From 66684189f0f5d182b1c3ab362fc0f919970c7079 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 9 Oct 2018 17:50:12 -0700 Subject: [PATCH] initial commit This initial commit added the following files from bpf-next repository: src: bpf.c bpf.h btf.c btf.h libbpf.c libbpf.h libbpf_errno.c netlink.c nlattr.c nlattr.h str_error.c str_error.h include: uapi/linux/{bpf.h, btf.h} tools/libc_compat.h The following files are also added: include/linux/{err.h, kernel.h, list.h, overflow.h, types.h} These files are customized headers to satisfy compilation. Their original counterparts are at linux:tools/include/linux directory. Signed-off-by: Yonghong Song --- include/linux/err.h | 11 + include/linux/kernel.h | 12 + include/linux/list.h | 17 + include/linux/overflow.h | 217 +++ include/linux/types.h | 44 + include/tools/libc_compat.h | 20 + include/uapi/linux/bpf.h | 2899 +++++++++++++++++++++++++++++++++++ include/uapi/linux/btf.h | 113 ++ src/bpf.c | 540 +++++++ src/bpf.h | 114 ++ src/btf.c | 395 +++++ src/btf.h | 26 + src/libbpf.c | 2465 +++++++++++++++++++++++++++++ src/libbpf.h | 305 ++++ src/libbpf_errno.c | 62 + src/netlink.c | 337 ++++ src/nlattr.c | 195 +++ src/nlattr.h | 106 ++ src/str_error.c | 18 + src/str_error.h | 6 + 20 files changed, 7902 insertions(+) create mode 100644 include/linux/err.h create mode 100644 include/linux/kernel.h create mode 100644 include/linux/list.h create mode 100644 include/linux/overflow.h create mode 100644 include/linux/types.h create mode 100644 include/tools/libc_compat.h create mode 100644 include/uapi/linux/bpf.h create mode 100644 include/uapi/linux/btf.h create mode 100644 src/bpf.c create mode 100644 src/bpf.h create mode 100644 src/btf.c create mode 100644 src/btf.h create mode 100644 src/libbpf.c create mode 100644 src/libbpf.h create mode 100644 src/libbpf_errno.c create mode 100644 src/netlink.c create mode 100644 src/nlattr.c create mode 100644 src/nlattr.h create mode 100644 src/str_error.c create mode 100644 src/str_error.h diff --git a/include/linux/err.h b/include/linux/err.h new file mode 100644 index 0000000..1bafb5a --- /dev/null +++ b/include/linux/err.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_ERR_H +#define __LINUX_ERR_H + +static inline void * ERR_PTR(long error_) +{ + return (void *) error_; +} + +#endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h new file mode 100644 index 0000000..bf88cff --- /dev/null +++ b/include/linux/kernel.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_KERNEL_H +#define __LINUX_KERNEL_H + +#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) + +#define container_of(ptr, type, member) ({ \ + const typeof(((type *)0)->member) * __mptr = (ptr); \ + (type *)((char *)__mptr - offsetof(type, member)); }) + +#endif diff --git a/include/linux/list.h b/include/linux/list.h new file mode 100644 index 0000000..2d5703e --- /dev/null +++ b/include/linux/list.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_LIST_H +#define __LINUX_LIST_H + +#define LIST_HEAD_INIT(name) { &(name), &(name) } +#define LIST_HEAD(name) \ + struct list_head name = LIST_HEAD_INIT(name) + +#define list_entry(ptr, type, member) \ + container_of(ptr, type, member) +#define list_first_entry(ptr, type, member) \ + list_entry((ptr)->next, type, member) +#define list_next_entry(pos, member) \ + list_entry((pos)->member.next, typeof(*(pos)), member) + +#endif diff --git a/include/linux/overflow.h b/include/linux/overflow.h new file mode 100644 index 0000000..c84dc34 --- /dev/null +++ b/include/linux/overflow.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_OVERFLOW_H +#define __LINUX_OVERFLOW_H + +#define is_signed_type(type) (((type)(-1)) < (type)1) +#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type))) +#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) +#define type_min(T) ((T)((T)-type_max(T)-(T)1)) + +#ifdef __GNUC__ +#define GCC_VERSION (__GNUC__ * 10000 \ + + __GNUC_MINOR__ * 100 \ + + __GNUC_PATCHLEVEL__) +#if GCC_VERSION >= 50100 +#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 +#endif +#endif + +#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW + +#define check_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_mul_overflow(__a, __b, __d); \ +}) + +#else + + +/* Checking for unsigned overflow is relatively easy without causing UB. */ +#define __unsigned_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a + __b; \ + *__d < __a; \ +}) +#define __unsigned_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a - __b; \ + __a < __b; \ +}) +/* + * If one of a or b is a compile-time constant, this avoids a division. + */ +#define __unsigned_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a * __b; \ + __builtin_constant_p(__b) ? \ + __b > 0 && __a > type_max(typeof(__a)) / __b : \ + __a > 0 && __b > type_max(typeof(__b)) / __a; \ +}) + +/* + * For signed types, detecting overflow is much harder, especially if + * we want to avoid UB. But the interface of these macros is such that + * we must provide a result in *d, and in fact we must produce the + * result promised by gcc's builtins, which is simply the possibly + * wrapped-around value. Fortunately, we can just formally do the + * operations in the widest relevant unsigned type (u64) and then + * truncate the result - gcc is smart enough to generate the same code + * with and without the (u64) casts. + */ + +/* + * Adding two signed integers can overflow only if they have the same + * sign, and overflow has happened iff the result has the opposite + * sign. + */ +#define __signed_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a + (u64)__b; \ + (((~(__a ^ __b)) & (*__d ^ __a)) \ + & type_min(typeof(__a))) != 0; \ +}) + +/* + * Subtraction is similar, except that overflow can now happen only + * when the signs are opposite. In this case, overflow has happened if + * the result has the opposite sign of a. + */ +#define __signed_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a - (u64)__b; \ + ((((__a ^ __b)) & (*__d ^ __a)) \ + & type_min(typeof(__a))) != 0; \ +}) + +/* + * Signed multiplication is rather hard. gcc always follows C99, so + * division is truncated towards 0. This means that we can write the + * overflow check like this: + * + * (a > 0 && (b > MAX/a || b < MIN/a)) || + * (a < -1 && (b > MIN/a || b < MAX/a) || + * (a == -1 && b == MIN) + * + * The redundant casts of -1 are to silence an annoying -Wtype-limits + * (included in -Wextra) warning: When the type is u8 or u16, the + * __b_c_e in check_mul_overflow obviously selects + * __unsigned_mul_overflow, but unfortunately gcc still parses this + * code and warns about the limited range of __b. + */ + +#define __signed_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + typeof(a) __tmax = type_max(typeof(a)); \ + typeof(a) __tmin = type_min(typeof(a)); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a * (u64)__b; \ + (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ + (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ + (__b == (typeof(__b))-1 && __a == __tmin); \ +}) + + +#define check_add_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_add_overflow(a, b, d), \ + __unsigned_add_overflow(a, b, d)) + +#define check_sub_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_sub_overflow(a, b, d), \ + __unsigned_sub_overflow(a, b, d)) + +#define check_mul_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_mul_overflow(a, b, d), \ + __unsigned_mul_overflow(a, b, d)) + + +#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ + +/** + * array_size() - Calculate size of 2-dimensional array. + * + * @a: dimension one + * @b: dimension two + * + * Calculates size of 2-dimensional array: @a * @b. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline size_t array_size(size_t a, size_t b) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/** + * array3_size() - Calculate size of 3-dimensional array. + * + * @a: dimension one + * @b: dimension two + * @c: dimension three + * + * Calculates size of 3-dimensional array: @a * @b * @c. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline size_t array3_size(size_t a, size_t b, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + if (check_mul_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +static inline size_t __ab_c_size(size_t n, size_t size, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(n, size, &bytes)) + return SIZE_MAX; + if (check_add_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +#endif diff --git a/include/linux/types.h b/include/linux/types.h new file mode 100644 index 0000000..3ddd19b --- /dev/null +++ b/include/linux/types.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_TYPES_H +#define __LINUX_TYPES_H + +#include +#include +#include + +#define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */ +#include +#include + +typedef uint64_t u64; +typedef int64_t s64; + +typedef __u32 u32; +typedef __s32 s32; + +typedef __u16 u16; +typedef __s16 s16; + +typedef __u8 u8; +typedef __s8 s8; + +#define __bitwise__ +#define __bitwise __bitwise__ + +typedef __u16 __bitwise __le16; +typedef __u16 __bitwise __be16; +typedef __u32 __bitwise __le32; +typedef __u32 __bitwise __be32; +typedef __u64 __bitwise __le64; +typedef __u64 __bitwise __be64; + +#ifndef __aligned_u64 +# define __aligned_u64 __u64 __attribute__((aligned(8))) +#endif + +struct list_head { + struct list_head *next, *prev; +}; + +#endif diff --git a/include/tools/libc_compat.h b/include/tools/libc_compat.h new file mode 100644 index 0000000..e907ba6 --- /dev/null +++ b/include/tools/libc_compat.h @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: (LGPL-2.0+ OR BSD-2-Clause) +/* Copyright (C) 2018 Netronome Systems, Inc. */ + +#ifndef __TOOLS_LIBC_COMPAT_H +#define __TOOLS_LIBC_COMPAT_H + +#include +#include + +#ifdef COMPAT_NEED_REALLOCARRAY +static inline void *reallocarray(void *ptr, size_t nmemb, size_t size) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(nmemb, size, &bytes))) + return NULL; + return realloc(ptr, bytes); +} +#endif +#endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h new file mode 100644 index 0000000..f9187b4 --- /dev/null +++ b/include/uapi/linux/bpf.h @@ -0,0 +1,2899 @@ +/* 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 +#include + +/* 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, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, +}; + +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, + BPF_PROG_TYPE_FLOW_DISSECTOR, +}; + +enum bpf_attach_type { + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_SOCK_OPS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, + BPF_SK_MSG_VERDICT, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_POST_BIND, + BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + BPF_LIRC_MODE2, + BPF_FLOW_DISSECTOR, + __MAX_BPF_ATTACH_TYPE +}; + +#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE + +/* 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_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: + * + * 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. + * * ```` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * bloc (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * u32 bpf_get_prandom_u32(void) + * Description + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * Return + * A random 32-bit unsigned value. + * + * u32 bpf_get_smp_processor_id(void) + * Description + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with preemption disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * Return + * The SMP id of the processor running the program. + * + * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * Description + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * Description + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * Description + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 32. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * Description + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_get_current_pid_tgid(void) + * Return + * 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. + * + * u32 bpf_get_cgroup_classid(struct sk_buff *skb) + * Description + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/cgroup-v1/net_cls.txt*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * Return + * The classid, or 0 for the default unconfigured classid. + * + * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * Description + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_vlan_pop(struct sk_buff *skb) + * Description + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags) + * Description + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * Return + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + * + * int bpf_redirect(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * Return + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + * + * u32 bpf_get_route_realm(struct sk_buff *skb) + * Description + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * indentifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * Return + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + * + * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) + * Description + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags) + * Description + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack= + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * Return + * The size of the option data retrieved. + * + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * Description + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * Description + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * Description + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + * + * u32 bpf_get_hash_recalc(struct sk_buff *skb) + * Description + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * Return + * The 32-bit hash. + * + * u64 bpf_get_current_task(void) + * Return + * A pointer to the current task struct. + * + * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * Description + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * Description + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * Description + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then the whole length of the *skb* is pulled. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum) + * Description + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * Return + * The checksum on success, or a negative error code in case of + * failure. + * + * void bpf_set_hash_invalid(struct sk_buff *skb) + * Description + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + * int bpf_get_numa_node_id(void) + * Description + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * Return + * The id of current NUMA node. + * + * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read()** helper here instead + * to read the string would require to estimate the length at + * compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * u64 bpf_get_socket_cookie(struct sk_buff *skb) + * Description + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a unique socket + * identifier per namespace. + * Return + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_addr** contex. + * Return + * A 8-byte long non-decreasing number. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_ops** contex. + * Return + * A 8-byte long non-decreasing number. + * + * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Return + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + * + * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * Description + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * Return + * 0 + * + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * There is a single supported mode at this time: + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * Return + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * + * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For en eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_override_return(struct pt_reg *regs, u64 rc) + * Description + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * Return + * 0 + * + * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * Description + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * The supported callback values that *argval* can combine are: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * Return + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + * + * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * Return + * 0 + * + * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * Return + * 0 + * + * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * Description + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * Description + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). Looking for a free port to bind to can be + * expensive, therefore binding to port is not permitted by the + * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) + * must be set to zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * Description + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack= + * Return + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. + * + * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) + * Description + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) + * Description + * Do FIB lookup in kernel tables using parameters in *params*. + * If lookup is successful and result shows packet is to be + * forwarded, the neighbor tables are searched for the nexthop. + * If successful (ie., FIB lookup shows forwarding and nexthop + * is resolved), the nexthop address is returned in ipv4_dst + * or ipv6_dst based on family, smac is set to mac address of + * egress device, dmac is set to nexthop mac address, rt_metric + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. + * + * *plen* argument is the size of the passed in struct. + * *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_FIB_LOOKUP_DIRECT** + * Do a direct table lookup vs full lookup using FIB + * rules. + * **BPF_FIB_LOOKUP_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** tc cls_act programs. + * Return + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * packet is not forwarded or needs assist from full stack + * + * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a sockhash *map* referencing sockets. + * The *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. + * if the verdeict eBPF program returns **SK_PASS**), redirect it + * to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) + * Description + * Encapsulate the packet associated to *skb* within a Layer 3 + * protocol header. This header is provided in the buffer at + * address *hdr*, with *len* its size in bytes. *type* indicates + * the protocol of the header and can be one of: + * + * **BPF_LWT_ENCAP_SEG6** + * IPv6 encapsulation with Segment Routing Header + * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH, + * the IPv6 header is computed by the kernel. + * **BPF_LWT_ENCAP_SEG6_INLINE** + * Only works if *skb* contains an IPv6 packet. Insert a + * Segment Routing Header (**struct ipv6_sr_hdr**) inside + * the IPv6 header. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. Only the flags, tag and TLVs + * inside the outermost IPv6 Segment Routing Header can be + * modified through this helper. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) + * Description + * Adjust the size allocated to TLVs in the outermost IPv6 + * Segment Routing Header contained in the packet associated to + * *skb*, at position *offset* by *delta* bytes. Only offsets + * after the segments are accepted. *delta* can be as well + * positive (growing) as negative (shrinking). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) + * Description + * Apply an IPv6 Segment Routing action of type *action* to the + * packet associated to *skb*. Each action takes a parameter + * contained at address *param*, and of length *param_len* bytes. + * *action* can be one of: + * + * **SEG6_LOCAL_ACTION_END_X** + * End.X action: Endpoint with Layer-3 cross-connect. + * Type of *param*: **struct in6_addr**. + * **SEG6_LOCAL_ACTION_END_T** + * End.T action: Endpoint with specific IPv6 table lookup. + * Type of *param*: **int**. + * **SEG6_LOCAL_ACTION_END_B6** + * End.B6 action: Endpoint bound to an SRv6 policy. + * Type of param: **struct ipv6_sr_hdr**. + * **SEG6_LOCAL_ACTION_END_B6_ENCAP** + * End.B6.Encap action: Endpoint bound to an SRv6 + * encapsulation policy. + * Type of param: **struct ipv6_sr_hdr**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown** () again with the same values, or calling + * **bpf_rc_repeat** (). + * + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * int bpf_rc_repeat(void *ctx) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * Description + * Return the cgroup v2 id of the socket associated with the *skb*. + * This is roughly similar to the **bpf_get_cgroup_classid**\ () + * helper for cgroup v1 by providing a tag resp. identifier that + * can be matched on or used for map lookups e.g. to implement + * policy. The cgroup v2 id of a given path in the hierarchy is + * exposed in user space through the f_handle API in order to get + * to the same 64-bit id. + * + * This helper can be used on TC egress path, but not on ingress, + * and is available only if the kernel was compiled with the + * **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_get_current_cgroup_id(void) + * Return + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. + * + * void* get_local_storage(void *map, u64 flags) + * Description + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the bpf program type, a local storage area + * can be shared between multiple instances of the bpf program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the BPF_STX_XADD instruction to alter + * the shared data. + * Return + * Pointer to the local storage area. + * + * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * Description + * Select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY map + * It checks the selected sk is matching the incoming + * request in the skb. + * Return + * 0 on success, or a negative error in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is zero, then the socket lookup table in the + * netns associated with the *ctx* will be used. For the TC hooks, + * this in the netns of the device in the skb. For socket hooks, + * this in the netns of the socket. If *netns* is non-zero, then + * it specifies the ID of the netns relative to the netns + * associated with the *ctx*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * int bpf_sk_release(struct bpf_sock *sk) + * Description + * Release the reference held by *sock*. *sock* must be a non-NULL + * pointer that was returned from bpf_sk_lookup_xxx\ (). + * Return + * 0 on success, or a negative error in case of failure. + */ +#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), \ + FN(get_stack), \ + FN(skb_load_bytes_relative), \ + FN(fib_lookup), \ + FN(sock_hash_update), \ + FN(msg_redirect_hash), \ + FN(sk_redirect_hash), \ + FN(lwt_push_encap), \ + FN(lwt_seg6_store_bytes), \ + FN(lwt_seg6_adjust_srh), \ + FN(lwt_seg6_action), \ + FN(rc_repeat), \ + FN(rc_keydown), \ + FN(skb_cgroup_id), \ + FN(get_current_cgroup_id), \ + FN(get_local_storage), \ + FN(sk_select_reuseport), \ + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), + +/* 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) + +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ +#define BPF_F_SKIP_FIELD_MASK 0xffULL +#define BPF_F_USER_STACK (1ULL << 8) +/* flags used by BPF_FUNC_get_stackid only. */ +#define BPF_F_FAST_STACK_CMP (1ULL << 9) +#define BPF_F_REUSE_STACKID (1ULL << 10) +/* flags used by BPF_FUNC_get_stack only. */ +#define BPF_F_USER_BUILD_ID (1ULL << 11) + +/* BPF_FUNC_skb_set_tunnel_key flags. */ +#define BPF_F_ZERO_CSUM_TX (1ULL << 1) +#define BPF_F_DONT_FRAGMENT (1ULL << 2) +#define BPF_F_SEQ_NUMBER (1ULL << 3) + +/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and + * BPF_FUNC_perf_event_read_value flags. + */ +#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, +}; + +/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ +enum bpf_hdr_start_off { + BPF_HDR_START_MAC, + BPF_HDR_START_NET, +}; + +/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ +enum bpf_lwt_encap_mode { + BPF_LWT_ENCAP_SEG6, + BPF_LWT_ENCAP_SEG6_INLINE +}; + +/* 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_flow_keys *flow_keys; +}; + +struct bpf_tunnel_key { + __u32 tunnel_id; + union { + __u32 remote_ipv4; + __u32 remote_ipv6[4]; + }; + __u8 tunnel_tos; + __u8 tunnel_ttl; + __u16 tunnel_ext; /* Padding, future use. */ + __u32 tunnel_label; +}; + +/* user accessible mirror of in-kernel xfrm_state. + * new fields can only be added to the end of this structure + */ +struct bpf_xfrm_state { + __u32 reqid; + __u32 spi; /* Stored in network byte order */ + __u16 family; + __u16 ext; /* Padding, future use. */ + union { + __u32 remote_ipv4; /* Stored in network byte order */ + __u32 remote_ipv6[4]; /* Stored in network byte order */ + }; +}; + +/* Generic BPF return codes which all BPF program types may support. + * 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 + */ +}; + +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + +#define XDP_PACKET_HEADROOM 256 + +/* 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; + + __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 */ +}; + +struct sk_reuseport_md { + /* + * Start of directly accessible data. It begins from + * the tcp/udp header. + */ + void *data; + void *data_end; /* End of directly accessible data */ + /* + * Total length of packet (starting from the tcp/udp header). + * Note that the directly accessible bytes (data_end - data) + * could be less than this "len". Those bytes could be + * indirectly read by a helper "bpf_skb_load_bytes()". + */ + __u32 len; + /* + * Eth protocol in the mac header (network byte order). e.g. + * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD) + */ + __u32 eth_protocol; + __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ + __u32 bind_inany; /* Is sock bound to an INANY address? */ + __u32 hash; /* A hash of the packet 4 tuples */ +}; + +#define BPF_TAG_SIZE 8 + +struct bpf_prog_info { + __u32 type; + __u32 id; + __u8 tag[BPF_TAG_SIZE]; + __u32 jited_prog_len; + __u32 xlated_prog_len; + __aligned_u64 jited_prog_insns; + __aligned_u64 xlated_prog_insns; + __u64 load_time; /* ns since boottime */ + __u32 created_by_uid; + __u32 nr_map_ids; + __aligned_u64 map_ids; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 gpl_compatible:1; + __u64 netns_dev; + __u64 netns_ino; + __u32 nr_jited_ksyms; + __u32 nr_jited_func_lens; + __aligned_u64 jited_ksyms; + __aligned_u64 jited_func_lens; +} __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; + __u32 :32; + __u64 netns_dev; + __u64 netns_ino; + __u32 btf_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; +} __attribute__((aligned(8))); + +struct bpf_btf_info { + __aligned_u64 btf; + __u32 btf_size; + __u32 id; +} __attribute__((aligned(8))); + +/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed + * by user and intended to be used by socket (e.g. to bind to, depends on + * attach attach type). + */ +struct bpf_sock_addr { + __u32 user_family; /* Allows 4-byte read, but no write. */ + __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. + * Stored in network byte order. + */ + __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 user_port; /* Allows 4-byte read and write. + * Stored in network byte order + */ + __u32 family; /* Allows 4-byte read, but no write */ + __u32 type; /* Allows 4-byte read, but no write */ + __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ +}; + +/* User bpf_sock_ops struct to access socket values and specify request ops + * and their replies. + * Some of this fields are in network (bigendian) byte order and may need + * 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 + */ + BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after + * socket transition to LISTEN state. + */ +}; + +/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect + * 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]; +}; + +/* DIRECT: Skip the FIB rules and go to FIB table associated with device + * OUTPUT: Do lookup from egress perspective; default is ingress + */ +#define BPF_FIB_LOOKUP_DIRECT BIT(0) +#define BPF_FIB_LOOKUP_OUTPUT BIT(1) + +enum { + BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ + BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */ + BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */ + BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */ + BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */ + BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */ + BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ + BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ + BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ +}; + +struct bpf_fib_lookup { + /* input: network family for lookup (AF_INET, AF_INET6) + * output: network family of egress nexthop + */ + __u8 family; + + /* set if lookup is to consider L4 data - e.g., FIB rules */ + __u8 l4_protocol; + __be16 sport; + __be16 dport; + + /* total length of packet from network header - used for MTU check */ + __u16 tot_len; + + /* input: L3 device index for lookup + * output: device index from FIB lookup + */ + __u32 ifindex; + + union { + /* inputs to lookup */ + __u8 tos; /* AF_INET */ + __be32 flowinfo; /* AF_INET6, flow_label + priority */ + + /* output: metric of fib result (IPv4/IPv6 only) */ + __u32 rt_metric; + }; + + union { + __be32 ipv4_src; + __u32 ipv6_src[4]; /* in6_addr; network order */ + }; + + /* input to bpf_fib_lookup, ipv{4,6}_dst is destination address in + * network header. output: bpf_fib_lookup sets to gateway address + * if FIB lookup returns gateway route + */ + union { + __be32 ipv4_dst; + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ +}; + +enum bpf_task_fd_type { + BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_UPROBE, /* filename + offset */ + BPF_FD_TYPE_URETPROBE, /* filename + offset */ +}; + +struct bpf_flow_keys { + __u16 nhoff; + __u16 thoff; + __u16 addr_proto; /* ETH_P_* of valid addrs */ + __u8 is_frag; + __u8 is_first_frag; + __u8 is_encap; + __u8 ip_proto; + __be16 n_proto; + __be16 sport; + __be16 dport; + union { + struct { + __be32 ipv4_src; + __be32 ipv4_dst; + }; + struct { + __u32 ipv6_src[4]; /* in6_addr; network order */ + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + }; +}; + +#endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h new file mode 100644 index 0000000..972265f --- /dev/null +++ b/include/uapi/linux/btf.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2018 Facebook */ +#ifndef _UAPI__LINUX_BTF_H__ +#define _UAPI__LINUX_BTF_H__ + +#include + +#define BTF_MAGIC 0xeB9F +#define BTF_VERSION 1 + +struct btf_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 type_off; /* offset of type section */ + __u32 type_len; /* length of type section */ + __u32 str_off; /* offset of string section */ + __u32 str_len; /* length of string section */ +}; + +/* Max # of type identifier */ +#define BTF_MAX_TYPE 0x0000ffff +/* Max offset into the string section */ +#define BTF_MAX_NAME_OFFSET 0x0000ffff +/* Max # of struct/union/enum members or func args */ +#define BTF_MAX_VLEN 0xffff + +struct btf_type { + __u32 name_off; + /* "info" bits arrangement + * bits 0-15: vlen (e.g. # of struct's members) + * bits 16-23: unused + * bits 24-27: kind (e.g. int, ptr, array...etc) + * bits 28-31: unused + */ + __u32 info; + /* "size" is used by INT, ENUM, STRUCT and UNION. + * "size" tells the size of the type it is describing. + * + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT. + * "type" is a type_id referring to another type. + */ + union { + __u32 size; + __u32 type; + }; +}; + +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f) +#define BTF_INFO_VLEN(info) ((info) & 0xffff) + +#define BTF_KIND_UNKN 0 /* Unknown */ +#define BTF_KIND_INT 1 /* Integer */ +#define BTF_KIND_PTR 2 /* Pointer */ +#define BTF_KIND_ARRAY 3 /* Array */ +#define BTF_KIND_STRUCT 4 /* Struct */ +#define BTF_KIND_UNION 5 /* Union */ +#define BTF_KIND_ENUM 6 /* Enumeration */ +#define BTF_KIND_FWD 7 /* Forward */ +#define BTF_KIND_TYPEDEF 8 /* Typedef */ +#define BTF_KIND_VOLATILE 9 /* Volatile */ +#define BTF_KIND_CONST 10 /* Const */ +#define BTF_KIND_RESTRICT 11 /* Restrict */ +#define BTF_KIND_MAX 11 +#define NR_BTF_KINDS 12 + +/* For some specific BTF_KIND, "struct btf_type" is immediately + * followed by extra data. + */ + +/* BTF_KIND_INT is followed by a u32 and the following + * is the 32 bits arrangement: + */ +#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) +#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) + +/* Attributes stored in the BTF_INT_ENCODING */ +#define BTF_INT_SIGNED (1 << 0) +#define BTF_INT_CHAR (1 << 1) +#define BTF_INT_BOOL (1 << 2) + +/* BTF_KIND_ENUM is followed by multiple "struct btf_enum". + * The exact number of btf_enum is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum { + __u32 name_off; + __s32 val; +}; + +/* BTF_KIND_ARRAY is followed by one "struct btf_array" */ +struct btf_array { + __u32 type; + __u32 index_type; + __u32 nelems; +}; + +/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed + * by multiple "struct btf_member". The exact number + * of btf_member is stored in the vlen (of the info in + * "struct btf_type"). + */ +struct btf_member { + __u32 name_off; + __u32 type; + __u32 offset; /* offset in bits */ +}; + +#endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/src/bpf.c b/src/bpf.c new file mode 100644 index 0000000..d70a255 --- /dev/null +++ b/src/bpf.c @@ -0,0 +1,540 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * common eBPF ELF operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov + * Copyright (C) 2015 Wang Nan + * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see + */ + +#include +#include +#include +#include +#include +#include "bpf.h" +#include "libbpf.h" +#include + +/* + * When building perf, unistd.h is overridden. __NR_bpf is + * required to be defined explicitly. + */ +#ifndef __NR_bpf +# if defined(__i386__) +# define __NR_bpf 357 +# elif defined(__x86_64__) +# define __NR_bpf 321 +# elif defined(__aarch64__) +# define __NR_bpf 280 +# elif defined(__sparc__) +# define __NR_bpf 349 +# elif defined(__s390__) +# define __NR_bpf 351 +# else +# error __NR_bpf not defined. libbpf does not support your arch. +# endif +#endif + +#ifndef min +#define min(x, y) ((x) < (y) ? (x) : (y)) +#endif + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, + unsigned int size) +{ + return syscall(__NR_bpf, cmd, attr, size); +} + +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) +{ + __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0; + union bpf_attr attr; + + memset(&attr, '\0', sizeof(attr)); + + attr.map_type = create_attr->map_type; + attr.key_size = create_attr->key_size; + attr.value_size = create_attr->value_size; + attr.max_entries = create_attr->max_entries; + attr.map_flags = create_attr->map_flags; + memcpy(attr.map_name, create_attr->name, + min(name_len, BPF_OBJ_NAME_LEN - 1)); + attr.numa_node = create_attr->numa_node; + attr.btf_fd = create_attr->btf_fd; + attr.btf_key_type_id = create_attr->btf_key_type_id; + attr.btf_value_type_id = create_attr->btf_value_type_id; + attr.map_ifindex = create_attr->map_ifindex; + attr.inner_map_fd = create_attr->inner_map_fd; + + return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); +} + +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node) +{ + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + if (node >= 0) { + map_attr.numa_node = node; + map_attr.map_flags |= BPF_F_NUMA_NODE; + } + + return bpf_create_map_xattr(&map_attr); +} + +int bpf_create_map(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags) +{ + struct bpf_create_map_attr map_attr = {}; + + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); +} + +int bpf_create_map_name(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags) +{ + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); +} + +int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags, int node) +{ + __u32 name_len = name ? strlen(name) : 0; + union bpf_attr attr; + + memset(&attr, '\0', sizeof(attr)); + + attr.map_type = map_type; + attr.key_size = key_size; + attr.value_size = 4; + attr.inner_map_fd = inner_map_fd; + attr.max_entries = max_entries; + attr.map_flags = map_flags; + memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + + if (node >= 0) { + attr.map_flags |= BPF_F_NUMA_NODE; + attr.numa_node = node; + } + + return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); +} + +int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags) +{ + return bpf_create_map_in_map_node(map_type, name, key_size, + inner_map_fd, max_entries, map_flags, + -1); +} + +int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz) +{ + union bpf_attr attr; + __u32 name_len; + int fd; + + if (!load_attr) + return -EINVAL; + + name_len = load_attr->name ? strlen(load_attr->name) : 0; + + bzero(&attr, sizeof(attr)); + attr.prog_type = load_attr->prog_type; + attr.expected_attach_type = load_attr->expected_attach_type; + attr.insn_cnt = (__u32)load_attr->insns_cnt; + attr.insns = ptr_to_u64(load_attr->insns); + attr.license = ptr_to_u64(load_attr->license); + attr.log_buf = ptr_to_u64(NULL); + attr.log_size = 0; + attr.log_level = 0; + attr.kern_version = load_attr->kern_version; + attr.prog_ifindex = load_attr->prog_ifindex; + memcpy(attr.prog_name, load_attr->name, + min(name_len, BPF_OBJ_NAME_LEN - 1)); + + fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); + if (fd >= 0 || !log_buf || !log_buf_sz) + return fd; + + /* Try again with log */ + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_buf_sz; + attr.log_level = 1; + log_buf[0] = 0; + return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); +} + +int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz) +{ + struct bpf_load_program_attr load_attr; + + memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); + load_attr.prog_type = type; + load_attr.expected_attach_type = 0; + load_attr.name = NULL; + load_attr.insns = insns; + load_attr.insns_cnt = insns_cnt; + load_attr.license = license; + load_attr.kern_version = kern_version; + + return bpf_load_program_xattr(&load_attr, log_buf, log_buf_sz); +} + +int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, int strict_alignment, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz, int log_level) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.prog_type = type; + attr.insn_cnt = (__u32)insns_cnt; + attr.insns = ptr_to_u64(insns); + attr.license = ptr_to_u64(license); + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_buf_sz; + attr.log_level = log_level; + log_buf[0] = 0; + attr.kern_version = kern_version; + attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0; + + return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); +} + +int bpf_map_update_elem(int fd, const void *key, const void *value, + __u64 flags) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + attr.flags = flags; + + return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); +} + +int bpf_map_lookup_elem(int fd, const void *key, void *value) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + + return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); +} + +int bpf_map_delete_elem(int fd, const void *key) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + + return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); +} + +int bpf_map_get_next_key(int fd, const void *key, void *next_key) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.next_key = ptr_to_u64(next_key); + + return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); +} + +int bpf_obj_pin(int fd, const char *pathname) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.pathname = ptr_to_u64((void *)pathname); + attr.bpf_fd = fd; + + return sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr)); +} + +int bpf_obj_get(const char *pathname) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.pathname = ptr_to_u64((void *)pathname); + + return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr)); +} + +int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, + unsigned int flags) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.target_fd = target_fd; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + attr.attach_flags = flags; + + return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); +} + +int bpf_prog_detach(int target_fd, enum bpf_attach_type type) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.target_fd = target_fd; + attr.attach_type = type; + + return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); +} + +int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.target_fd = target_fd; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + + return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); +} + +int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, + __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt) +{ + union bpf_attr attr; + int ret; + + bzero(&attr, sizeof(attr)); + attr.query.target_fd = target_fd; + attr.query.attach_type = type; + attr.query.query_flags = query_flags; + attr.query.prog_cnt = *prog_cnt; + attr.query.prog_ids = ptr_to_u64(prog_ids); + + ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr)); + if (attach_flags) + *attach_flags = attr.query.attach_flags; + *prog_cnt = attr.query.prog_cnt; + return ret; +} + +int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, + void *data_out, __u32 *size_out, __u32 *retval, + __u32 *duration) +{ + union bpf_attr attr; + int ret; + + bzero(&attr, sizeof(attr)); + attr.test.prog_fd = prog_fd; + attr.test.data_in = ptr_to_u64(data); + attr.test.data_out = ptr_to_u64(data_out); + attr.test.data_size_in = size; + attr.test.repeat = repeat; + + ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + if (size_out) + *size_out = attr.test.data_size_out; + if (retval) + *retval = attr.test.retval; + if (duration) + *duration = attr.test.duration; + return ret; +} + +int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) +{ + union bpf_attr attr; + int err; + + bzero(&attr, sizeof(attr)); + attr.start_id = start_id; + + err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr)); + if (!err) + *next_id = attr.next_id; + + return err; +} + +int bpf_map_get_next_id(__u32 start_id, __u32 *next_id) +{ + union bpf_attr attr; + int err; + + bzero(&attr, sizeof(attr)); + attr.start_id = start_id; + + err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr)); + if (!err) + *next_id = attr.next_id; + + return err; +} + +int bpf_prog_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.prog_id = id; + + return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_map_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.map_id = id; + + return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_btf_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.btf_id = id; + + return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len) +{ + union bpf_attr attr; + int err; + + bzero(&attr, sizeof(attr)); + attr.info.bpf_fd = prog_fd; + attr.info.info_len = *info_len; + attr.info.info = ptr_to_u64(info); + + err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr)); + if (!err) + *info_len = attr.info.info_len; + + return err; +} + +int bpf_raw_tracepoint_open(const char *name, int prog_fd) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.raw_tracepoint.name = ptr_to_u64(name); + attr.raw_tracepoint.prog_fd = prog_fd; + + return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr)); +} + +int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, + bool do_log) +{ + union bpf_attr attr = {}; + int fd; + + attr.btf = ptr_to_u64(btf); + attr.btf_size = btf_size; + +retry: + if (do_log && log_buf && log_buf_size) { + attr.btf_log_level = 1; + attr.btf_log_size = log_buf_size; + attr.btf_log_buf = ptr_to_u64(log_buf); + } + + fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr)); + if (fd == -1 && !do_log && log_buf && log_buf_size) { + do_log = true; + goto retry; + } + + return fd; +} + +int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, + __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, + __u64 *probe_addr) +{ + union bpf_attr attr = {}; + int err; + + attr.task_fd_query.pid = pid; + attr.task_fd_query.fd = fd; + attr.task_fd_query.flags = flags; + attr.task_fd_query.buf = ptr_to_u64(buf); + attr.task_fd_query.buf_len = *buf_len; + + err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr)); + *buf_len = attr.task_fd_query.buf_len; + *prog_id = attr.task_fd_query.prog_id; + *fd_type = attr.task_fd_query.fd_type; + *probe_offset = attr.task_fd_query.probe_offset; + *probe_addr = attr.task_fd_query.probe_addr; + + return err; +} diff --git a/src/bpf.h b/src/bpf.h new file mode 100644 index 0000000..87520a8 --- /dev/null +++ b/src/bpf.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * common eBPF ELF operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov + * Copyright (C) 2015 Wang Nan + * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see + */ +#ifndef __LIBBPF_BPF_H +#define __LIBBPF_BPF_H + +#include +#include +#include + +struct bpf_create_map_attr { + const char *name; + enum bpf_map_type map_type; + __u32 map_flags; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 numa_node; + __u32 btf_fd; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 map_ifindex; + __u32 inner_map_fd; +}; + +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node); +int bpf_create_map_name(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags); +int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, + int max_entries, __u32 map_flags); +int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags, int node); +int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags); + +struct bpf_load_program_attr { + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + const char *name; + const struct bpf_insn *insns; + size_t insns_cnt; + const char *license; + __u32 kern_version; + __u32 prog_ifindex; +}; + +/* Recommend log buffer size */ +#define BPF_LOG_BUF_SIZE (256 * 1024) +int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz); +int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz); +int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, int strict_alignment, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz, int log_level); + +int bpf_map_update_elem(int fd, const void *key, const void *value, + __u64 flags); + +int bpf_map_lookup_elem(int fd, const void *key, void *value); +int bpf_map_delete_elem(int fd, const void *key); +int bpf_map_get_next_key(int fd, const void *key, void *next_key); +int bpf_obj_pin(int fd, const char *pathname); +int bpf_obj_get(const char *pathname); +int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, + unsigned int flags); +int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); +int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); +int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, + void *data_out, __u32 *size_out, __u32 *retval, + __u32 *duration); +int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); +int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); +int bpf_prog_get_fd_by_id(__u32 id); +int bpf_map_get_fd_by_id(__u32 id); +int bpf_btf_get_fd_by_id(__u32 id); +int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); +int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, + __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); +int bpf_raw_tracepoint_open(const char *name, int prog_fd); +int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, + bool do_log); +int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, + __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, + __u64 *probe_addr); +#endif /* __LIBBPF_BPF_H */ diff --git a/src/btf.c b/src/btf.c new file mode 100644 index 0000000..449591a --- /dev/null +++ b/src/btf.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include +#include +#include +#include +#include +#include +#include "btf.h" +#include "bpf.h" + +#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); } +#define max(a, b) ((a) > (b) ? (a) : (b)) +#define min(a, b) ((a) < (b) ? (a) : (b)) + +#define BTF_MAX_NR_TYPES 65535 + +#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \ + ((k) == BTF_KIND_VOLATILE) || \ + ((k) == BTF_KIND_CONST) || \ + ((k) == BTF_KIND_RESTRICT)) + +static struct btf_type btf_void; + +struct btf { + union { + struct btf_header *hdr; + void *data; + }; + struct btf_type **types; + const char *strings; + void *nohdr_data; + __u32 nr_types; + __u32 types_size; + __u32 data_size; + int fd; +}; + +static int btf_add_type(struct btf *btf, struct btf_type *t) +{ + if (btf->types_size - btf->nr_types < 2) { + struct btf_type **new_types; + __u32 expand_by, new_size; + + if (btf->types_size == BTF_MAX_NR_TYPES) + return -E2BIG; + + expand_by = max(btf->types_size >> 2, 16); + new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); + + new_types = realloc(btf->types, sizeof(*new_types) * new_size); + if (!new_types) + return -ENOMEM; + + if (btf->nr_types == 0) + new_types[0] = &btf_void; + + btf->types = new_types; + btf->types_size = new_size; + } + + btf->types[++(btf->nr_types)] = t; + + return 0; +} + +static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log) +{ + const struct btf_header *hdr = btf->hdr; + __u32 meta_left; + + if (btf->data_size < sizeof(struct btf_header)) { + elog("BTF header not found\n"); + return -EINVAL; + } + + if (hdr->magic != BTF_MAGIC) { + elog("Invalid BTF magic:%x\n", hdr->magic); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + elog("Unsupported BTF version:%u\n", hdr->version); + return -ENOTSUP; + } + + if (hdr->flags) { + elog("Unsupported BTF flags:%x\n", hdr->flags); + return -ENOTSUP; + } + + meta_left = btf->data_size - sizeof(*hdr); + if (!meta_left) { + elog("BTF has no data\n"); + return -EINVAL; + } + + if (meta_left < hdr->type_off) { + elog("Invalid BTF type section offset:%u\n", hdr->type_off); + return -EINVAL; + } + + if (meta_left < hdr->str_off) { + elog("Invalid BTF string section offset:%u\n", hdr->str_off); + return -EINVAL; + } + + if (hdr->type_off >= hdr->str_off) { + elog("BTF type section offset >= string section offset. No type?\n"); + return -EINVAL; + } + + if (hdr->type_off & 0x02) { + elog("BTF type section is not aligned to 4 bytes\n"); + return -EINVAL; + } + + btf->nohdr_data = btf->hdr + 1; + + return 0; +} + +static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log) +{ + const struct btf_header *hdr = btf->hdr; + const char *start = btf->nohdr_data + hdr->str_off; + const char *end = start + btf->hdr->str_len; + + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || + start[0] || end[-1]) { + elog("Invalid BTF string section\n"); + return -EINVAL; + } + + btf->strings = start; + + return 0; +} + +static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) +{ + struct btf_header *hdr = btf->hdr; + void *nohdr_data = btf->nohdr_data; + void *next_type = nohdr_data + hdr->type_off; + void *end_type = nohdr_data + hdr->str_off; + + while (next_type < end_type) { + struct btf_type *t = next_type; + __u16 vlen = BTF_INFO_VLEN(t->info); + int err; + + next_type += sizeof(*t); + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + next_type += sizeof(int); + break; + case BTF_KIND_ARRAY: + next_type += sizeof(struct btf_array); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + next_type += vlen * sizeof(struct btf_member); + break; + case BTF_KIND_ENUM: + next_type += vlen * sizeof(struct btf_enum); + break; + case BTF_KIND_TYPEDEF: + case BTF_KIND_PTR: + case BTF_KIND_FWD: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + break; + default: + elog("Unsupported BTF_KIND:%u\n", + BTF_INFO_KIND(t->info)); + return -EINVAL; + } + + err = btf_add_type(btf, t); + if (err) + return err; + } + + return 0; +} + +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} + +static bool btf_type_is_void(const struct btf_type *t) +{ + return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + +static bool btf_type_is_void_or_null(const struct btf_type *t) +{ + return !t || btf_type_is_void(t); +} + +static __s64 btf_type_size(const struct btf_type *t) +{ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + return t->size; + case BTF_KIND_PTR: + return sizeof(void *); + default: + return -EINVAL; + } +} + +#define MAX_RESOLVE_DEPTH 32 + +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id) +{ + const struct btf_array *array; + const struct btf_type *t; + __u32 nelems = 1; + __s64 size = -1; + int i; + + t = btf__type_by_id(btf, type_id); + for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); + i++) { + size = btf_type_size(t); + if (size >= 0) + break; + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + type_id = t->type; + break; + case BTF_KIND_ARRAY: + array = (const struct btf_array *)(t + 1); + if (nelems && array->nelems > UINT32_MAX / nelems) + return -E2BIG; + nelems *= array->nelems; + type_id = array->type; + break; + default: + return -EINVAL; + } + + t = btf__type_by_id(btf, type_id); + } + + if (size < 0) + return -EINVAL; + + if (nelems && size > UINT32_MAX / nelems) + return -E2BIG; + + return nelems * size; +} + +int btf__resolve_type(const struct btf *btf, __u32 type_id) +{ + const struct btf_type *t; + int depth = 0; + + t = btf__type_by_id(btf, type_id); + while (depth < MAX_RESOLVE_DEPTH && + !btf_type_is_void_or_null(t) && + IS_MODIFIER(BTF_INFO_KIND(t->info))) { + type_id = t->type; + t = btf__type_by_id(btf, type_id); + depth++; + } + + if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t)) + return -EINVAL; + + return type_id; +} + +__s32 btf__find_by_name(const struct btf *btf, const char *type_name) +{ + __u32 i; + + if (!strcmp(type_name, "void")) + return 0; + + for (i = 1; i <= btf->nr_types; i++) { + const struct btf_type *t = btf->types[i]; + const char *name = btf__name_by_offset(btf, t->name_off); + + if (name && !strcmp(type_name, name)) + return i; + } + + return -ENOENT; +} + +void btf__free(struct btf *btf) +{ + if (!btf) + return; + + if (btf->fd != -1) + close(btf->fd); + + free(btf->data); + free(btf->types); + free(btf); +} + +struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log) +{ + __u32 log_buf_size = 0; + char *log_buf = NULL; + struct btf *btf; + int err; + + btf = calloc(1, sizeof(struct btf)); + if (!btf) + return ERR_PTR(-ENOMEM); + + btf->fd = -1; + + if (err_log) { + log_buf = malloc(BPF_LOG_BUF_SIZE); + if (!log_buf) { + err = -ENOMEM; + goto done; + } + *log_buf = 0; + log_buf_size = BPF_LOG_BUF_SIZE; + } + + btf->data = malloc(size); + if (!btf->data) { + err = -ENOMEM; + goto done; + } + + memcpy(btf->data, data, size); + btf->data_size = size; + + btf->fd = bpf_load_btf(btf->data, btf->data_size, + log_buf, log_buf_size, false); + + if (btf->fd == -1) { + err = -errno; + elog("Error loading BTF: %s(%d)\n", strerror(errno), errno); + if (log_buf && *log_buf) + elog("%s\n", log_buf); + goto done; + } + + err = btf_parse_hdr(btf, err_log); + if (err) + goto done; + + err = btf_parse_str_sec(btf, err_log); + if (err) + goto done; + + err = btf_parse_type_sec(btf, err_log); + +done: + free(log_buf); + + if (err) { + btf__free(btf); + return ERR_PTR(err); + } + + return btf; +} + +int btf__fd(const struct btf *btf) +{ + return btf->fd; +} + +const char *btf__name_by_offset(const struct btf *btf, __u32 offset) +{ + if (offset < btf->hdr->str_len) + return &btf->strings[offset]; + else + return NULL; +} diff --git a/src/btf.h b/src/btf.h new file mode 100644 index 0000000..6db5462 --- /dev/null +++ b/src/btf.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2018 Facebook */ + +#ifndef __LIBBPF_BTF_H +#define __LIBBPF_BTF_H + +#include + +#define BTF_ELF_SEC ".BTF" + +struct btf; +struct btf_type; + +typedef int (*btf_print_fn_t)(const char *, ...) + __attribute__((format(printf, 1, 2))); + +void btf__free(struct btf *btf); +struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log); +__s32 btf__find_by_name(const struct btf *btf, const char *type_name); +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id); +int btf__resolve_type(const struct btf *btf, __u32 type_id); +int btf__fd(const struct btf *btf); +const char *btf__name_by_offset(const struct btf *btf, __u32 offset); + +#endif /* __LIBBPF_BTF_H */ diff --git a/src/libbpf.c b/src/libbpf.c new file mode 100644 index 0000000..176cf55 --- /dev/null +++ b/src/libbpf.c @@ -0,0 +1,2465 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Common eBPF ELF object loading operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov + * Copyright (C) 2015 Wang Nan + * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "libbpf.h" +#include "bpf.h" +#include "btf.h" +#include "str_error.h" + +#ifndef EM_BPF +#define EM_BPF 247 +#endif + +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + +#define __printf(a, b) __attribute__((format(printf, a, b))) + +__printf(1, 2) +static int __base_pr(const char *format, ...) +{ + va_list args; + int err; + + va_start(args, format); + err = vfprintf(stderr, format, args); + va_end(args); + return err; +} + +static __printf(1, 2) libbpf_print_fn_t __pr_warning = __base_pr; +static __printf(1, 2) libbpf_print_fn_t __pr_info = __base_pr; +static __printf(1, 2) libbpf_print_fn_t __pr_debug; + +#define __pr(func, fmt, ...) \ +do { \ + if ((func)) \ + (func)("libbpf: " fmt, ##__VA_ARGS__); \ +} while (0) + +#define pr_warning(fmt, ...) __pr(__pr_warning, fmt, ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr(__pr_info, fmt, ##__VA_ARGS__) +#define pr_debug(fmt, ...) __pr(__pr_debug, fmt, ##__VA_ARGS__) + +void libbpf_set_print(libbpf_print_fn_t warn, + libbpf_print_fn_t info, + libbpf_print_fn_t debug) +{ + __pr_warning = warn; + __pr_info = info; + __pr_debug = debug; +} + +#define STRERR_BUFSIZE 128 + +#define CHECK_ERR(action, err, out) do { \ + err = action; \ + if (err) \ + goto out; \ +} while(0) + + +/* Copied from tools/perf/util/util.h */ +#ifndef zfree +# define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) +#endif + +#ifndef zclose +# define zclose(fd) ({ \ + int ___err = 0; \ + if ((fd) >= 0) \ + ___err = close((fd)); \ + fd = -1; \ + ___err; }) +#endif + +#ifdef HAVE_LIBELF_MMAP_SUPPORT +# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP +#else +# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ +#endif + +/* + * bpf_prog should be a better name but it has been used in + * linux/filter.h. + */ +struct bpf_program { + /* Index in elf obj file, for relocation use. */ + int idx; + char *name; + int prog_ifindex; + char *section_name; + struct bpf_insn *insns; + size_t insns_cnt, main_prog_cnt; + enum bpf_prog_type type; + + struct reloc_desc { + enum { + RELO_LD64, + RELO_CALL, + } type; + int insn_idx; + union { + int map_idx; + int text_off; + }; + } *reloc_desc; + int nr_reloc; + + struct { + int nr; + int *fds; + } instances; + bpf_program_prep_t preprocessor; + + struct bpf_object *obj; + void *priv; + bpf_program_clear_priv_t clear_priv; + + enum bpf_attach_type expected_attach_type; +}; + +struct bpf_map { + int fd; + char *name; + size_t offset; + int map_ifindex; + struct bpf_map_def def; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + void *priv; + bpf_map_clear_priv_t clear_priv; +}; + +static LIST_HEAD(bpf_objects_list); + +struct bpf_object { + char license[64]; + __u32 kern_version; + + struct bpf_program *programs; + size_t nr_programs; + struct bpf_map *maps; + size_t nr_maps; + + bool loaded; + bool has_pseudo_calls; + + /* + * Information when doing elf related work. Only valid if fd + * is valid. + */ + struct { + int fd; + void *obj_buf; + size_t obj_buf_sz; + Elf *elf; + GElf_Ehdr ehdr; + Elf_Data *symbols; + size_t strtabidx; + struct { + GElf_Shdr shdr; + Elf_Data *data; + } *reloc; + int nr_reloc; + int maps_shndx; + int text_shndx; + } efile; + /* + * All loaded bpf_object is linked in a list, which is + * hidden to caller. bpf_objects__ handlers deal with + * all objects. + */ + struct list_head list; + + struct btf *btf; + + void *priv; + bpf_object_clear_priv_t clear_priv; + + char path[]; +}; +#define obj_elf_valid(o) ((o)->efile.elf) + +void bpf_program__unload(struct bpf_program *prog) +{ + int i; + + if (!prog) + return; + + /* + * If the object is opened but the program was never loaded, + * it is possible that prog->instances.nr == -1. + */ + if (prog->instances.nr > 0) { + for (i = 0; i < prog->instances.nr; i++) + zclose(prog->instances.fds[i]); + } else if (prog->instances.nr != -1) { + pr_warning("Internal error: instances.nr is %d\n", + prog->instances.nr); + } + + prog->instances.nr = -1; + zfree(&prog->instances.fds); +} + +static void bpf_program__exit(struct bpf_program *prog) +{ + if (!prog) + return; + + if (prog->clear_priv) + prog->clear_priv(prog, prog->priv); + + prog->priv = NULL; + prog->clear_priv = NULL; + + bpf_program__unload(prog); + zfree(&prog->name); + zfree(&prog->section_name); + zfree(&prog->insns); + zfree(&prog->reloc_desc); + + prog->nr_reloc = 0; + prog->insns_cnt = 0; + prog->idx = -1; +} + +static int +bpf_program__init(void *data, size_t size, char *section_name, int idx, + struct bpf_program *prog) +{ + if (size < sizeof(struct bpf_insn)) { + pr_warning("corrupted section '%s'\n", section_name); + return -EINVAL; + } + + bzero(prog, sizeof(*prog)); + + prog->section_name = strdup(section_name); + if (!prog->section_name) { + pr_warning("failed to alloc name for prog under section(%d) %s\n", + idx, section_name); + goto errout; + } + + prog->insns = malloc(size); + if (!prog->insns) { + pr_warning("failed to alloc insns for prog under section %s\n", + section_name); + goto errout; + } + prog->insns_cnt = size / sizeof(struct bpf_insn); + memcpy(prog->insns, data, + prog->insns_cnt * sizeof(struct bpf_insn)); + prog->idx = idx; + prog->instances.fds = NULL; + prog->instances.nr = -1; + prog->type = BPF_PROG_TYPE_KPROBE; + + return 0; +errout: + bpf_program__exit(prog); + return -ENOMEM; +} + +static int +bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, + char *section_name, int idx) +{ + struct bpf_program prog, *progs; + int nr_progs, err; + + err = bpf_program__init(data, size, section_name, idx, &prog); + if (err) + return err; + + progs = obj->programs; + nr_progs = obj->nr_programs; + + progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0])); + if (!progs) { + /* + * In this case the original obj->programs + * is still valid, so don't need special treat for + * bpf_close_object(). + */ + pr_warning("failed to alloc a new program under section '%s'\n", + section_name); + bpf_program__exit(&prog); + return -ENOMEM; + } + + pr_debug("found program %s\n", prog.section_name); + obj->programs = progs; + obj->nr_programs = nr_progs + 1; + prog.obj = obj; + progs[nr_progs] = prog; + return 0; +} + +static int +bpf_object__init_prog_names(struct bpf_object *obj) +{ + Elf_Data *symbols = obj->efile.symbols; + struct bpf_program *prog; + size_t pi, si; + + for (pi = 0; pi < obj->nr_programs; pi++) { + const char *name = NULL; + + prog = &obj->programs[pi]; + + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; + si++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, si, &sym)) + continue; + if (sym.st_shndx != prog->idx) + continue; + if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL) + continue; + + name = elf_strptr(obj->efile.elf, + obj->efile.strtabidx, + sym.st_name); + if (!name) { + pr_warning("failed to get sym name string for prog %s\n", + prog->section_name); + return -LIBBPF_ERRNO__LIBELF; + } + } + + if (!name && prog->idx == obj->efile.text_shndx) + name = ".text"; + + if (!name) { + pr_warning("failed to find sym for prog %s\n", + prog->section_name); + return -EINVAL; + } + + prog->name = strdup(name); + if (!prog->name) { + pr_warning("failed to allocate memory for prog sym %s\n", + name); + return -ENOMEM; + } + } + + return 0; +} + +static struct bpf_object *bpf_object__new(const char *path, + void *obj_buf, + size_t obj_buf_sz) +{ + struct bpf_object *obj; + + obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1); + if (!obj) { + pr_warning("alloc memory failed for %s\n", path); + return ERR_PTR(-ENOMEM); + } + + strcpy(obj->path, path); + obj->efile.fd = -1; + + /* + * Caller of this function should also calls + * bpf_object__elf_finish() after data collection to return + * obj_buf to user. If not, we should duplicate the buffer to + * avoid user freeing them before elf finish. + */ + obj->efile.obj_buf = obj_buf; + obj->efile.obj_buf_sz = obj_buf_sz; + obj->efile.maps_shndx = -1; + + obj->loaded = false; + + INIT_LIST_HEAD(&obj->list); + list_add(&obj->list, &bpf_objects_list); + return obj; +} + +static void bpf_object__elf_finish(struct bpf_object *obj) +{ + if (!obj_elf_valid(obj)) + return; + + if (obj->efile.elf) { + elf_end(obj->efile.elf); + obj->efile.elf = NULL; + } + obj->efile.symbols = NULL; + + zfree(&obj->efile.reloc); + obj->efile.nr_reloc = 0; + zclose(obj->efile.fd); + obj->efile.obj_buf = NULL; + obj->efile.obj_buf_sz = 0; +} + +static int bpf_object__elf_init(struct bpf_object *obj) +{ + int err = 0; + GElf_Ehdr *ep; + + if (obj_elf_valid(obj)) { + pr_warning("elf init: internal error\n"); + return -LIBBPF_ERRNO__LIBELF; + } + + if (obj->efile.obj_buf_sz > 0) { + /* + * obj_buf should have been validated by + * bpf_object__open_buffer(). + */ + obj->efile.elf = elf_memory(obj->efile.obj_buf, + obj->efile.obj_buf_sz); + } else { + obj->efile.fd = open(obj->path, O_RDONLY); + if (obj->efile.fd < 0) { + char errmsg[STRERR_BUFSIZE]; + char *cp = libbpf_strerror_r(errno, errmsg, + sizeof(errmsg)); + + pr_warning("failed to open %s: %s\n", obj->path, cp); + return -errno; + } + + obj->efile.elf = elf_begin(obj->efile.fd, + LIBBPF_ELF_C_READ_MMAP, + NULL); + } + + if (!obj->efile.elf) { + pr_warning("failed to open %s as ELF file\n", + obj->path); + err = -LIBBPF_ERRNO__LIBELF; + goto errout; + } + + if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) { + pr_warning("failed to get EHDR from %s\n", + obj->path); + err = -LIBBPF_ERRNO__FORMAT; + goto errout; + } + ep = &obj->efile.ehdr; + + /* Old LLVM set e_machine to EM_NONE */ + if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) { + pr_warning("%s is not an eBPF object file\n", + obj->path); + err = -LIBBPF_ERRNO__FORMAT; + goto errout; + } + + return 0; +errout: + bpf_object__elf_finish(obj); + return err; +} + +static int +bpf_object__check_endianness(struct bpf_object *obj) +{ + static unsigned int const endian = 1; + + switch (obj->efile.ehdr.e_ident[EI_DATA]) { + case ELFDATA2LSB: + /* We are big endian, BPF obj is little endian. */ + if (*(unsigned char const *)&endian != 1) + goto mismatch; + break; + + case ELFDATA2MSB: + /* We are little endian, BPF obj is big endian. */ + if (*(unsigned char const *)&endian != 0) + goto mismatch; + break; + default: + return -LIBBPF_ERRNO__ENDIAN; + } + + return 0; + +mismatch: + pr_warning("Error: endianness mismatch.\n"); + return -LIBBPF_ERRNO__ENDIAN; +} + +static int +bpf_object__init_license(struct bpf_object *obj, + void *data, size_t size) +{ + memcpy(obj->license, data, + min(size, sizeof(obj->license) - 1)); + pr_debug("license of %s is %s\n", obj->path, obj->license); + return 0; +} + +static int +bpf_object__init_kversion(struct bpf_object *obj, + void *data, size_t size) +{ + __u32 kver; + + if (size != sizeof(kver)) { + pr_warning("invalid kver section in %s\n", obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + memcpy(&kver, data, sizeof(kver)); + obj->kern_version = kver; + pr_debug("kernel version of %s is %x\n", obj->path, + obj->kern_version); + return 0; +} + +static int compare_bpf_map(const void *_a, const void *_b) +{ + const struct bpf_map *a = _a; + const struct bpf_map *b = _b; + + return a->offset - b->offset; +} + +static int +bpf_object__init_maps(struct bpf_object *obj) +{ + int i, map_idx, map_def_sz, nr_maps = 0; + Elf_Scn *scn; + Elf_Data *data; + Elf_Data *symbols = obj->efile.symbols; + + if (obj->efile.maps_shndx < 0) + return -EINVAL; + if (!symbols) + return -EINVAL; + + scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); + return -EINVAL; + } + + /* + * Count number of maps. Each map has a name. + * Array of maps is not supported: only the first element is + * considered. + * + * TODO: Detect array of map and report error. + */ + for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, i, &sym)) + continue; + if (sym.st_shndx != obj->efile.maps_shndx) + continue; + nr_maps++; + } + + /* Alloc obj->maps and fill nr_maps. */ + pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, + nr_maps, data->d_size); + + if (!nr_maps) + return 0; + + /* Assume equally sized map definitions */ + map_def_sz = data->d_size / nr_maps; + if (!data->d_size || (data->d_size % nr_maps) != 0) { + pr_warning("unable to determine map definition size " + "section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; + } + + obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); + if (!obj->maps) { + pr_warning("alloc maps for object failed\n"); + return -ENOMEM; + } + obj->nr_maps = nr_maps; + + /* + * fill all fd with -1 so won't close incorrect + * fd (fd=0 is stdin) when failure (zclose won't close + * negative fd)). + */ + for (i = 0; i < nr_maps; i++) + obj->maps[i].fd = -1; + + /* + * Fill obj->maps using data in "maps" section. + */ + for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + GElf_Sym sym; + const char *map_name; + struct bpf_map_def *def; + + if (!gelf_getsym(symbols, i, &sym)) + continue; + if (sym.st_shndx != obj->efile.maps_shndx) + continue; + + map_name = elf_strptr(obj->efile.elf, + obj->efile.strtabidx, + sym.st_name); + obj->maps[map_idx].offset = sym.st_value; + if (sym.st_value + map_def_sz > data->d_size) { + pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", + obj->path, map_name); + return -EINVAL; + } + + obj->maps[map_idx].name = strdup(map_name); + if (!obj->maps[map_idx].name) { + pr_warning("failed to alloc map name\n"); + return -ENOMEM; + } + pr_debug("map %d is \"%s\"\n", map_idx, + obj->maps[map_idx].name); + def = (struct bpf_map_def *)(data->d_buf + sym.st_value); + /* + * If the definition of the map in the object file fits in + * bpf_map_def, copy it. Any extra fields in our version + * of bpf_map_def will default to zero as a result of the + * calloc above. + */ + if (map_def_sz <= sizeof(struct bpf_map_def)) { + memcpy(&obj->maps[map_idx].def, def, map_def_sz); + } else { + /* + * Here the map structure being read is bigger than what + * we expect, truncate if the excess bits are all zero. + * If they are not zero, reject this map as + * incompatible. + */ + char *b; + for (b = ((char *)def) + sizeof(struct bpf_map_def); + b < ((char *)def) + map_def_sz; b++) { + if (*b != 0) { + pr_warning("maps section in %s: \"%s\" " + "has unrecognized, non-zero " + "options\n", + obj->path, map_name); + return -EINVAL; + } + } + memcpy(&obj->maps[map_idx].def, def, + sizeof(struct bpf_map_def)); + } + map_idx++; + } + + qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); + return 0; +} + +static bool section_have_execinstr(struct bpf_object *obj, int idx) +{ + Elf_Scn *scn; + GElf_Shdr sh; + + scn = elf_getscn(obj->efile.elf, idx); + if (!scn) + return false; + + if (gelf_getshdr(scn, &sh) != &sh) + return false; + + if (sh.sh_flags & SHF_EXECINSTR) + return true; + + return false; +} + +static int bpf_object__elf_collect(struct bpf_object *obj) +{ + Elf *elf = obj->efile.elf; + GElf_Ehdr *ep = &obj->efile.ehdr; + Elf_Scn *scn = NULL; + int idx = 0, err = 0; + + /* Elf is corrupted/truncated, avoid calling elf_strptr. */ + if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { + pr_warning("failed to get e_shstrndx from %s\n", + obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + char *name; + GElf_Shdr sh; + Elf_Data *data; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warning("failed to get section(%d) header from %s\n", + idx, obj->path); + err = -LIBBPF_ERRNO__FORMAT; + goto out; + } + + name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); + if (!name) { + pr_warning("failed to get section(%d) name from %s\n", + idx, obj->path); + err = -LIBBPF_ERRNO__FORMAT; + goto out; + } + + data = elf_getdata(scn, 0); + if (!data) { + pr_warning("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); + err = -LIBBPF_ERRNO__FORMAT; + goto out; + } + pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", + idx, name, (unsigned long)data->d_size, + (int)sh.sh_link, (unsigned long)sh.sh_flags, + (int)sh.sh_type); + + if (strcmp(name, "license") == 0) + err = bpf_object__init_license(obj, + data->d_buf, + data->d_size); + else if (strcmp(name, "version") == 0) + err = bpf_object__init_kversion(obj, + data->d_buf, + data->d_size); + else if (strcmp(name, "maps") == 0) + obj->efile.maps_shndx = idx; + else if (strcmp(name, BTF_ELF_SEC) == 0) { + obj->btf = btf__new(data->d_buf, data->d_size, + __pr_debug); + if (IS_ERR(obj->btf)) { + pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_ELF_SEC, PTR_ERR(obj->btf)); + obj->btf = NULL; + } + } else if (sh.sh_type == SHT_SYMTAB) { + if (obj->efile.symbols) { + pr_warning("bpf: multiple SYMTAB in %s\n", + obj->path); + err = -LIBBPF_ERRNO__FORMAT; + } else { + obj->efile.symbols = data; + obj->efile.strtabidx = sh.sh_link; + } + } else if ((sh.sh_type == SHT_PROGBITS) && + (sh.sh_flags & SHF_EXECINSTR) && + (data->d_size > 0)) { + if (strcmp(name, ".text") == 0) + obj->efile.text_shndx = idx; + err = bpf_object__add_program(obj, data->d_buf, + data->d_size, name, idx); + if (err) { + char errmsg[STRERR_BUFSIZE]; + char *cp = libbpf_strerror_r(-err, errmsg, + sizeof(errmsg)); + + pr_warning("failed to alloc program %s (%s): %s", + name, obj->path, cp); + } + } else if (sh.sh_type == SHT_REL) { + void *reloc = obj->efile.reloc; + int nr_reloc = obj->efile.nr_reloc + 1; + int sec = sh.sh_info; /* points to other section */ + + /* Only do relo for section with exec instructions */ + if (!section_have_execinstr(obj, sec)) { + pr_debug("skip relo %s(%d) for section(%d)\n", + name, idx, sec); + continue; + } + + reloc = reallocarray(reloc, nr_reloc, + sizeof(*obj->efile.reloc)); + if (!reloc) { + pr_warning("realloc failed\n"); + err = -ENOMEM; + } else { + int n = nr_reloc - 1; + + obj->efile.reloc = reloc; + obj->efile.nr_reloc = nr_reloc; + + obj->efile.reloc[n].shdr = sh; + obj->efile.reloc[n].data = data; + } + } else { + pr_debug("skip section(%d) %s\n", idx, name); + } + if (err) + goto out; + } + + if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) { + pr_warning("Corrupted ELF file: index of strtab invalid\n"); + return LIBBPF_ERRNO__FORMAT; + } + if (obj->efile.maps_shndx >= 0) { + err = bpf_object__init_maps(obj); + if (err) + goto out; + } + err = bpf_object__init_prog_names(obj); +out: + return err; +} + +static struct bpf_program * +bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) +{ + struct bpf_program *prog; + size_t i; + + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + if (prog->idx == idx) + return prog; + } + return NULL; +} + +struct bpf_program * +bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) +{ + struct bpf_program *pos; + + bpf_object__for_each_program(pos, obj) { + if (pos->section_name && !strcmp(pos->section_name, title)) + return pos; + } + return NULL; +} + +static int +bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, + Elf_Data *data, struct bpf_object *obj) +{ + Elf_Data *symbols = obj->efile.symbols; + int text_shndx = obj->efile.text_shndx; + int maps_shndx = obj->efile.maps_shndx; + struct bpf_map *maps = obj->maps; + size_t nr_maps = obj->nr_maps; + int i, nrels; + + pr_debug("collecting relocating info for: '%s'\n", + prog->section_name); + nrels = shdr->sh_size / shdr->sh_entsize; + + prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels); + if (!prog->reloc_desc) { + pr_warning("failed to alloc memory in relocation\n"); + return -ENOMEM; + } + prog->nr_reloc = nrels; + + for (i = 0; i < nrels; i++) { + GElf_Sym sym; + GElf_Rel rel; + unsigned int insn_idx; + struct bpf_insn *insns = prog->insns; + size_t map_idx; + + if (!gelf_getrel(data, i, &rel)) { + pr_warning("relocation: failed to get %d reloc\n", i); + return -LIBBPF_ERRNO__FORMAT; + } + + if (!gelf_getsym(symbols, + GELF_R_SYM(rel.r_info), + &sym)) { + pr_warning("relocation: symbol %"PRIx64" not found\n", + GELF_R_SYM(rel.r_info)); + return -LIBBPF_ERRNO__FORMAT; + } + pr_debug("relo for %lld value %lld name %d\n", + (long long) (rel.r_info >> 32), + (long long) sym.st_value, sym.st_name); + + if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) { + pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", + prog->section_name, sym.st_shndx); + return -LIBBPF_ERRNO__RELOC; + } + + insn_idx = rel.r_offset / sizeof(struct bpf_insn); + pr_debug("relocation: insn_idx=%u\n", insn_idx); + + if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) { + if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) { + pr_warning("incorrect bpf_call opcode\n"); + return -LIBBPF_ERRNO__RELOC; + } + prog->reloc_desc[i].type = RELO_CALL; + prog->reloc_desc[i].insn_idx = insn_idx; + prog->reloc_desc[i].text_off = sym.st_value; + obj->has_pseudo_calls = true; + continue; + } + + if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { + pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n", + insn_idx, insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; + } + + /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */ + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + if (maps[map_idx].offset == sym.st_value) { + pr_debug("relocation: find map %zd (%s) for insn %u\n", + map_idx, maps[map_idx].name, insn_idx); + break; + } + } + + if (map_idx >= nr_maps) { + pr_warning("bpf relocation: map_idx %d large than %d\n", + (int)map_idx, (int)nr_maps - 1); + return -LIBBPF_ERRNO__RELOC; + } + + prog->reloc_desc[i].type = RELO_LD64; + prog->reloc_desc[i].insn_idx = insn_idx; + prog->reloc_desc[i].map_idx = map_idx; + } + return 0; +} + +static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) +{ + const struct btf_type *container_type; + const struct btf_member *key, *value; + struct bpf_map_def *def = &map->def; + const size_t max_name = 256; + char container_name[max_name]; + __s64 key_size, value_size; + __s32 container_id; + + if (snprintf(container_name, max_name, "____btf_map_%s", map->name) == + max_name) { + pr_warning("map:%s length of '____btf_map_%s' is too long\n", + map->name, map->name); + return -EINVAL; + } + + container_id = btf__find_by_name(btf, container_name); + if (container_id < 0) { + pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n", + map->name, container_name); + return container_id; + } + + container_type = btf__type_by_id(btf, container_id); + if (!container_type) { + pr_warning("map:%s cannot find BTF type for container_id:%u\n", + map->name, container_id); + return -EINVAL; + } + + if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || + BTF_INFO_VLEN(container_type->info) < 2) { + pr_warning("map:%s container_name:%s is an invalid container struct\n", + map->name, container_name); + return -EINVAL; + } + + key = (struct btf_member *)(container_type + 1); + value = key + 1; + + key_size = btf__resolve_size(btf, key->type); + if (key_size < 0) { + pr_warning("map:%s invalid BTF key_type_size\n", + map->name); + return key_size; + } + + if (def->key_size != key_size) { + pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", + map->name, (__u32)key_size, def->key_size); + return -EINVAL; + } + + value_size = btf__resolve_size(btf, value->type); + if (value_size < 0) { + pr_warning("map:%s invalid BTF value_type_size\n", map->name); + return value_size; + } + + if (def->value_size != value_size) { + pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", + map->name, (__u32)value_size, def->value_size); + return -EINVAL; + } + + map->btf_key_type_id = key->type; + map->btf_value_type_id = value->type; + + return 0; +} + +int bpf_map__reuse_fd(struct bpf_map *map, int fd) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int new_fd, err; + char *new_name; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) + return err; + + new_name = strdup(info.name); + if (!new_name) + return -errno; + + new_fd = open("/", O_RDONLY | O_CLOEXEC); + if (new_fd < 0) + goto err_free_new_name; + + new_fd = dup3(fd, new_fd, O_CLOEXEC); + if (new_fd < 0) + goto err_close_new_fd; + + err = zclose(map->fd); + if (err) + goto err_close_new_fd; + free(map->name); + + map->fd = new_fd; + map->name = new_name; + map->def.type = info.type; + map->def.key_size = info.key_size; + map->def.value_size = info.value_size; + map->def.max_entries = info.max_entries; + map->def.map_flags = info.map_flags; + map->btf_key_type_id = info.btf_key_type_id; + map->btf_value_type_id = info.btf_value_type_id; + + return 0; + +err_close_new_fd: + close(new_fd); +err_free_new_name: + free(new_name); + return -errno; +} + +static int +bpf_object__create_maps(struct bpf_object *obj) +{ + struct bpf_create_map_attr create_attr = {}; + unsigned int i; + int err; + + for (i = 0; i < obj->nr_maps; i++) { + struct bpf_map *map = &obj->maps[i]; + struct bpf_map_def *def = &map->def; + char *cp, errmsg[STRERR_BUFSIZE]; + int *pfd = &map->fd; + + if (map->fd >= 0) { + pr_debug("skip map create (preset) %s: fd=%d\n", + map->name, map->fd); + continue; + } + + create_attr.name = map->name; + create_attr.map_ifindex = map->map_ifindex; + create_attr.map_type = def->type; + create_attr.map_flags = def->map_flags; + create_attr.key_size = def->key_size; + create_attr.value_size = def->value_size; + create_attr.max_entries = def->max_entries; + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + + if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) { + create_attr.btf_fd = btf__fd(obj->btf); + create_attr.btf_key_type_id = map->btf_key_type_id; + create_attr.btf_value_type_id = map->btf_value_type_id; + } + + *pfd = bpf_create_map_xattr(&create_attr); + if (*pfd < 0 && create_attr.btf_key_type_id) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", + map->name, cp, errno); + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + *pfd = bpf_create_map_xattr(&create_attr); + } + + if (*pfd < 0) { + size_t j; + + err = *pfd; + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("failed to create map (name: '%s'): %s\n", + map->name, cp); + for (j = 0; j < i; j++) + zclose(obj->maps[j].fd); + return err; + } + pr_debug("create map %s: fd=%d\n", map->name, *pfd); + } + + return 0; +} + +static int +bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, + struct reloc_desc *relo) +{ + struct bpf_insn *insn, *new_insn; + struct bpf_program *text; + size_t new_cnt; + + if (relo->type != RELO_CALL) + return -LIBBPF_ERRNO__RELOC; + + if (prog->idx == obj->efile.text_shndx) { + pr_warning("relo in .text insn %d into off %d\n", + relo->insn_idx, relo->text_off); + return -LIBBPF_ERRNO__RELOC; + } + + if (prog->main_prog_cnt == 0) { + text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx); + if (!text) { + pr_warning("no .text section found yet relo into text exist\n"); + return -LIBBPF_ERRNO__RELOC; + } + new_cnt = prog->insns_cnt + text->insns_cnt; + new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn)); + if (!new_insn) { + pr_warning("oom in prog realloc\n"); + return -ENOMEM; + } + memcpy(new_insn + prog->insns_cnt, text->insns, + text->insns_cnt * sizeof(*insn)); + prog->insns = new_insn; + prog->main_prog_cnt = prog->insns_cnt; + prog->insns_cnt = new_cnt; + pr_debug("added %zd insn from %s to prog %s\n", + text->insns_cnt, text->section_name, + prog->section_name); + } + insn = &prog->insns[relo->insn_idx]; + insn->imm += prog->main_prog_cnt - relo->insn_idx; + return 0; +} + +static int +bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) +{ + int i, err; + + if (!prog || !prog->reloc_desc) + return 0; + + for (i = 0; i < prog->nr_reloc; i++) { + if (prog->reloc_desc[i].type == RELO_LD64) { + struct bpf_insn *insns = prog->insns; + int insn_idx, map_idx; + + insn_idx = prog->reloc_desc[i].insn_idx; + map_idx = prog->reloc_desc[i].map_idx; + + if (insn_idx >= (int)prog->insns_cnt) { + pr_warning("relocation out of range: '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__RELOC; + } + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + insns[insn_idx].imm = obj->maps[map_idx].fd; + } else { + err = bpf_program__reloc_text(prog, obj, + &prog->reloc_desc[i]); + if (err) + return err; + } + } + + zfree(&prog->reloc_desc); + prog->nr_reloc = 0; + return 0; +} + + +static int +bpf_object__relocate(struct bpf_object *obj) +{ + struct bpf_program *prog; + size_t i; + int err; + + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + + err = bpf_program__relocate(prog, obj); + if (err) { + pr_warning("failed to relocate '%s'\n", + prog->section_name); + return err; + } + } + return 0; +} + +static int bpf_object__collect_reloc(struct bpf_object *obj) +{ + int i, err; + + if (!obj_elf_valid(obj)) { + pr_warning("Internal error: elf object is closed\n"); + return -LIBBPF_ERRNO__INTERNAL; + } + + for (i = 0; i < obj->efile.nr_reloc; i++) { + GElf_Shdr *shdr = &obj->efile.reloc[i].shdr; + Elf_Data *data = obj->efile.reloc[i].data; + int idx = shdr->sh_info; + struct bpf_program *prog; + + if (shdr->sh_type != SHT_REL) { + pr_warning("internal error at %d\n", __LINE__); + return -LIBBPF_ERRNO__INTERNAL; + } + + prog = bpf_object__find_prog_by_idx(obj, idx); + if (!prog) { + pr_warning("relocation failed: no section(%d)\n", idx); + return -LIBBPF_ERRNO__RELOC; + } + + err = bpf_program__collect_reloc(prog, + shdr, data, + obj); + if (err) + return err; + } + return 0; +} + +static int +load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, + const char *name, struct bpf_insn *insns, int insns_cnt, + char *license, __u32 kern_version, int *pfd, int prog_ifindex) +{ + struct bpf_load_program_attr load_attr; + char *cp, errmsg[STRERR_BUFSIZE]; + char *log_buf; + int ret; + + memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); + load_attr.prog_type = type; + load_attr.expected_attach_type = expected_attach_type; + load_attr.name = name; + load_attr.insns = insns; + load_attr.insns_cnt = insns_cnt; + load_attr.license = license; + load_attr.kern_version = kern_version; + load_attr.prog_ifindex = prog_ifindex; + + if (!load_attr.insns || !load_attr.insns_cnt) + return -EINVAL; + + log_buf = malloc(BPF_LOG_BUF_SIZE); + if (!log_buf) + pr_warning("Alloc log buffer for bpf loader error, continue without log\n"); + + ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE); + + if (ret >= 0) { + *pfd = ret; + ret = 0; + goto out; + } + + ret = -LIBBPF_ERRNO__LOAD; + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("load bpf program failed: %s\n", cp); + + if (log_buf && log_buf[0] != '\0') { + ret = -LIBBPF_ERRNO__VERIFY; + pr_warning("-- BEGIN DUMP LOG ---\n"); + pr_warning("\n%s\n", log_buf); + pr_warning("-- END LOG --\n"); + } else if (load_attr.insns_cnt >= BPF_MAXINSNS) { + pr_warning("Program too large (%zu insns), at most %d insns\n", + load_attr.insns_cnt, BPF_MAXINSNS); + ret = -LIBBPF_ERRNO__PROG2BIG; + } else { + /* Wrong program type? */ + if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) { + int fd; + + load_attr.prog_type = BPF_PROG_TYPE_KPROBE; + load_attr.expected_attach_type = 0; + fd = bpf_load_program_xattr(&load_attr, NULL, 0); + if (fd >= 0) { + close(fd); + ret = -LIBBPF_ERRNO__PROGTYPE; + goto out; + } + } + + if (log_buf) + ret = -LIBBPF_ERRNO__KVER; + } + +out: + free(log_buf); + return ret; +} + +int +bpf_program__load(struct bpf_program *prog, + char *license, __u32 kern_version) +{ + int err = 0, fd, i; + + if (prog->instances.nr < 0 || !prog->instances.fds) { + if (prog->preprocessor) { + pr_warning("Internal error: can't load program '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__INTERNAL; + } + + prog->instances.fds = malloc(sizeof(int)); + if (!prog->instances.fds) { + pr_warning("Not enough memory for BPF fds\n"); + return -ENOMEM; + } + prog->instances.nr = 1; + prog->instances.fds[0] = -1; + } + + if (!prog->preprocessor) { + if (prog->instances.nr != 1) { + pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n", + prog->section_name, prog->instances.nr); + } + err = load_program(prog->type, prog->expected_attach_type, + prog->name, prog->insns, prog->insns_cnt, + license, kern_version, &fd, + prog->prog_ifindex); + if (!err) + prog->instances.fds[0] = fd; + goto out; + } + + for (i = 0; i < prog->instances.nr; i++) { + struct bpf_prog_prep_result result; + bpf_program_prep_t preprocessor = prog->preprocessor; + + bzero(&result, sizeof(result)); + err = preprocessor(prog, i, prog->insns, + prog->insns_cnt, &result); + if (err) { + pr_warning("Preprocessing the %dth instance of program '%s' failed\n", + i, prog->section_name); + goto out; + } + + if (!result.new_insn_ptr || !result.new_insn_cnt) { + pr_debug("Skip loading the %dth instance of program '%s'\n", + i, prog->section_name); + prog->instances.fds[i] = -1; + if (result.pfd) + *result.pfd = -1; + continue; + } + + err = load_program(prog->type, prog->expected_attach_type, + prog->name, result.new_insn_ptr, + result.new_insn_cnt, + license, kern_version, &fd, + prog->prog_ifindex); + + if (err) { + pr_warning("Loading the %dth instance of program '%s' failed\n", + i, prog->section_name); + goto out; + } + + if (result.pfd) + *result.pfd = fd; + prog->instances.fds[i] = fd; + } +out: + if (err) + pr_warning("failed to load program '%s'\n", + prog->section_name); + zfree(&prog->insns); + prog->insns_cnt = 0; + return err; +} + +static bool bpf_program__is_function_storage(struct bpf_program *prog, + struct bpf_object *obj) +{ + return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls; +} + +static int +bpf_object__load_progs(struct bpf_object *obj) +{ + size_t i; + int err; + + for (i = 0; i < obj->nr_programs; i++) { + if (bpf_program__is_function_storage(&obj->programs[i], obj)) + continue; + err = bpf_program__load(&obj->programs[i], + obj->license, + obj->kern_version); + if (err) + return err; + } + return 0; +} + +static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_SOCKET_FILTER: + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_XDP: + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_LWT_IN: + case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: + case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_SK_SKB: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_LIRC_MODE2: + case BPF_PROG_TYPE_SK_REUSEPORT: + case BPF_PROG_TYPE_FLOW_DISSECTOR: + return false; + case BPF_PROG_TYPE_UNSPEC: + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + default: + return true; + } +} + +static int bpf_object__validate(struct bpf_object *obj, bool needs_kver) +{ + if (needs_kver && obj->kern_version == 0) { + pr_warning("%s doesn't provide kernel version\n", + obj->path); + return -LIBBPF_ERRNO__KVERSION; + } + return 0; +} + +static struct bpf_object * +__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, + bool needs_kver) +{ + struct bpf_object *obj; + int err; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warning("failed to init libelf for %s\n", path); + return ERR_PTR(-LIBBPF_ERRNO__LIBELF); + } + + obj = bpf_object__new(path, obj_buf, obj_buf_sz); + if (IS_ERR(obj)) + return obj; + + CHECK_ERR(bpf_object__elf_init(obj), err, out); + CHECK_ERR(bpf_object__check_endianness(obj), err, out); + CHECK_ERR(bpf_object__elf_collect(obj), err, out); + CHECK_ERR(bpf_object__collect_reloc(obj), err, out); + CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); + + bpf_object__elf_finish(obj); + return obj; +out: + bpf_object__close(obj); + return ERR_PTR(err); +} + +struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) +{ + /* param validation */ + if (!attr->file) + return NULL; + + pr_debug("loading %s\n", attr->file); + + return __bpf_object__open(attr->file, NULL, 0, + bpf_prog_type__needs_kver(attr->prog_type)); +} + +struct bpf_object *bpf_object__open(const char *path) +{ + struct bpf_object_open_attr attr = { + .file = path, + .prog_type = BPF_PROG_TYPE_UNSPEC, + }; + + return bpf_object__open_xattr(&attr); +} + +struct bpf_object *bpf_object__open_buffer(void *obj_buf, + size_t obj_buf_sz, + const char *name) +{ + char tmp_name[64]; + + /* param validation */ + if (!obj_buf || obj_buf_sz <= 0) + return NULL; + + if (!name) { + snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx", + (unsigned long)obj_buf, + (unsigned long)obj_buf_sz); + tmp_name[sizeof(tmp_name) - 1] = '\0'; + name = tmp_name; + } + pr_debug("loading object '%s' from buffer\n", + name); + + return __bpf_object__open(name, obj_buf, obj_buf_sz, true); +} + +int bpf_object__unload(struct bpf_object *obj) +{ + size_t i; + + if (!obj) + return -EINVAL; + + for (i = 0; i < obj->nr_maps; i++) + zclose(obj->maps[i].fd); + + for (i = 0; i < obj->nr_programs; i++) + bpf_program__unload(&obj->programs[i]); + + return 0; +} + +int bpf_object__load(struct bpf_object *obj) +{ + int err; + + if (!obj) + return -EINVAL; + + if (obj->loaded) { + pr_warning("object should not be loaded twice\n"); + return -EINVAL; + } + + obj->loaded = true; + + CHECK_ERR(bpf_object__create_maps(obj), err, out); + CHECK_ERR(bpf_object__relocate(obj), err, out); + CHECK_ERR(bpf_object__load_progs(obj), err, out); + + return 0; +out: + bpf_object__unload(obj); + pr_warning("failed to load object '%s'\n", obj->path); + return err; +} + +static int check_path(const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct statfs st_fs; + char *dname, *dir; + int err = 0; + + if (path == NULL) + return -EINVAL; + + dname = strdup(path); + if (dname == NULL) + return -ENOMEM; + + dir = dirname(dname); + if (statfs(dir, &st_fs)) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("failed to statfs %s: %s\n", dir, cp); + err = -errno; + } + free(dname); + + if (!err && st_fs.f_type != BPF_FS_MAGIC) { + pr_warning("specified path %s is not on BPF FS\n", path); + err = -EINVAL; + } + + return err; +} + +int bpf_program__pin_instance(struct bpf_program *prog, const char *path, + int instance) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warning("invalid program pointer\n"); + return -EINVAL; + } + + if (instance < 0 || instance >= prog->instances.nr) { + pr_warning("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); + return -EINVAL; + } + + if (bpf_obj_pin(prog->instances.fds[instance], path)) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("failed to pin program: %s\n", cp); + return -errno; + } + pr_debug("pinned program '%s'\n", path); + + return 0; +} + +static int make_dir(const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err = 0; + + if (mkdir(path, 0700) && errno != EEXIST) + err = -errno; + + if (err) { + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warning("failed to mkdir %s: %s\n", path, cp); + } + return err; +} + +int bpf_program__pin(struct bpf_program *prog, const char *path) +{ + int i, err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warning("invalid program pointer\n"); + return -EINVAL; + } + + if (prog->instances.nr <= 0) { + pr_warning("no instances of prog %s to pin\n", + prog->section_name); + return -EINVAL; + } + + err = make_dir(path); + if (err) + return err; + + for (i = 0; i < prog->instances.nr; i++) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%d", path, i); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_program__pin_instance(prog, buf, i); + if (err) + return err; + } + + return 0; +} + +int bpf_map__pin(struct bpf_map *map, const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err; + + err = check_path(path); + if (err) + return err; + + if (map == NULL) { + pr_warning("invalid map pointer\n"); + return -EINVAL; + } + + if (bpf_obj_pin(map->fd, path)) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("failed to pin map: %s\n", cp); + return -errno; + } + + pr_debug("pinned map '%s'\n", path); + return 0; +} + +int bpf_object__pin(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + struct bpf_map *map; + int err; + + if (!obj) + return -ENOENT; + + if (!obj->loaded) { + pr_warning("object not yet loaded; load it first\n"); + return -ENOENT; + } + + err = make_dir(path); + if (err) + return err; + + bpf_map__for_each(map, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_map__pin(map, buf); + if (err) + return err; + } + + bpf_object__for_each_program(prog, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + prog->section_name); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_program__pin(prog, buf); + if (err) + return err; + } + + return 0; +} + +void bpf_object__close(struct bpf_object *obj) +{ + size_t i; + + if (!obj) + return; + + if (obj->clear_priv) + obj->clear_priv(obj, obj->priv); + + bpf_object__elf_finish(obj); + bpf_object__unload(obj); + btf__free(obj->btf); + + for (i = 0; i < obj->nr_maps; i++) { + zfree(&obj->maps[i].name); + if (obj->maps[i].clear_priv) + obj->maps[i].clear_priv(&obj->maps[i], + obj->maps[i].priv); + obj->maps[i].priv = NULL; + obj->maps[i].clear_priv = NULL; + } + zfree(&obj->maps); + obj->nr_maps = 0; + + if (obj->programs && obj->nr_programs) { + for (i = 0; i < obj->nr_programs; i++) + bpf_program__exit(&obj->programs[i]); + } + zfree(&obj->programs); + + list_del(&obj->list); + free(obj); +} + +struct bpf_object * +bpf_object__next(struct bpf_object *prev) +{ + struct bpf_object *next; + + if (!prev) + next = list_first_entry(&bpf_objects_list, + struct bpf_object, + list); + else + next = list_next_entry(prev, list); + + /* Empty list is noticed here so don't need checking on entry. */ + if (&next->list == &bpf_objects_list) + return NULL; + + return next; +} + +const char *bpf_object__name(struct bpf_object *obj) +{ + return obj ? obj->path : ERR_PTR(-EINVAL); +} + +unsigned int bpf_object__kversion(struct bpf_object *obj) +{ + return obj ? obj->kern_version : 0; +} + +int bpf_object__btf_fd(const struct bpf_object *obj) +{ + return obj->btf ? btf__fd(obj->btf) : -1; +} + +int bpf_object__set_priv(struct bpf_object *obj, void *priv, + bpf_object_clear_priv_t clear_priv) +{ + if (obj->priv && obj->clear_priv) + obj->clear_priv(obj, obj->priv); + + obj->priv = priv; + obj->clear_priv = clear_priv; + return 0; +} + +void *bpf_object__priv(struct bpf_object *obj) +{ + return obj ? obj->priv : ERR_PTR(-EINVAL); +} + +static struct bpf_program * +__bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) +{ + size_t idx; + + if (!obj->programs) + return NULL; + /* First handler */ + if (prev == NULL) + return &obj->programs[0]; + + if (prev->obj != obj) { + pr_warning("error: program handler doesn't match object\n"); + return NULL; + } + + idx = (prev - obj->programs) + 1; + if (idx >= obj->nr_programs) + return NULL; + return &obj->programs[idx]; +} + +struct bpf_program * +bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) +{ + struct bpf_program *prog = prev; + + do { + prog = __bpf_program__next(prog, obj); + } while (prog && bpf_program__is_function_storage(prog, obj)); + + return prog; +} + +int bpf_program__set_priv(struct bpf_program *prog, void *priv, + bpf_program_clear_priv_t clear_priv) +{ + if (prog->priv && prog->clear_priv) + prog->clear_priv(prog, prog->priv); + + prog->priv = priv; + prog->clear_priv = clear_priv; + return 0; +} + +void *bpf_program__priv(struct bpf_program *prog) +{ + return prog ? prog->priv : ERR_PTR(-EINVAL); +} + +void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) +{ + prog->prog_ifindex = ifindex; +} + +const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) +{ + const char *title; + + title = prog->section_name; + if (needs_copy) { + title = strdup(title); + if (!title) { + pr_warning("failed to strdup program title\n"); + return ERR_PTR(-ENOMEM); + } + } + + return title; +} + +int bpf_program__fd(struct bpf_program *prog) +{ + return bpf_program__nth_fd(prog, 0); +} + +int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, + bpf_program_prep_t prep) +{ + int *instances_fds; + + if (nr_instances <= 0 || !prep) + return -EINVAL; + + if (prog->instances.nr > 0 || prog->instances.fds) { + pr_warning("Can't set pre-processor after loading\n"); + return -EINVAL; + } + + instances_fds = malloc(sizeof(int) * nr_instances); + if (!instances_fds) { + pr_warning("alloc memory failed for fds\n"); + return -ENOMEM; + } + + /* fill all fd with -1 */ + memset(instances_fds, -1, sizeof(int) * nr_instances); + + prog->instances.nr = nr_instances; + prog->instances.fds = instances_fds; + prog->preprocessor = prep; + return 0; +} + +int bpf_program__nth_fd(struct bpf_program *prog, int n) +{ + int fd; + + if (!prog) + return -EINVAL; + + if (n >= prog->instances.nr || n < 0) { + pr_warning("Can't get the %dth fd from program %s: only %d instances\n", + n, prog->section_name, prog->instances.nr); + return -EINVAL; + } + + fd = prog->instances.fds[n]; + if (fd < 0) { + pr_warning("%dth instance of program '%s' is invalid\n", + n, prog->section_name); + return -ENOENT; + } + + return fd; +} + +void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) +{ + prog->type = type; +} + +static bool bpf_program__is_type(struct bpf_program *prog, + enum bpf_prog_type type) +{ + return prog ? (prog->type == type) : false; +} + +#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ +int bpf_program__set_##NAME(struct bpf_program *prog) \ +{ \ + if (!prog) \ + return -EINVAL; \ + bpf_program__set_type(prog, TYPE); \ + return 0; \ +} \ + \ +bool bpf_program__is_##NAME(struct bpf_program *prog) \ +{ \ + return bpf_program__is_type(prog, TYPE); \ +} \ + +BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); +BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); +BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); +BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); +BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); +BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); +BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); +BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); + +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type) +{ + prog->expected_attach_type = type; +} + +#define BPF_PROG_SEC_IMPL(string, ptype, eatype, atype) \ + { string, sizeof(string) - 1, ptype, eatype, atype } + +/* Programs that can NOT be attached. */ +#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, -EINVAL) + +/* Programs that can be attached. */ +#define BPF_APROG_SEC(string, ptype, atype) \ + BPF_PROG_SEC_IMPL(string, ptype, 0, atype) + +/* Programs that must specify expected attach type at load time. */ +#define BPF_EAPROG_SEC(string, ptype, eatype) \ + BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype) + +/* Programs that can be attached but attach type can't be identified by section + * name. Kept for backward compatibility. + */ +#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) + +static const struct { + const char *sec; + size_t len; + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + enum bpf_attach_type attach_type; +} section_names[] = { + BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), + BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), + BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), + BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), + BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), + BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), + BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), + BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), + BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT), + BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT), + BPF_PROG_SEC("lwt_seg6local", BPF_PROG_TYPE_LWT_SEG6LOCAL), + BPF_APROG_SEC("cgroup_skb/ingress", BPF_PROG_TYPE_CGROUP_SKB, + BPF_CGROUP_INET_INGRESS), + BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB, + BPF_CGROUP_INET_EGRESS), + BPF_APROG_COMPAT("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), + BPF_APROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK, + BPF_CGROUP_INET_SOCK_CREATE), + BPF_EAPROG_SEC("cgroup/post_bind4", BPF_PROG_TYPE_CGROUP_SOCK, + BPF_CGROUP_INET4_POST_BIND), + BPF_EAPROG_SEC("cgroup/post_bind6", BPF_PROG_TYPE_CGROUP_SOCK, + BPF_CGROUP_INET6_POST_BIND), + BPF_APROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE, + BPF_CGROUP_DEVICE), + BPF_APROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS, + BPF_CGROUP_SOCK_OPS), + BPF_APROG_SEC("sk_skb/stream_parser", BPF_PROG_TYPE_SK_SKB, + BPF_SK_SKB_STREAM_PARSER), + BPF_APROG_SEC("sk_skb/stream_verdict", BPF_PROG_TYPE_SK_SKB, + BPF_SK_SKB_STREAM_VERDICT), + BPF_APROG_COMPAT("sk_skb", BPF_PROG_TYPE_SK_SKB), + BPF_APROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG, + BPF_SK_MSG_VERDICT), + BPF_APROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2, + BPF_LIRC_MODE2), + BPF_APROG_SEC("flow_dissector", BPF_PROG_TYPE_FLOW_DISSECTOR, + BPF_FLOW_DISSECTOR), + BPF_EAPROG_SEC("cgroup/bind4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_INET4_BIND), + BPF_EAPROG_SEC("cgroup/bind6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_INET6_BIND), + BPF_EAPROG_SEC("cgroup/connect4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_INET4_CONNECT), + BPF_EAPROG_SEC("cgroup/connect6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_INET6_CONNECT), + BPF_EAPROG_SEC("cgroup/sendmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_UDP4_SENDMSG), + BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_UDP6_SENDMSG), +}; + +#undef BPF_PROG_SEC_IMPL +#undef BPF_PROG_SEC +#undef BPF_APROG_SEC +#undef BPF_EAPROG_SEC +#undef BPF_APROG_COMPAT + +int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type) +{ + int i; + + if (!name) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(section_names); i++) { + if (strncmp(name, section_names[i].sec, section_names[i].len)) + continue; + *prog_type = section_names[i].prog_type; + *expected_attach_type = section_names[i].expected_attach_type; + return 0; + } + return -EINVAL; +} + +int libbpf_attach_type_by_name(const char *name, + enum bpf_attach_type *attach_type) +{ + int i; + + if (!name) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(section_names); i++) { + if (strncmp(name, section_names[i].sec, section_names[i].len)) + continue; + if (section_names[i].attach_type == -EINVAL) + return -EINVAL; + *attach_type = section_names[i].attach_type; + return 0; + } + return -EINVAL; +} + +static int +bpf_program__identify_section(struct bpf_program *prog, + enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type) +{ + return libbpf_prog_type_by_name(prog->section_name, prog_type, + expected_attach_type); +} + +int bpf_map__fd(struct bpf_map *map) +{ + return map ? map->fd : -EINVAL; +} + +const struct bpf_map_def *bpf_map__def(struct bpf_map *map) +{ + return map ? &map->def : ERR_PTR(-EINVAL); +} + +const char *bpf_map__name(struct bpf_map *map) +{ + return map ? map->name : NULL; +} + +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map) +{ + return map ? map->btf_key_type_id : 0; +} + +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map) +{ + return map ? map->btf_value_type_id : 0; +} + +int bpf_map__set_priv(struct bpf_map *map, void *priv, + bpf_map_clear_priv_t clear_priv) +{ + if (!map) + return -EINVAL; + + if (map->priv) { + if (map->clear_priv) + map->clear_priv(map, map->priv); + } + + map->priv = priv; + map->clear_priv = clear_priv; + return 0; +} + +void *bpf_map__priv(struct bpf_map *map) +{ + return map ? map->priv : ERR_PTR(-EINVAL); +} + +bool bpf_map__is_offload_neutral(struct bpf_map *map) +{ + return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; +} + +void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) +{ + map->map_ifindex = ifindex; +} + +struct bpf_map * +bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +{ + size_t idx; + struct bpf_map *s, *e; + + if (!obj || !obj->maps) + return NULL; + + s = obj->maps; + e = obj->maps + obj->nr_maps; + + if (prev == NULL) + return s; + + if ((prev < s) || (prev >= e)) { + pr_warning("error in %s: map handler doesn't belong to object\n", + __func__); + return NULL; + } + + idx = (prev - obj->maps) + 1; + if (idx >= obj->nr_maps) + return NULL; + return &obj->maps[idx]; +} + +struct bpf_map * +bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) +{ + struct bpf_map *pos; + + bpf_map__for_each(pos, obj) { + if (pos->name && !strcmp(pos->name, name)) + return pos; + } + return NULL; +} + +struct bpf_map * +bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) +{ + int i; + + for (i = 0; i < obj->nr_maps; i++) { + if (obj->maps[i].offset == offset) + return &obj->maps[i]; + } + return ERR_PTR(-ENOENT); +} + +long libbpf_get_error(const void *ptr) +{ + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + return 0; +} + +int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_prog_load_attr attr; + + memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); + attr.file = file; + attr.prog_type = type; + attr.expected_attach_type = 0; + + return bpf_prog_load_xattr(&attr, pobj, prog_fd); +} + +int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_object_open_attr open_attr = { + .file = attr->file, + .prog_type = attr->prog_type, + }; + struct bpf_program *prog, *first_prog = NULL; + enum bpf_attach_type expected_attach_type; + enum bpf_prog_type prog_type; + struct bpf_object *obj; + struct bpf_map *map; + int err; + + if (!attr) + return -EINVAL; + if (!attr->file) + return -EINVAL; + + obj = bpf_object__open_xattr(&open_attr); + if (IS_ERR_OR_NULL(obj)) + return -ENOENT; + + bpf_object__for_each_program(prog, obj) { + /* + * If type is not specified, try to guess it based on + * section name. + */ + prog_type = attr->prog_type; + prog->prog_ifindex = attr->ifindex; + expected_attach_type = attr->expected_attach_type; + if (prog_type == BPF_PROG_TYPE_UNSPEC) { + err = bpf_program__identify_section(prog, &prog_type, + &expected_attach_type); + if (err < 0) { + pr_warning("failed to guess program type based on section name %s\n", + prog->section_name); + bpf_object__close(obj); + return -EINVAL; + } + } + + bpf_program__set_type(prog, prog_type); + bpf_program__set_expected_attach_type(prog, + expected_attach_type); + + if (!first_prog) + first_prog = prog; + } + + bpf_map__for_each(map, obj) { + if (!bpf_map__is_offload_neutral(map)) + map->map_ifindex = attr->ifindex; + } + + if (!first_prog) { + pr_warning("object file doesn't contain bpf program\n"); + bpf_object__close(obj); + return -ENOENT; + } + + err = bpf_object__load(obj); + if (err) { + bpf_object__close(obj); + return -EINVAL; + } + + *pobj = obj; + *prog_fd = bpf_program__fd(first_prog); + return 0; +} + +enum bpf_perf_event_ret +bpf_perf_event_read_simple(void *mem, unsigned long size, + unsigned long page_size, void **buf, size_t *buf_len, + bpf_perf_event_print_t fn, void *priv) +{ + volatile struct perf_event_mmap_page *header = mem; + __u64 data_tail = header->data_tail; + __u64 data_head = header->data_head; + int ret = LIBBPF_PERF_EVENT_ERROR; + void *base, *begin, *end; + + asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ + if (data_head == data_tail) + return LIBBPF_PERF_EVENT_CONT; + + base = ((char *)header) + page_size; + + begin = base + data_tail % size; + end = base + data_head % size; + + while (begin != end) { + struct perf_event_header *ehdr; + + ehdr = begin; + if (begin + ehdr->size > base + size) { + long len = base + size - begin; + + if (*buf_len < ehdr->size) { + free(*buf); + *buf = malloc(ehdr->size); + if (!*buf) { + ret = LIBBPF_PERF_EVENT_ERROR; + break; + } + *buf_len = ehdr->size; + } + + memcpy(*buf, begin, len); + memcpy(*buf + len, base, ehdr->size - len); + ehdr = (void *)*buf; + begin = base + ehdr->size - len; + } else if (begin + ehdr->size == base + size) { + begin = base; + } else { + begin += ehdr->size; + } + + ret = fn(ehdr, priv); + if (ret != LIBBPF_PERF_EVENT_CONT) + break; + + data_tail += ehdr->size; + } + + __sync_synchronize(); /* smp_mb() */ + header->data_tail = data_tail; + + return ret; +} diff --git a/src/libbpf.h b/src/libbpf.h new file mode 100644 index 0000000..8af8d36 --- /dev/null +++ b/src/libbpf.h @@ -0,0 +1,305 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Common eBPF ELF object loading operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov + * Copyright (C) 2015 Wang Nan + * Copyright (C) 2015 Huawei Inc. + */ +#ifndef __LIBBPF_LIBBPF_H +#define __LIBBPF_LIBBPF_H + +#include +#include +#include +#include // for size_t +#include + +enum libbpf_errno { + __LIBBPF_ERRNO__START = 4000, + + /* Something wrong in libelf */ + LIBBPF_ERRNO__LIBELF = __LIBBPF_ERRNO__START, + LIBBPF_ERRNO__FORMAT, /* BPF object format invalid */ + LIBBPF_ERRNO__KVERSION, /* Incorrect or no 'version' section */ + LIBBPF_ERRNO__ENDIAN, /* Endian mismatch */ + LIBBPF_ERRNO__INTERNAL, /* Internal error in libbpf */ + LIBBPF_ERRNO__RELOC, /* Relocation failed */ + LIBBPF_ERRNO__LOAD, /* Load program failure for unknown reason */ + LIBBPF_ERRNO__VERIFY, /* Kernel verifier blocks program loading */ + LIBBPF_ERRNO__PROG2BIG, /* Program too big */ + LIBBPF_ERRNO__KVER, /* Incorrect kernel version */ + LIBBPF_ERRNO__PROGTYPE, /* Kernel doesn't support this program type */ + LIBBPF_ERRNO__WRNGPID, /* Wrong pid in netlink message */ + LIBBPF_ERRNO__INVSEQ, /* Invalid netlink sequence */ + LIBBPF_ERRNO__NLPARSE, /* netlink parsing error */ + __LIBBPF_ERRNO__END, +}; + +int libbpf_strerror(int err, char *buf, size_t size); + +/* + * __printf is defined in include/linux/compiler-gcc.h. However, + * it would be better if libbpf.h didn't depend on Linux header files. + * So instead of __printf, here we use gcc attribute directly. + */ +typedef int (*libbpf_print_fn_t)(const char *, ...) + __attribute__((format(printf, 1, 2))); + +void libbpf_set_print(libbpf_print_fn_t warn, + libbpf_print_fn_t info, + libbpf_print_fn_t debug); + +/* Hide internal to user */ +struct bpf_object; + +struct bpf_object_open_attr { + const char *file; + enum bpf_prog_type prog_type; +}; + +struct bpf_object *bpf_object__open(const char *path); +struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr); +struct bpf_object *bpf_object__open_buffer(void *obj_buf, + size_t obj_buf_sz, + const char *name); +int bpf_object__pin(struct bpf_object *object, const char *path); +void bpf_object__close(struct bpf_object *object); + +/* Load/unload object into/from kernel */ +int bpf_object__load(struct bpf_object *obj); +int bpf_object__unload(struct bpf_object *obj); +const char *bpf_object__name(struct bpf_object *obj); +unsigned int bpf_object__kversion(struct bpf_object *obj); +int bpf_object__btf_fd(const struct bpf_object *obj); + +struct bpf_program * +bpf_object__find_program_by_title(struct bpf_object *obj, const char *title); + +struct bpf_object *bpf_object__next(struct bpf_object *prev); +#define bpf_object__for_each_safe(pos, tmp) \ + for ((pos) = bpf_object__next(NULL), \ + (tmp) = bpf_object__next(pos); \ + (pos) != NULL; \ + (pos) = (tmp), (tmp) = bpf_object__next(tmp)) + +typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); +int bpf_object__set_priv(struct bpf_object *obj, void *priv, + bpf_object_clear_priv_t clear_priv); +void *bpf_object__priv(struct bpf_object *prog); + +int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type); +int libbpf_attach_type_by_name(const char *name, + enum bpf_attach_type *attach_type); + +/* Accessors of bpf_program */ +struct bpf_program; +struct bpf_program *bpf_program__next(struct bpf_program *prog, + struct bpf_object *obj); + +#define bpf_object__for_each_program(pos, obj) \ + for ((pos) = bpf_program__next(NULL, (obj)); \ + (pos) != NULL; \ + (pos) = bpf_program__next((pos), (obj))) + +typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, + void *); + +int bpf_program__set_priv(struct bpf_program *prog, void *priv, + bpf_program_clear_priv_t clear_priv); + +void *bpf_program__priv(struct bpf_program *prog); +void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); + +const char *bpf_program__title(struct bpf_program *prog, bool needs_copy); + +int bpf_program__load(struct bpf_program *prog, char *license, + __u32 kern_version); +int bpf_program__fd(struct bpf_program *prog); +int bpf_program__pin_instance(struct bpf_program *prog, const char *path, + int instance); +int bpf_program__pin(struct bpf_program *prog, const char *path); +void bpf_program__unload(struct bpf_program *prog); + +struct bpf_insn; + +/* + * Libbpf allows callers to adjust BPF programs before being loaded + * into kernel. One program in an object file can be transformed into + * multiple variants to be attached to different hooks. + * + * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd + * form an API for this purpose. + * + * - bpf_program_prep_t: + * Defines a 'preprocessor', which is a caller defined function + * passed to libbpf through bpf_program__set_prep(), and will be + * called before program is loaded. The processor should adjust + * the program one time for each instance according to the instance id + * passed to it. + * + * - bpf_program__set_prep: + * Attaches a preprocessor to a BPF program. The number of instances + * that should be created is also passed through this function. + * + * - bpf_program__nth_fd: + * After the program is loaded, get resulting FD of a given instance + * of the BPF program. + * + * If bpf_program__set_prep() is not used, the program would be loaded + * without adjustment during bpf_object__load(). The program has only + * one instance. In this case bpf_program__fd(prog) is equal to + * bpf_program__nth_fd(prog, 0). + */ + +struct bpf_prog_prep_result { + /* + * If not NULL, load new instruction array. + * If set to NULL, don't load this instance. + */ + struct bpf_insn *new_insn_ptr; + int new_insn_cnt; + + /* If not NULL, result FD is written to it. */ + int *pfd; +}; + +/* + * Parameters of bpf_program_prep_t: + * - prog: The bpf_program being loaded. + * - n: Index of instance being generated. + * - insns: BPF instructions array. + * - insns_cnt:Number of instructions in insns. + * - res: Output parameter, result of transformation. + * + * Return value: + * - Zero: pre-processing success. + * - Non-zero: pre-processing error, stop loading. + */ +typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, + struct bpf_insn *insns, int insns_cnt, + struct bpf_prog_prep_result *res); + +int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, + bpf_program_prep_t prep); + +int bpf_program__nth_fd(struct bpf_program *prog, int n); + +/* + * Adjust type of BPF program. Default is kprobe. + */ +int bpf_program__set_socket_filter(struct bpf_program *prog); +int bpf_program__set_tracepoint(struct bpf_program *prog); +int bpf_program__set_raw_tracepoint(struct bpf_program *prog); +int bpf_program__set_kprobe(struct bpf_program *prog); +int bpf_program__set_sched_cls(struct bpf_program *prog); +int bpf_program__set_sched_act(struct bpf_program *prog); +int bpf_program__set_xdp(struct bpf_program *prog); +int bpf_program__set_perf_event(struct bpf_program *prog); +void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type); + +bool bpf_program__is_socket_filter(struct bpf_program *prog); +bool bpf_program__is_tracepoint(struct bpf_program *prog); +bool bpf_program__is_raw_tracepoint(struct bpf_program *prog); +bool bpf_program__is_kprobe(struct bpf_program *prog); +bool bpf_program__is_sched_cls(struct bpf_program *prog); +bool bpf_program__is_sched_act(struct bpf_program *prog); +bool bpf_program__is_xdp(struct bpf_program *prog); +bool bpf_program__is_perf_event(struct bpf_program *prog); + +/* + * No need for __attribute__((packed)), all members of 'bpf_map_def' + * are all aligned. In addition, using __attribute__((packed)) + * would trigger a -Wpacked warning message, and lead to an error + * if -Werror is set. + */ +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; +}; + +/* + * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, + * so no need to worry about a name clash. + */ +struct bpf_map; +struct bpf_map * +bpf_object__find_map_by_name(struct bpf_object *obj, const char *name); + +/* + * Get bpf_map through the offset of corresponding struct bpf_map_def + * in the BPF object file. + */ +struct bpf_map * +bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); + +struct bpf_map * +bpf_map__next(struct bpf_map *map, struct bpf_object *obj); +#define bpf_map__for_each(pos, obj) \ + for ((pos) = bpf_map__next(NULL, (obj)); \ + (pos) != NULL; \ + (pos) = bpf_map__next((pos), (obj))) + +int bpf_map__fd(struct bpf_map *map); +const struct bpf_map_def *bpf_map__def(struct bpf_map *map); +const char *bpf_map__name(struct bpf_map *map); +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map); +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map); + +typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); +int bpf_map__set_priv(struct bpf_map *map, void *priv, + bpf_map_clear_priv_t clear_priv); +void *bpf_map__priv(struct bpf_map *map); +int bpf_map__reuse_fd(struct bpf_map *map, int fd); +bool bpf_map__is_offload_neutral(struct bpf_map *map); +void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); +int bpf_map__pin(struct bpf_map *map, const char *path); + +long libbpf_get_error(const void *ptr); + +struct bpf_prog_load_attr { + const char *file; + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + int ifindex; +}; + +int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, + struct bpf_object **pobj, int *prog_fd); +int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd); + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); + +enum bpf_perf_event_ret { + LIBBPF_PERF_EVENT_DONE = 0, + LIBBPF_PERF_EVENT_ERROR = -1, + LIBBPF_PERF_EVENT_CONT = -2, +}; + +typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event, + void *priv); +int bpf_perf_event_read_simple(void *mem, unsigned long size, + unsigned long page_size, + void **buf, size_t *buf_len, + bpf_perf_event_print_t fn, void *priv); + +struct nlattr; +typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); +int libbpf_netlink_open(unsigned int *nl_pid); +int libbpf_nl_get_link(int sock, unsigned int nl_pid, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); +int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); +int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); +int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); +#endif /* __LIBBPF_LIBBPF_H */ diff --git a/src/libbpf_errno.c b/src/libbpf_errno.c new file mode 100644 index 0000000..d83b17f --- /dev/null +++ b/src/libbpf_errno.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Copyright (C) 2013-2015 Alexei Starovoitov + * Copyright (C) 2015 Wang Nan + * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. + */ + +#include +#include + +#include "libbpf.h" + +#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) +#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) +#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) + +static const char *libbpf_strerror_table[NR_ERRNO] = { + [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf", + [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid", + [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost", + [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch", + [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf", + [ERRCODE_OFFSET(RELOC)] = "Relocation failed", + [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading", + [ERRCODE_OFFSET(PROG2BIG)] = "Program too big", + [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version", + [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", + [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", + [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", + [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing", +}; + +int libbpf_strerror(int err, char *buf, size_t size) +{ + if (!buf || !size) + return -1; + + err = err > 0 ? err : -err; + + if (err < __LIBBPF_ERRNO__START) { + int ret; + + ret = strerror_r(err, buf, size); + buf[size - 1] = '\0'; + return ret; + } + + if (err < __LIBBPF_ERRNO__END) { + const char *msg; + + msg = libbpf_strerror_table[ERRNO_OFFSET(err)]; + snprintf(buf, size, "%s", msg); + buf[size - 1] = '\0'; + return 0; + } + + snprintf(buf, size, "Unknown libbpf error %d", err); + buf[size - 1] = '\0'; + return -1; +} diff --git a/src/netlink.c b/src/netlink.c new file mode 100644 index 0000000..0ce67ae --- /dev/null +++ b/src/netlink.c @@ -0,0 +1,337 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "bpf.h" +#include "libbpf.h" +#include "nlattr.h" + +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif + +typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t, + void *cookie); + +int libbpf_netlink_open(__u32 *nl_pid) +{ + struct sockaddr_nl sa; + socklen_t addrlen; + int one = 1, ret; + int sock; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) + return -errno; + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + fprintf(stderr, "Netlink error reporting not supported\n"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + *nl_pid = sa.nl_pid; + return sock; + +cleanup: + close(sock); + return ret; +} + +static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq, + __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + bool multipart = true; + struct nlmsgerr *err; + struct nlmsghdr *nh; + char buf[4096]; + int len, ret; + + while (multipart) { + multipart = false; + len = recv(sock, buf, sizeof(buf), 0); + if (len < 0) { + ret = -errno; + goto done; + } + + if (len == 0) + break; + + for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != nl_pid) { + ret = -LIBBPF_ERRNO__WRNGPID; + goto done; + } + if (nh->nlmsg_seq != seq) { + ret = -LIBBPF_ERRNO__INVSEQ; + goto done; + } + if (nh->nlmsg_flags & NLM_F_MULTI) + multipart = true; + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + libbpf_nla_dump_errormsg(nh); + goto done; + case NLMSG_DONE: + return 0; + default: + break; + } + if (_fn) { + ret = _fn(nh, fn, cookie); + if (ret) + return ret; + } + } + } + ret = 0; +done: + return ret; +} + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) +{ + int sock, seq = 0, ret; + struct nlattr *nla, *nla_xdp; + struct { + struct nlmsghdr nh; + struct ifinfomsg ifinfo; + char attrbuf[64]; + } req; + __u32 nl_pid; + + sock = libbpf_netlink_open(&nl_pid); + if (sock < 0) + return sock; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_SETLINK; + req.nh.nlmsg_pid = 0; + req.nh.nlmsg_seq = ++seq; + req.ifinfo.ifi_family = AF_UNSPEC; + req.ifinfo.ifi_index = ifindex; + + /* started nested attribute for XDP */ + nla = (struct nlattr *)(((char *)&req) + + NLMSG_ALIGN(req.nh.nlmsg_len)); + nla->nla_type = NLA_F_NESTED | IFLA_XDP; + nla->nla_len = NLA_HDRLEN; + + /* add XDP fd */ + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FD; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); + memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); + nla->nla_len += nla_xdp->nla_len; + + /* if user passed in any flags, add those too */ + if (flags) { + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FLAGS; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); + memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); + nla->nla_len += nla_xdp->nla_len; + } + + req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); + + if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { + ret = -errno; + goto cleanup; + } + ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL); + +cleanup: + close(sock); + return ret; +} + +static int __dump_link_nlmsg(struct nlmsghdr *nlh, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct nlattr *tb[IFLA_MAX + 1], *attr; + struct ifinfomsg *ifi = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); + attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_link_nlmsg(cookie, ifi, tb); +} + +int libbpf_nl_get_link(int sock, unsigned int nl_pid, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct ifinfomsg ifm; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nlh.nlmsg_type = RTM_GETLINK, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifm.ifi_family = AF_PACKET, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, + dump_link_nlmsg, cookie); +} + +static int __dump_class_nlmsg(struct nlmsghdr *nlh, + libbpf_dump_nlmsg_t dump_class_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_class_nlmsg(cookie, t, tb); +} + +int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTCLASS, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg, + dump_class_nlmsg, cookie); +} + +static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_qdisc_nlmsg(cookie, t, tb); +} + +int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETQDISC, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg, + dump_qdisc_nlmsg, cookie); +} + +static int __dump_filter_nlmsg(struct nlmsghdr *nlh, + libbpf_dump_nlmsg_t dump_filter_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_filter_nlmsg(cookie, t, tb); +} + +int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTFILTER, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + .t.tcm_parent = handle, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg, + dump_filter_nlmsg, cookie); +} diff --git a/src/nlattr.c b/src/nlattr.c new file mode 100644 index 0000000..1e69c0c --- /dev/null +++ b/src/nlattr.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * NETLINK Netlink attributes + * + * Copyright (c) 2003-2013 Thomas Graf + */ + +#include +#include "nlattr.h" +#include +#include +#include + +static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = { + [LIBBPF_NLA_U8] = sizeof(uint8_t), + [LIBBPF_NLA_U16] = sizeof(uint16_t), + [LIBBPF_NLA_U32] = sizeof(uint32_t), + [LIBBPF_NLA_U64] = sizeof(uint64_t), + [LIBBPF_NLA_STRING] = 1, + [LIBBPF_NLA_FLAG] = 0, +}; + +static struct nlattr *nla_next(const struct nlattr *nla, int *remaining) +{ + int totlen = NLA_ALIGN(nla->nla_len); + + *remaining -= totlen; + return (struct nlattr *) ((char *) nla + totlen); +} + +static int nla_ok(const struct nlattr *nla, int remaining) +{ + return remaining >= sizeof(*nla) && + nla->nla_len >= sizeof(*nla) && + nla->nla_len <= remaining; +} + +static int nla_type(const struct nlattr *nla) +{ + return nla->nla_type & NLA_TYPE_MASK; +} + +static int validate_nla(struct nlattr *nla, int maxtype, + struct libbpf_nla_policy *policy) +{ + struct libbpf_nla_policy *pt; + unsigned int minlen = 0; + int type = nla_type(nla); + + if (type < 0 || type > maxtype) + return 0; + + pt = &policy[type]; + + if (pt->type > LIBBPF_NLA_TYPE_MAX) + return 0; + + if (pt->minlen) + minlen = pt->minlen; + else if (pt->type != LIBBPF_NLA_UNSPEC) + minlen = nla_attr_minlen[pt->type]; + + if (libbpf_nla_len(nla) < minlen) + return -1; + + if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen) + return -1; + + if (pt->type == LIBBPF_NLA_STRING) { + char *data = libbpf_nla_data(nla); + + if (data[libbpf_nla_len(nla) - 1] != '\0') + return -1; + } + + return 0; +} + +static inline int nlmsg_len(const struct nlmsghdr *nlh) +{ + return nlh->nlmsg_len - NLMSG_HDRLEN; +} + +/** + * Create attribute index based on a stream of attributes. + * @arg tb Index array to be filled (maxtype+1 elements). + * @arg maxtype Maximum attribute type expected and accepted. + * @arg head Head of attribute stream. + * @arg len Length of attribute stream. + * @arg policy Attribute validation policy. + * + * Iterates over the stream of attributes and stores a pointer to each + * attribute in the index array using the attribute type as index to + * the array. Attribute with a type greater than the maximum type + * specified will be silently ignored in order to maintain backwards + * compatibility. If \a policy is not NULL, the attribute will be + * validated using the specified policy. + * + * @see nla_validate + * @return 0 on success or a negative error code. + */ +int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, + int len, struct libbpf_nla_policy *policy) +{ + struct nlattr *nla; + int rem, err; + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + + libbpf_nla_for_each_attr(nla, head, len, rem) { + int type = nla_type(nla); + + if (type > maxtype) + continue; + + if (policy) { + err = validate_nla(nla, maxtype, policy); + if (err < 0) + goto errout; + } + + if (tb[type]) + fprintf(stderr, "Attribute of type %#x found multiple times in message, " + "previous attribute is being ignored.\n", type); + + tb[type] = nla; + } + + err = 0; +errout: + return err; +} + +/** + * Create attribute index based on nested attribute + * @arg tb Index array to be filled (maxtype+1 elements). + * @arg maxtype Maximum attribute type expected and accepted. + * @arg nla Nested Attribute. + * @arg policy Attribute validation policy. + * + * Feeds the stream of attributes nested into the specified attribute + * to libbpf_nla_parse(). + * + * @see libbpf_nla_parse + * @return 0 on success or a negative error code. + */ +int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype, + struct nlattr *nla, + struct libbpf_nla_policy *policy) +{ + return libbpf_nla_parse(tb, maxtype, libbpf_nla_data(nla), + libbpf_nla_len(nla), policy); +} + +/* dump netlink extended ack error message */ +int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh) +{ + struct libbpf_nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = { + [NLMSGERR_ATTR_MSG] = { .type = LIBBPF_NLA_STRING }, + [NLMSGERR_ATTR_OFFS] = { .type = LIBBPF_NLA_U32 }, + }; + struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr; + struct nlmsgerr *err; + char *errmsg = NULL; + int hlen, alen; + + /* no TLVs, nothing to do here */ + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return 0; + + err = (struct nlmsgerr *)NLMSG_DATA(nlh); + hlen = sizeof(*err); + + /* if NLM_F_CAPPED is set then the inner err msg was capped */ + if (!(nlh->nlmsg_flags & NLM_F_CAPPED)) + hlen += nlmsg_len(&err->msg); + + attr = (struct nlattr *) ((void *) err + hlen); + alen = nlh->nlmsg_len - hlen; + + if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, + extack_policy) != 0) { + fprintf(stderr, + "Failed to parse extended error attributes\n"); + return 0; + } + + if (tb[NLMSGERR_ATTR_MSG]) + errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]); + + fprintf(stderr, "Kernel error message: %s\n", errmsg); + + return 0; +} diff --git a/src/nlattr.h b/src/nlattr.h new file mode 100644 index 0000000..6cc3ac9 --- /dev/null +++ b/src/nlattr.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * NETLINK Netlink attributes + * + * Copyright (c) 2003-2013 Thomas Graf + */ + +#ifndef __LIBBPF_NLATTR_H +#define __LIBBPF_NLATTR_H + +#include +#include +/* avoid multiple definition of netlink features */ +#define __LINUX_NETLINK_H + +/** + * Standard attribute types to specify validation policy + */ +enum { + LIBBPF_NLA_UNSPEC, /**< Unspecified type, binary data chunk */ + LIBBPF_NLA_U8, /**< 8 bit integer */ + LIBBPF_NLA_U16, /**< 16 bit integer */ + LIBBPF_NLA_U32, /**< 32 bit integer */ + LIBBPF_NLA_U64, /**< 64 bit integer */ + LIBBPF_NLA_STRING, /**< NUL terminated character string */ + LIBBPF_NLA_FLAG, /**< Flag */ + LIBBPF_NLA_MSECS, /**< Micro seconds (64bit) */ + LIBBPF_NLA_NESTED, /**< Nested attributes */ + __LIBBPF_NLA_TYPE_MAX, +}; + +#define LIBBPF_NLA_TYPE_MAX (__LIBBPF_NLA_TYPE_MAX - 1) + +/** + * @ingroup attr + * Attribute validation policy. + * + * See section @core_doc{core_attr_parse,Attribute Parsing} for more details. + */ +struct libbpf_nla_policy { + /** Type of attribute or LIBBPF_NLA_UNSPEC */ + uint16_t type; + + /** Minimal length of payload required */ + uint16_t minlen; + + /** Maximal length of payload allowed */ + uint16_t maxlen; +}; + +/** + * @ingroup attr + * Iterate over a stream of attributes + * @arg pos loop counter, set to current attribute + * @arg head head of attribute stream + * @arg len length of attribute stream + * @arg rem initialized to len, holds bytes currently remaining in stream + */ +#define libbpf_nla_for_each_attr(pos, head, len, rem) \ + for (pos = head, rem = len; \ + nla_ok(pos, rem); \ + pos = nla_next(pos, &(rem))) + +/** + * libbpf_nla_data - head of payload + * @nla: netlink attribute + */ +static inline void *libbpf_nla_data(const struct nlattr *nla) +{ + return (char *) nla + NLA_HDRLEN; +} + +static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla) +{ + return *(uint8_t *)libbpf_nla_data(nla); +} + +static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla) +{ + return *(uint32_t *)libbpf_nla_data(nla); +} + +static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla) +{ + return (const char *)libbpf_nla_data(nla); +} + +/** + * libbpf_nla_len - length of payload + * @nla: netlink attribute + */ +static inline int libbpf_nla_len(const struct nlattr *nla) +{ + return nla->nla_len - NLA_HDRLEN; +} + +int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, + int len, struct libbpf_nla_policy *policy); +int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype, + struct nlattr *nla, + struct libbpf_nla_policy *policy); + +int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh); + +#endif /* __LIBBPF_NLATTR_H */ diff --git a/src/str_error.c b/src/str_error.c new file mode 100644 index 0000000..00e48ac --- /dev/null +++ b/src/str_error.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +#undef _GNU_SOURCE +#include +#include +#include "str_error.h" + +/* + * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl + * libc, while checking strerror_r() return to avoid having to check this in + * all places calling it. + */ +char *libbpf_strerror_r(int err, char *dst, int len) +{ + int ret = strerror_r(err, dst, len); + if (ret) + snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); + return dst; +} diff --git a/src/str_error.h b/src/str_error.h new file mode 100644 index 0000000..a139334 --- /dev/null +++ b/src/str_error.h @@ -0,0 +1,6 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __LIBBPF_STR_ERROR_H +#define __LIBBPF_STR_ERROR_H + +char *libbpf_strerror_r(int err, char *dst, int len); +#endif /* __LIBBPF_STR_ERROR_H */