd;	/* fd pointing to the inner map */
		__u32	numa_node;	/* numa node (effective only if
					 * BPF_F_NUMA_NODE is set).
					 */
		char	map_name[BPF_OBJ_NAME_LEN];
		__u32	map_ifindex;	/* ifindex of netdev to create on */
		__u32	btf_fd;		/* fd pointing to a BTF type data */
		__u32	btf_key_id;	/* BTF type_id of the key */
		__u32	btf_value_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		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;
	};
} __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.
 * 			* 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.
 *
 * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
 * 	Description
 * 		Store *len* bytes from address *from* into the packet
 * 		associated to *skb*, at *offset*. *flags* are a combination of
 * 		**BPF_F_RECOMPUTE_CSUM** (automatically recompute the
 * 		checksum for the packet after storing the bytes) and
 * 		**BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\
 * 		**->swhash** and *skb*\ **->l4hash** to 0).
 *
 * 		A call to this helper is susceptible to change the underlaying
 * 		packet buffer. Therefore, at load time, all checks on pointers
 * 		previously done by the verifier are invalidated and must be
 * 		performed again, if the helper is used in combination with
 * 		direct packet access.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size)
 * 	Description
 * 		Recompute the layer 3 (e.g. IP) checksum for the packet
 * 		associated to *skb*. Computation is incremental, so the helper
 * 		must know the former value of the header field that was
 * 		modified (*from*), the new value of this field (*to*), and the
 * 		number of bytes (2 or 4) for this field, stored in *size*.
 * 		Alternatively, it is possible to store the difference between
 * 		the previous and the new values of the header field in *to*, by
 * 		setting *from* and *size* to 0. For both methods, *offset*
 * 		indicates the location of the IP checksum within the packet.
 *
 * 		This helper works in combination with **bpf_csum_diff**\ (),
 * 		which does not update the checksum in-place, but offers more
 * 		flexibility and can handle sizes larger than 2 or 4 for the
 * 		checksum to update.
 *
 * 		A call to this helper is susceptible to change the underlaying
 * 		packet buffer. Therefore, at load time, all checks on pointers
 * 		previously done by the verifier are invalidated and must be
 * 		performed again, if the helper is used in combination with
 * 		direct packet access.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags)
 * 	Description
 * 		Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the
 * 		packet associated to *skb*. Computation is incremental, so the
 * 		helper must know the former value of the header field that was
 * 		modified (*from*), the new value of this field (*to*), and the
 * 		number of bytes (2 or 4) for this field, stored on the lowest
 * 		four bits of *flags*. Alternatively, it is possible to store
 * 		the difference between the previous and the new values of the
 * 		header field in *to*, by setting *from* and the four lowest
 * 		bits of *flags* to 0. For both methods, *offset* indicates the
 * 		location of the IP checksum within the packet. In addition to
 * 		the size of the field, *flags* can be added (bitwise OR) actual
 * 		flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left
 * 		untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and
 * 		for updates resulting in a null checksum the value is set to
 * 		**CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates
 * 		the checksum is to be computed against a pseudo-header.
 *
 * 		This helper works in combination with **bpf_csum_diff**\ (),
 * 		which does not update the checksum in-place, but offers more
 * 		flexibility and can handle sizes larger than 2 or 4 for the
 * 		checksum to update.
 *
 * 		A call to this helper is susceptible to change the underlaying
 * 		packet buffer. Therefore, at load time, all checks on pointers
 * 		previously done by the verifier are invalidated and must be
 * 		performed again, if the helper is used in combination with
 * 		direct packet access.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index)
 * 	Description
 * 		This special helper is used to trigger a "tail call", or in
 * 		other words, to jump into another eBPF program. The same stack
 * 		frame is used (but values on stack and in registers for the
 * 		caller are not accessible to the callee). This mechanism allows
 * 		for program chaining, either for raising the maximum number of
 * 		available eBPF instructions, or to execute given programs in
 * 		conditional blocks. For security reasons, there is an upper
 * 		limit to the number of successive tail calls that can be
 * 		performed.
 *
 * 		Upon call of this helper, the program attempts to jump into a
 * 		program referenced at index *index* in *prog_array_map*, a
 * 		special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes
 * 		*ctx*, a pointer to the context.
 *
 * 		If the call succeeds, the kernel immediately runs the first
 * 		instruction of the new program. This is not a function call,
 * 		and it never returns to the previous program. If the call
 * 		fails, then the helper has no effect, and the caller continues
 * 		to run its subsequent instructions. A call can fail if the
 * 		destination program for the jump does not exist (i.e. *index*
 * 		is superior to the number of entries in *prog_array_map*), or
 * 		if the maximum number of tail calls has been reached for this
 * 		chain of programs. This limit is defined in the kernel by the
 * 		macro **MAX_TAIL_CALL_CNT** (not accessible to user space),
 * 		which is currently set to 32.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags)
 * 	Description
 * 		Clone and redirect the packet associated to *skb* to another
 * 		net device of index *ifindex*. Both ingress and egress
 * 		interfaces can be used for redirection. The **BPF_F_INGRESS**
 * 		value in *flags* is used to make the distinction (ingress path
 * 		is selected if the flag is present, egress path otherwise).
 * 		This is the only flag supported for now.
 *
 * 		In comparison with **bpf_redirect**\ () helper,
 * 		**bpf_clone_redirect**\ () has the associated cost of
 * 		duplicating the packet buffer, but this can be executed out of
 * 		the eBPF program. Conversely, **bpf_redirect**\ () is more
 * 		efficient, but it is handled through an action code where the
 * 		redirection happens only after the eBPF program has returned.
 *
 * 		A call to this helper is susceptible to change the underlaying
 * 		packet buffer. Therefore, at load time, all checks on pointers
 * 		previously done by the verifier are invalidated and must be
 * 		performed again, if the helper is used in combination with
 * 		direct packet access.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * u64 bpf_get_current_pid_tgid(void)
 * 	Return
 * 		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*.
 *
 * int bpf_get_current_comm(char *buf, u32 size_of_buf)
 * 	Description
 * 		Copy the **comm** attribute of the current task into *buf* of
 * 		*size_of_buf*. The **comm** attribute contains the name of
 * 		the executable (excluding the path) for the current task. The
 * 		*size_of_buf* must be strictly positive. On success, the
 * 		helper makes sure that the *buf* is NUL-terminated. On failure,
 * 		it is filled with zeroes.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 * 	Description
 * 		Push a *vlan_tci* (VLAN tag control information) of protocol
 * 		*vlan_proto* to the packet associated to *skb*, then update
 * 		the checksum. Note that if *vlan_proto* is different from
 * 		**ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to
 * 		be **ETH_P_8021Q**.
 *
 * 		A call to this helper is susceptible to change the underlaying
 * 		packet buffer. Therefore, at load time, all checks on pointers
 * 		previously done by the verifier are invalidated and must be
 * 		performed again, if the helper is used in combination with
 * 		direct packet access.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_skb_vlan_pop(struct sk_buff *skb)
 * 	Description
 * 		Pop a VLAN header from the packet associated to *skb*.
 *
 * 		A call to this helper is susceptible to change the underlaying
 * 		packet buffer. Therefore, at load time, all checks on pointers
 * 		previously done by the verifier are invalidated and must be
 * 		performed again, if the helper is used in combination with
 * 		direct packet access.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
 * 	Description
 * 		Get tunnel metadata. This helper takes a pointer *key* to an
 * 		empty **struct bpf_tunnel_key** of **size**, that will be
 * 		filled with tunnel metadata for the packet associated to *skb*.
 * 		The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which
 * 		indicates that the tunnel is based on IPv6 protocol instead of
 * 		IPv4.
 *
 * 		The **struct bpf_tunnel_key** is an object that generalizes the
 * 		principal parameters used by various tunneling protocols into a
 * 		single struct. This way, it can be used to easily make a
 * 		decision based on the contents of the encapsulation header,
 * 		"summarized" in this struct. In particular, it holds the IP
 * 		address of the remote end (IPv4 or IPv6, depending on the case)
 * 		in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also,
 * 		this struct exposes the *key*\ **->tunnel_id**, which is
 * 		generally mapped to a VNI (Virtual Network Identifier), making
 * 		it programmable together with the **bpf_skb_set_tunnel_key**\
 * 		() helper.
 *
 * 		Let's imagine that the following code is part of a program
 * 		attached to the TC ingress interface, on one end of a GRE
 * 		tunnel, and is supposed to filter out all messages coming from
 * 		remote ends with IPv4 address other than 10.0.0.1:
 *
 * 		::
 *
 * 			int ret;
 * 			struct bpf_tunnel_key key = {};
 * 			
 * 			ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
 * 			if (ret < 0)
 * 				return TC_ACT_SHOT;	// drop packet
 * 			
 * 			if (key.remote_ipv4 != 0x0a000001)
 * 				return TC_ACT_SHOT;	// drop packet
 * 			
 * 			return TC_ACT_OK;		// accept packet
 *
 * 		This interface can also be used with all encapsulation devices
 * 		that can operate in "collect metadata" mode: instead of having
 * 		one network device per specific configuration, the "collect
 * 		metadata" mode only requires a single device where the
 * 		configuration can be extracted from this helper.
 *
 * 		This can be used together with various tunnels such as VXLan,
 * 		Geneve, GRE or IP in IP (IPIP).
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags)
 * 	Description
 * 		Populate tunnel metadata for packet associated to *skb.* The
 * 		tunnel metadata is set to the contents of *key*, of *size*. The
 * 		*flags* can be set to a combination of the following values:
 *
 * 		**BPF_F_TUNINFO_IPV6**
 * 			Indicate that the tunnel is based on IPv6 protocol
 * 			instead of IPv4.
 * 		**BPF_F_ZERO_CSUM_TX**
 * 			For IPv4 packets, add a flag to tunnel metadata
 * 			indicating that checksum computation should be skipped
 * 			and checksum set to zeroes.
 * 		**BPF_F_DONT_FRAGMENT**
 * 			Add a flag to tunnel metadata indicating that the
 * 			packet should not be fragmented.
 * 		**BPF_F_SEQ_NUMBER**
 * 			Add a flag to tunnel metadata indicating that a
 * 			sequence number should be added to tunnel header before
 * 			sending the packet. This flag was added for GRE
 * 			encapsulation, but might be used with other protocols
 * 			as well in the future.
 *
 * 		Here is a typical usage on the transmit path:
 *
 * 		::
 *
 * 			struct bpf_tunnel_key key;
 * 			     populate key ...
 * 			bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
 * 			bpf_clone_redirect(skb, vxlan_dev_ifindex, 0);
 *
 * 		See also the description of the **bpf_skb_get_tunnel_key**\ ()
 * 		helper for additional information.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_redirect(u32 ifindex, u64 flags)
 * 	Description
 * 		Redirect the packet to another net device of index *ifindex*.
 * 		This helper is somewhat similar to **bpf_clone_redirect**\
 * 		(), except that the packet is not cloned, which provides
 * 		increased performance.
 *
 * 		Except for XDP, both ingress and egress interfaces can be used
 * 		for redirection. The **BPF_F_INGRESS** value in *flags* is used
 * 		to make the distinction (ingress path is selected if the flag
 * 		is present, egress path otherwise). Currently, XDP only
 * 		supports redirection to the egress interface, and accepts no
 * 		flag at all.
 *
 * 		The same effect can be attained with the more generic
 * 		**bpf_redirect_map**\ (), which requires specific maps to be
 * 		used but offers better performance.
 * 	Return
 * 		For XDP, the helper returns **XDP_REDIRECT** on success or
 * 		**XDP_ABORTED** on error. For other program types, the values
 * 		are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on
 * 		error.
 *
 * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
 * 	Description
 * 		Write raw *data* blob into a special BPF perf event held by
 * 		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
 * 		event must have the following attributes: **PERF_SAMPLE_RAW**
 * 		as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
 * 		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
 *
 * 		The *flags* are used to indicate the index in *map* for which
 * 		the value must be put, masked with **BPF_F_INDEX_MASK**.
 * 		Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
 * 		to indicate that the index of the current CPU core should be
 * 		used.
 *
 * 		The value to write, of *size*, is passed through eBPF stack and
 * 		pointed by *data*.
 *
 * 		The context of the program *ctx* needs also be passed to the
 * 		helper.
 *
 * 		On user space, a program willing to read the values needs to
 * 		call **perf_event_open**\ () on the perf event (either for
 * 		one or for all CPUs) and to store the file descriptor into the
 * 		*map*. This must be done before the eBPF program can send data
 * 		into it. An example is available in file
 * 		*samples/bpf/trace_output_user.c* in the Linux kernel source
 * 		tree (the eBPF program counterpart is in
 * 		*samples/bpf/trace_output_kern.c*).
 *
 * 		**bpf_perf_event_output**\ () achieves better performance
 * 		than **bpf_trace_printk**\ () for sharing data with user
 * 		space, and is much better suitable for streaming data from eBPF
 * 		programs.
 *
 * 		Note that this helper is not restricted to tracing use cases
 * 		and can be used with programs attached to TC or XDP as well,
 * 		where it allows for passing data to user space listeners. Data
 * 		can be:
 *
 * 		* Only custom structs,
 * 		* Only the packet payload, or
 * 		* A combination of both.
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
 * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags)
 * 	Description
 * 		Walk a user or a kernel stack and return its id. To achieve
 * 		this, the helper needs *ctx*, which is a pointer to the context
 * 		on which the tracing program is executed, and a pointer to a
 * 		*map* of type **BPF_MAP_TYPE_STACK_TRACE**.
 *
 * 		The last argument, *flags*, holds the number of stack frames to
 * 		skip (from 0 to 255), masked with
 * 		**BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set
 * 		a combination of the following flags:
 *
 * 		**BPF_F_USER_STACK**
 * 			Collect a user space stack instead of a kernel stack.
 * 		**BPF_F_FAST_STACK_CMP**
 * 			Compare stacks by hash only.
 * 		**BPF_F_REUSE_STACKID**
 * 			If two different stacks hash into the same *stackid*,
 * 			discard the old one.
 *
 * 		The stack id retrieved is a 32 bit long integer handle which
 * 		can be further combined with other data (including other stack
 * 		ids) and used as a key into maps. This can be useful for
 * 		generating a variety of graphs (such as flame graphs or off-cpu
 * 		graphs).
 *
 * 		For walking a stack, this helper is an improvement over
 * 		**bpf_probe_read**\ (), which can be used with unrolled loops
 * 		but is not efficient and consumes a lot of eBPF instructions.
 * 		Instead, **bpf_get_stackid**\ () can collect up to
 * 		**PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that
 * 		this limit can be controlled with the **sysctl** program, and
 * 		that it should be manually increased in order to profile long
 * 		user stacks (such as stacks for Java programs). To do so, use:
 *
 * 		::
 *
 * 			# sysctl kernel.perf_event_max_stack=<new value>
 *
 * 	Return
 * 		The positive or null stack id on success, or a negative error
 * 		in case of failure.
 *
 * u64 bpf_get_current_task(void)
 * 	Return
 * 		A pointer to the current task struct.
 */
#define __BPF_FUNC_MAPPER(FN)		\
	FN(unspec),			\
	FN(map_lookup_elem),		\
	FN(map_update_elem),		\
	FN(map_delete_elem),		\
	FN(probe_read),			\
	FN(ktime_get_ns),		\
	FN(trace_printk),		\
	FN(get_prandom_u32),		\
	FN(get_smp_processor_id),	\
	FN(skb_store_bytes),		\
	FN(l3_csum_replace),		\
	FN(l4_csum_replace),		\
	FN(tail_call),			\
	FN(clone_redirect),		\
	FN(get_current_pid_tgid),	\
	FN(get_current_uid_gid),	\
	FN(get_current_comm),		\
	FN(get_cgroup_classid),		\
	FN(skb_vlan_push),		\
	FN(skb_vlan_pop),		\
	FN(skb_get_tunnel_key),		\
	FN(skb_set_tunnel_key),		\
	FN(perf_event_read),		\
	FN(redirect),			\
	FN(get_route_realm),		\
	FN(perf_event_output),		\
	FN(skb_load_bytes),		\
	FN(get_stackid),		\
	FN(csum_diff),			\
	FN(skb_get_tunnel_opt),		\
	FN(skb_set_tunnel_opt),		\
	FN(skb_change_proto),		\
	FN(skb_change_type),		\
	FN(skb_under_cgroup),		\
	FN(get_hash_recalc),		\
	FN(get_current_task),		\
	FN(probe_write_user),		\
	FN(current_task_under_cgroup),	\
	FN(skb_change_tail),		\
	FN(skb_pull_data),		\
	FN(csum_update),		\
	FN(set_hash_invalid),		\
	FN(get_numa_node_id),		\
	FN(skb_change_head),		\
	FN(xdp_adjust_head),		\
	FN(probe_read_str),		\
	FN(get_socket_cookie),		\
	FN(get_socket_uid),		\
	FN(set_hash),			\
	FN(setsockopt),			\
	FN(skb_adjust_room),		\
	FN(redirect_map),		\
	FN(sk_redirect_map),		\
	FN(sock_map_update),		\
	FN(xdp_adjust_meta),		\
	FN(perf_event_read_value),	\
	FN(perf_prog_read_value),	\
	FN(getsockopt),			\
	FN(override_return),		\
	FN(sock_ops_cb_flags_set),	\
	FN(msg_redirect_map),		\
	FN(msg_apply_bytes),		\
	FN(msg_cork_bytes),		\
	FN(msg_pull_data),		\
	FN(bind),			\
	FN(xdp_adjust_tail),		\
	FN(skb_get_xfrm_state),

/* integer value in 'imm' field of BPF_CALL instruction selects which helper
 * function eBPF program intends to call
 */
#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
enum bpf_func_id {
	__BPF_FUNC_MAPPER(__BPF_ENUM_FN)
	__BPF_FUNC_MAX_ID,
};
#undef __BPF_ENUM_FN

/* 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)
#define BPF_F_MARK_ENFORCE		(1ULL << 6)

/* 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)
#define BPF_F_SEQ_NUMBER		(1ULL << 3)

/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
 * BPF_FUNC_perf_event_read_value flags.
 */
#define BPF_F_INDEX_MASK		0xffffffffULL
#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
/* BPF_FUNC_perf_event_output for sk_buff input context. */
#define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)

/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
	BPF_ADJ_ROOM_NET,
};

/* user accessible mirror of in-kernel sk_buff.
 * new fields can only be added to the end of this structure
 */
struct __sk_buff {
	__u32 len;
	__u32 pkt_type;
	__u32 mark;
	__u32 queue_mapping;
	__u32 protocol;
	__u32 vlan_present;
	__u32 vlan_tci;
	__u32 vlan_proto;
	__u32 priority;
	__u32 ingress_ifindex;
	__u32 ifindex;
	__u32 tc_index;
	__u32 cb[5];
	__u32 hash;
	__u32 tc_classid;
	__u32 data;
	__u32 data_end;
	__u32 napi_id;

	/* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */
	__u32 family;
	__u32 remote_ip4;	/* Stored in network byte order */
	__u32 local_ip4;	/* Stored in network byte order */
	__u32 remote_ip6[4];	/* Stored in network byte order */
	__u32 local_ip6[4];	/* Stored in network byte order */
	__u32 remote_port;	/* Stored in network byte order */
	__u32 local_port;	/* stored in host byte order */
	/* ... here. */

	__u32 data_meta;
};

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;
};

/* 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;
	union {
		__u32 remote_ipv4;	/* Stored in network byte order */
		__u32 remote_ipv6[4];	/* Stored in network byte order */
	};
};

/* Generic BPF return codes which all BPF program types may support.
 * The values are binary compatible with their TC_ACT_* counter-part to
 * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT
 * 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;
	__u32 mark;
	__u32 priority;
	__u32 src_ip4;		/* Allows 1,2,4-byte read.
				 * Stored in network byte order.
				 */
	__u32 src_ip6[4];	/* Allows 1,2,4-byte read.
				 * Stored in network byte order.
				 */
	__u32 src_port;		/* Allows 4-byte read.
				 * Stored in host byte order
				 */
};

#define XDP_PACKET_HEADROOM 256

/* User return codes for XDP prog type.
 * A valid XDP program must return one of these defined values. All other
 * return codes are reserved for future use. Unknown return codes will
 * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
 */
enum xdp_action {
	XDP_ABORTED = 0,
	XDP_DROP,
	XDP_PASS,
	XDP_TX,
	XDP_REDIRECT,
};

/* user accessible metadata for XDP packet hook
 * new fields must be added to the end of this structure
 */
struct xdp_md {
	__u32 data;
	__u32 data_end;
	__u32 data_meta;
	/* Below access go through struct xdp_rxq_info */
	__u32 ingress_ifindex; /* rxq->dev->ifindex */
	__u32 rx_queue_index;  /* rxq->queue_index  */
};

enum sk_action {
	SK_DROP = 0,
	SK_PASS,
};

/* user accessible metadata for SK_MSG packet hook, new fields must
 * be added to the end of this structure
 */
struct sk_msg_md {
	void *data;
	void *data_end;
};

#define BPF_TAG_SIZE	8

struct bpf_prog_info {
	__u32 type;
	__u32 id;
	__u8  tag[BPF_TAG_SIZE];
	__u32 jited_prog_len;
	__u32 xlated_prog_len;
	__aligned_u64 jited_prog_insns;
	__aligned_u64 xlated_prog_insns;
	__u64 load_time;	/* ns since boottime */
	__u32 created_by_uid;
	__u32 nr_map_ids;
	__aligned_u64 map_ids;
	char name[BPF_OBJ_NAME_LEN];
	__u32 ifindex;
	__u32 gpl_compatible:1;
	__u64 netns_dev;
	__u64 netns_ino;
} __attribute__((aligned(8)));

struct bpf_map_info {
	__u32 type;
	__u32 id;
	__u32 key_size;
	__u32 value_size;
	__u32 max_entries;
	__u32 map_flags;
	char  name[BPF_OBJ_NAME_LEN];
	__u32 ifindex;
	__u64 netns_dev;
	__u64 netns_ino;
} __attribute__((aligned(8)));

/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
 * by user and intended to be used by socket (e.g. to bind to, depends on
 * attach attach type).
 */
struct bpf_sock_addr {
	__u32 user_family;	/* Allows 4-byte read, but no write. */
	__u32 user_ip4;		/* Allows 1,2,4-byte read and 4-byte write.
				 * Stored in network byte order.
				 */
	__u32 user_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
				 * Stored in network byte order.
				 */
	__u32 user_port;	/* Allows 4-byte read and write.
				 * Stored in network byte order
				 */
	__u32 family;		/* Allows 4-byte read, but no write */
	__u32 type;		/* Allows 4-byte read, but no write */
	__u32 protocol;		/* Allows 4-byte read, but no write */
};

/* 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 {
		__u32 args[4];		/* Optionally passed to bpf program */
		__u32 reply;		/* Returned by bpf program	    */
		__u32 replylong[4];	/* Optionally returned by bpf prog  */
	};
	__u32 family;
	__u32 remote_ip4;	/* Stored in network byte order */
	__u32 local_ip4;	/* Stored in network byte order */
	__u32 remote_ip6[4];	/* Stored in network byte order */
	__u32 local_ip6[4];	/* Stored in network byte order */
	__u32 remote_port;	/* Stored in network byte order */
	__u32 local_port;	/* stored in host byte order */
	__u32 is_fullsock;	/* Some TCP fields are only valid if
				 * there is a full socket. If not, the
				 * fields read as zero.
				 */
	__u32 snd_cwnd;
	__u32 srtt_us;		/* Averaged RTT << 3 in usecs */
	__u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */
	__u32 state;
	__u32 rtt_min;
	__u32 snd_ssthresh;
	__u32 rcv_nxt;
	__u32 snd_nxt;
	__u32 snd_una;
	__u32 mss_cache;
	__u32 ecn_flags;
	__u32 rate_delivered;
	__u32 rate_interval_us;
	__u32 packets_out;
	__u32 retrans_out;
	__u32 total_retrans;
	__u32 segs_in;
	__u32 data_segs_in;
	__u32 segs_out;
	__u32 data_segs_out;
	__u32 lost_out;
	__u32 sacked_out;
	__u32 sk_txhash;
	__u64 bytes_received;
	__u64 bytes_acked;
};

/* Definitions for bpf_sock_ops_cb_flags */
#define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
#define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
#define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x7		/* Mask of all currently
							 * supported cb flags
							 */

/* List of known BPF sock_ops operators.
 * New entries can only be added at the end
 */
enum {
	BPF_SOCK_OPS_VOID,
	BPF_SOCK_OPS_TIMEOUT_INIT,	/* Should return SYN-RTO value to use or
					 * -1 if default value should be used
					 */
	BPF_SOCK_OPS_RWND_INIT,		/* Should return initial advertized
					 * window (in packets) or -1 if default
					 * value should be used
					 */
	BPF_SOCK_OPS_TCP_CONNECT_CB,	/* Calls BPF program right before an
					 * active connection is initialized
					 */
	BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB,	/* Calls BPF program when an
						 * active connection is
						 * established
						 */
	BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,	/* Calls BPF program when a
						 * passive connection is
						 * established
						 */
	BPF_SOCK_OPS_NEEDS_ECN,		/* If connection's congestion control
					 * needs ECN
					 */
	BPF_SOCK_OPS_BASE_RTT,		/* Get base RTT. The correct value is
					 * based on the path and may be
					 * dependent on the congestion control
					 * algorithm. In general it indicates
					 * a congestion threshold. RTTs above
					 * this indicate congestion
					 */
	BPF_SOCK_OPS_RTO_CB,		/* Called when an RTO has triggered.
					 * Arg1: value of icsk_retransmits
					 * Arg2: value of icsk_rto
					 * Arg3: whether RTO has expired
					 */
	BPF_SOCK_OPS_RETRANS_CB,	/* Called when skb is retransmitted.
					 * Arg1: sequence number of 1st byte
					 * Arg2: # segments
					 * Arg3: return value of
					 *       tcp_transmit_skb (0 => success)
					 */
	BPF_SOCK_OPS_STATE_CB,		/* Called when TCP changes state.
					 * Arg1: old_state
					 * Arg2: new_state
					 */
};

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

	BPF_TCP_MAX_STATES	/* Leave at the end! */
};

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

struct bpf_perf_event_value {
	__u64 counter;
	__u64 enabled;
	__u64 running;
};

#define BPF_DEVCG_ACC_MKNOD	(1ULL << 0)
#define BPF_DEVCG_ACC_READ	(1ULL << 1)
#define BPF_DEVCG_ACC_WRITE	(1ULL << 2)

#define BPF_DEVCG_DEV_BLOCK	(1ULL << 0)
#define BPF_DEVCG_DEV_CHAR	(1ULL << 1)

struct bpf_cgroup_dev_ctx {
	/* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
	__u32 access_type;
	__u32 major;
	__u32 minor;
};

struct bpf_raw_tracepoint_args {
	__u64 args[0];
};

#endif /* _UAPI__LINUX_BPF_H__ */