diff --git a/source/tools/detect/mem/oomcheck/oomcheck.py b/source/tools/detect/mem/oomcheck/oomcheck.py index ebb637c0c386994ed07c157956d7060aee5022c1..cd9a4e336d3281ca1441f2956787180dbb7ef072 100644 --- a/source/tools/detect/mem/oomcheck/oomcheck.py +++ b/source/tools/detect/mem/oomcheck/oomcheck.py @@ -351,7 +351,7 @@ def memleak_check(total, kmem): return False def tcp_mem_check(used): - skcheck_bin = os.getenv("SYSAK_WORK_PATH"); + skcheck_bin = os.getenv("SYSAK_WORK_PATH",""); skcheck_bin += "/tools/skcheck -j /tmp/skcheck.json > /dev/null 2>&1" ret = os.popen(skcheck_bin).read() if not os.path.exists("/tmp/skcheck.json"): @@ -670,11 +670,13 @@ def oom_get_max_task(num, oom_result): state = oom['state_mem'] state['msg'] = [] state['total_rss'] = 0 + s_bra = 0 for line in oom['oom_msg']: try: if 'rss' in line and 'oom_score_adj' in line and 'name' in line: dump_task = True state['msg'].append(line) + s_bra = line.count('[') continue if not dump_task: continue @@ -682,7 +684,7 @@ def oom_get_max_task(num, oom_result): break if OOM_END_KEYWORD in line or OOM_END_KEYWORD_4_19 in line: break - if line.count('[') !=2 or line.count(']') !=2: + if line.count('[') != s_bra: break pid_idx = line.rfind('[') last_idx = line.rfind(']') diff --git a/source/tools/detect/sched/workqlatency/README.md b/source/tools/detect/sched/workqlatency/README.md index 161f496ba5bb5b147f65de12bf3faebad10abc6b..7480dd08800d8c27f1ff448accb8441b147379d2 100644 --- a/source/tools/detect/sched/workqlatency/README.md +++ b/source/tools/detect/sched/workqlatency/README.md @@ -11,7 +11,7 @@ example: sysak workqlatency -t 100 #trace work runtime and latency statistics ``` -使用示例:sysak worklatency -t 10 监控10‘s内内存直接回收规整情况 +使用示例:sysak worklatency -t 10 监控10‘s work latency和runtime情况 ``` Kwork Name Cpu Avg delay(ns) Count Max delay(ns) Max delay start(s) Max delay end(s) <0xffffffff9245ade0> blk_mq_timeout_work 1 6507 1 6507 2022-08-14 09:57:13 2022-08-14 09:57:13 diff --git a/source/tools/monitor/raptor/README.md b/source/tools/monitor/raptor/README.md new file mode 100644 index 0000000000000000000000000000000000000000..2d76d520a19a8fdcab3f441cc99da6e8c0a4a07f --- /dev/null +++ b/source/tools/monitor/raptor/README.md @@ -0,0 +1,114 @@ +# 功能说明 +continuous profiling 系统性能持续分析 + +使用说明: +``` +Usage: sysak raptor [options] [args] +Options: + oncpu + offcpu + pingslow + userslow +args: + --akid akid + SLS AccessKeyID + + --akse akse + SLS AccessKeySecret + + --app-name + application name used when uploading profiling data + + --cpu -1 + Number of cpu you want to profile. -1 to profile the whole system + + --endpoint endpoint + SLS Endpoint + + --exit-time 2880 + time of minutes unit the profiling to exit, default means 2 days + + --help false + help for oncpu + + --log-level info + log level: debug|info|warn|error + + --logstore akid + SLS Logstore + + --pid -1 + PID you want to profile. -1 to profile the whole system + + --project akid + SLS Project + + --sample-rate 100 + sample rate for the profiler in Hz. 100 means reading 100 times per second + + --server http://localhost:4040 + the server address + + --sls unuser + producer/procuderaw/consumer data to/from SLS + + --space 0 + 0 profile user space, 1 user+kernel space + + --symbol-cache-size 256 + max size of symbols cache + + --tag {} + tag in key=value form. The flag may be specified multiple times + + --timer -1 + Timer(min) trigger to start the profiling, minimum timer every 5 minutes + + --upload-rate 10s + profile upload rate + + --upload-threads 4 + number of upload threads + + --upload-timeout 10s + profile upload timeout + + --usage -1 + Cpu usage trigger to start the profiling +example: +sysak raptor oncpu --server "http://127.0.0.1:4040" --app-name 实例ip +``` +- oncpu + +主要用于排查应用偶现占用cpu过多的问题,对应ECS系统指标升高却不知道是哪个应用引起; + +- offcpu + +主要排查应用的性能问题,对应 应用自身的一些锁竞争等问题导致迟迟不能占用cpu,排查可能的问题如应用收包慢等问题; + +- pingslow + +ping主机有时延抖动,怀疑慢在主机的情况; + +- userslow + +用户进程没有及时收包造成的网络假抖动的情况; +**以oncpu功能为例,其他功能待完善** + +| 参数 | 说明 | +| --- | --- | +| --app-name | 标记profiling对象,一般取实例id | +| --pid | 指定任务做profiling,较少数据开销 | +| --sample-rate | 指定采样的频率,既1s内采样多少次 | +| --cpu | 指定cpu做profiilng,解决应用绑核,单cpu冲高问题 | +| --space | 采样上下文,0 进程上下文,1包含中断上下文 | +| --server | 服务端地址,local本地诊断结果输出 | +| --uplaod-rate | 多久上传一次数据,既数据切片的时间 | +| --exit-time | 默认部署后会运行两天退出,防止同学部署后忘记关闭,-1表示一直运行 | +| --akid | SLS AccessKeyID | +| --akse | SLS AccessKeySecret | +| --logstore | SLS Logstore | +| --project | SLS Project | +| --sls | producer/procuderaw/consumer data to/from SLS | + +云下环境后端flamegraph展示配合sysom使用。 diff --git a/source/tools/monitor/raptor/source/Makefile b/source/tools/monitor/raptor/source/Makefile index 179957b6f9e395db57e5179274aa73c498a1c0b8..44e63af9e72abc3ed0a3c25009ddbb0bba779660 100644 --- a/source/tools/monitor/raptor/source/Makefile +++ b/source/tools/monitor/raptor/source/Makefile @@ -9,8 +9,8 @@ RELEASE_GOVERSION := $(shell go version) RELEASE_AUTHOR := Dylane GOLDFLAGS := -EXTRA_CGO_CFLAGS := -I$(abspath ./profile/third/libbpf/lib/include) \ - -I$(abspath ./ebpf/src/lib/include) +EXTRA_CGO_CFLAGS := -I$(abspath ./ebpf/src/libbpf/lib/include) \ + -I$(abspath ./ebpf/src/bcc/lib/include/bcc_syms) EXTRA_CGO_LDFLAGS := -L$(abspath ./ebpf/src/libbpf/lib/lib64) -lbpf \ -L$(abspath ./ebpf/src/bcc/lib/lib) -lbcc-syms -lstdc++ -lelf -lz \ -L$(abspath ./ebpf/src/lib) -lnginx diff --git a/source/tools/monitor/raptor/source/ebpf/src/Makefile b/source/tools/monitor/raptor/source/ebpf/src/Makefile index c8e036c4f6d496ddb3aa144a5f876d49c9d94f4a..be9d960c0f46ed07ddc365ec18f7b5f1f2e7cd5a 100644 --- a/source/tools/monitor/raptor/source/ebpf/src/Makefile +++ b/source/tools/monitor/raptor/source/ebpf/src/Makefile @@ -11,6 +11,7 @@ LIBBPF_VERSION ?= v0.8.1 # libbpf to avoid dependency on system-wide headers, which could be missing or # outdated INCLUDES := -I$(OUTPUT) -I../../libbpf/include/uapi -I$(dir $(VMLINUX)) +BPFAPI := -I./libbpf/lib/include CFLAGS := -g -Wall -fPIC MYCFLAGS := -ggdb -gdwarf -O2 -Wall -fpie -Wno-unused-variable -Wno-unused-function -I./lib/include ARCH := $(shell uname -m | sed 's/x86_64/x86/' | sed 's/aarch64/arm64/' | sed 's/ppc64le/powerpc/' | sed 's/mips.*/mips/') @@ -107,20 +108,19 @@ build_bpf: profile: oncpu.bpf.o offcpu.bpf.o user_slow.bpf.o ping_slow.bpf.o nginx.bpf.o build_bpf oncpu.bpf.o: oncpu.bpf.c profile.bpf.h $(VMLINUX) - $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 -I. -c oncpu.bpf.c -o $@ + $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 $(BPFAPI) -c oncpu.bpf.c -o $@ offcpu.bpf.o: offcpu.bpf.c $(VMLINUX) - $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 -I. -c offcpu.bpf.c -o $@ + $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 $(BPFAPI) -c offcpu.bpf.c -o $@ user_slow.bpf.o: user_slow.bpf.c $(VMLINUX) - $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 -I. -c user_slow.bpf.c -o $@ + $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 $(BPFAPI) -c user_slow.bpf.c -o $@ ping_slow.bpf.o: ping_slow.bpf.c $(VMLINUX) - $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 -I. -c ping_slow.bpf.c -o $@ + $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 $(BPFAPI) -c ping_slow.bpf.c -o $@ nginx.bpf.o: nginx.bpf.c $(VMLINUX) - $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 -I. -c nginx.bpf.c -o $@ - + $(CLANG) $(MYCFLAGS) -target bpf -D__TARGET_ARCH_x86 $(BPFAPI) -c nginx.bpf.c -o $@ # delete failed targets .DELETE_ON_ERROR: diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bcc_proc.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bcc_proc.h deleted file mode 100644 index 368f27d9e0c3a0abc92afd4eec7323e33880a0fe..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bcc_proc.h +++ /dev/null @@ -1,68 +0,0 @@ -/* - * Copyright (c) 2016 GitHub, Inc. - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ -#ifndef LIBBCC_PROC_H -#define LIBBCC_PROC_H - -#include "bcc_syms.h" - -#ifdef __cplusplus -extern "C" { -#endif - -#include -#include -#include - - -typedef struct mod_info { - char *name; - uint64_t start_addr; - uint64_t end_addr; - long long unsigned int file_offset; - uint64_t dev_major; - uint64_t dev_minor; - uint64_t inode; -} mod_info; - -// Module info, whether to check mount namespace, payload -// Callback returning a negative value indicates to stop the iteration -typedef int (*bcc_procutils_modulecb)(mod_info *, int, void *); - -// Symbol name, address, payload -typedef void (*bcc_procutils_ksymcb)(const char *, const char *, uint64_t, void *); - -char *bcc_procutils_which_so(const char *libname, int pid); -char *bcc_procutils_which(const char *binpath); -int bcc_mapping_is_file_backed(const char *mapname); -// Iterate over all executable memory mapping sections of a Process. -// All anonymous and non-file-backed mapping sections, namely those -// listed in bcc_mapping_is_file_backed, will be ignored. -// Returns -1 on error, and 0 on success -int bcc_procutils_each_module(int pid, bcc_procutils_modulecb callback, - void *payload); - -int _procfs_maps_each_module(FILE *procmaps, int pid, - bcc_procutils_modulecb callback, void *payload); -// Iterate over all non-data Kernel symbols. -// Returns -1 on error, and 0 on success -int bcc_procutils_each_ksym(bcc_procutils_ksymcb callback, void *payload); -void bcc_procutils_free(const char *ptr); -const char *bcc_procutils_language(int pid); - -#ifdef __cplusplus -} -#endif -#endif diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bcc_syms.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bcc_syms.h deleted file mode 100644 index d70b707a7c2ae3160d595726e59f6618447bf847..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bcc_syms.h +++ /dev/null @@ -1,109 +0,0 @@ -/* - * Copyright (c) 2016 GitHub, Inc. - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ -#ifndef LIBBCC_SYMS_H -#define LIBBCC_SYMS_H - -#ifdef __cplusplus -extern "C" { -#endif - -#include -#include -#include "linux/bpf.h" -#include "bcc_proc.h" - -struct bcc_symbol { - const char *name; - const char *demangle_name; - const char *module; - uint64_t offset; -}; - -typedef int (*SYM_CB)(const char *symname, uint64_t addr); -struct mod_info; - -#ifndef STT_GNU_IFUNC -#define STT_GNU_IFUNC 10 -#endif - -#if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2 -// Indicate if the Local Entry Point (LEP) should be used as a symbol's -// start address -#define STT_PPC64_ELFV2_SYM_LEP 31 -#endif - -static const uint32_t BCC_SYM_ALL_TYPES = 65535; -struct bcc_symbol_option { - int use_debug_file; - int check_debug_file_crc; - // Symbolize on-demand or symbolize everything ahead of time - int lazy_symbolize; - // Bitmask flags indicating what types of ELF symbols to use - uint32_t use_symbol_type; -}; - -void *bcc_symcache_new(int pid, struct bcc_symbol_option *option); -void bcc_free_symcache(void *symcache, int pid); - -// The demangle_name pointer in bcc_symbol struct is returned from the -// __cxa_demangle function call, which is supposed to be freed by caller. Call -// this function after done using returned result of bcc_symcache_resolve. -void bcc_symbol_free_demangle_name(struct bcc_symbol *sym); -int bcc_symcache_resolve(void *symcache, uint64_t addr, struct bcc_symbol *sym, bool stale_check); -int bcc_symcache_resolve_no_demangle(void *symcache, uint64_t addr, - struct bcc_symbol *sym, bool stale_check); - -int bcc_symcache_resolve_name(void *resolver, const char *module, - const char *name, uint64_t *addr); -void bcc_symcache_refresh(void *resolver); - -int _bcc_syms_find_module(struct mod_info *info, int enter_ns, void *p); -int bcc_resolve_global_addr(int pid, const char *module, const uint64_t address, - uint8_t inode_match_only, uint64_t *global); - -/*bcc APIs for build_id stackmap support*/ -void *bcc_buildsymcache_new(void); -void bcc_free_buildsymcache(void *symcache); -int bcc_buildsymcache_add_module(void *resolver, const char *module_name); -int bcc_buildsymcache_resolve(void *resolver, - struct bpf_stack_build_id *trace, - struct bcc_symbol *sym); -// Call cb on every function symbol in the specified module. Uses simpler -// SYM_CB callback mainly for easier to use in Python API. -// Will prefer use debug file and check debug file CRC when reading the module. -int bcc_foreach_function_symbol(const char *module, SYM_CB cb); - -// Find the offset of a symbol in a module binary. If addr is not zero, will -// calculate the offset using the provided addr and the module's load address. -// -// If pid is provided, will use it to help lookup the module in the Process and -// enter the Process's mount Namespace. -// -// If option is not NULL, will respect the specified options for lookup. -// Otherwise default option will apply, which is to use debug file, verify -// checksum, and try all types of symbols. -// -// Return 0 on success and -1 on failure. Output will be write to sym. After -// use, sym->module need to be freed if it's not empty. -int bcc_resolve_symname(const char *module, const char *symname, - const uint64_t addr, int pid, - struct bcc_symbol_option* option, - struct bcc_symbol *sym); - -#ifdef __cplusplus -} -#endif -#endif diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf.h deleted file mode 100644 index 2e0d3731e4c0fb51653319c356f8f2e79c48b5d1..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf.h +++ /dev/null @@ -1,537 +0,0 @@ -/* 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 -#include - -#include "libbpf_common.h" -#include "libbpf_legacy.h" - -#ifdef __cplusplus -extern "C" { -#endif - -int libbpf_set_memlock_rlim(size_t memlock_bytes); - -struct bpf_map_create_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - - __u32 btf_fd; - __u32 btf_key_type_id; - __u32 btf_value_type_id; - __u32 btf_vmlinux_value_type_id; - - __u32 inner_map_fd; - __u32 map_flags; - __u64 map_extra; - - __u32 numa_node; - __u32 map_ifindex; -}; -#define bpf_map_create_opts__last_field map_ifindex - -LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, - const char *map_name, - __u32 key_size, - __u32 value_size, - __u32 max_entries, - const struct bpf_map_create_opts *opts); - -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; - union { - __u32 inner_map_fd; - __u32 btf_vmlinux_value_type_id; - }; -}; - -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") -LIBBPF_API int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") -LIBBPF_API 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); -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") -LIBBPF_API 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); -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") -LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags); -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") -LIBBPF_API 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); -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") -LIBBPF_API 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_prog_load_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - - /* libbpf can retry BPF_PROG_LOAD command if bpf() syscall returns - * -EAGAIN. This field determines how many attempts libbpf has to - * make. If not specified, libbpf will use default value of 5. - */ - int attempts; - - enum bpf_attach_type expected_attach_type; - __u32 prog_btf_fd; - __u32 prog_flags; - __u32 prog_ifindex; - __u32 kern_version; - - __u32 attach_btf_id; - __u32 attach_prog_fd; - __u32 attach_btf_obj_fd; - - const int *fd_array; - - /* .BTF.ext func info data */ - const void *func_info; - __u32 func_info_cnt; - __u32 func_info_rec_size; - - /* .BTF.ext line info data */ - const void *line_info; - __u32 line_info_cnt; - __u32 line_info_rec_size; - - /* verifier log options */ - __u32 log_level; - __u32 log_size; - char *log_buf; -}; -#define bpf_prog_load_opts__last_field log_buf - -LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, - const char *prog_name, const char *license, - const struct bpf_insn *insns, size_t insn_cnt, - const struct bpf_prog_load_opts *opts); -/* this "specialization" should go away in libbpf 1.0 */ -LIBBPF_API int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type, - const char *prog_name, const char *license, - const struct bpf_insn *insns, size_t insn_cnt, - const struct bpf_prog_load_opts *opts); - -/* This is an elaborate way to not conflict with deprecated bpf_prog_load() - * API, defined in libbpf.h. Once we hit libbpf 1.0, all this will be gone. - * With this approach, if someone is calling bpf_prog_load() with - * 4 arguments, they will use the deprecated API, which keeps backwards - * compatibility (both source code and binary). If bpf_prog_load() is called - * with 6 arguments, though, it gets redirected to __bpf_prog_load. - * So looking forward to libbpf 1.0 when this hack will be gone and - * __bpf_prog_load() will be called just bpf_prog_load(). - */ -#ifndef bpf_prog_load -#define bpf_prog_load(...) ___libbpf_overload(___bpf_prog_load, __VA_ARGS__) -#define ___bpf_prog_load4(file, type, pobj, prog_fd) \ - bpf_prog_load_deprecated(file, type, pobj, prog_fd) -#define ___bpf_prog_load6(prog_type, prog_name, license, insns, insn_cnt, opts) \ - bpf_prog_load(prog_type, prog_name, license, insns, insn_cnt, opts) -#endif /* bpf_prog_load */ - -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; - union { - __u32 kern_version; - __u32 attach_prog_fd; - }; - union { - __u32 prog_ifindex; - __u32 attach_btf_id; - }; - __u32 prog_btf_fd; - __u32 func_info_rec_size; - const void *func_info; - __u32 func_info_cnt; - __u32 line_info_rec_size; - const void *line_info; - __u32 line_info_cnt; - __u32 log_level; - __u32 prog_flags; -}; - -/* Flags to direct loading requirements */ -#define MAPS_RELAX_COMPAT 0x01 - -/* Recommended log buffer size */ -#define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ - -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") -LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, - char *log_buf, size_t log_buf_sz); -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") -LIBBPF_API 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); -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") -LIBBPF_API int bpf_verify_program(enum bpf_prog_type type, - const struct bpf_insn *insns, - size_t insns_cnt, __u32 prog_flags, - const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz, - int log_level); - -struct bpf_btf_load_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - - /* kernel log options */ - char *log_buf; - __u32 log_level; - __u32 log_size; -}; -#define bpf_btf_load_opts__last_field log_size - -LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, - const struct bpf_btf_load_opts *opts); - -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_btf_load() instead") -LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, - __u32 log_buf_size, bool do_log); - -LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, - __u64 flags); - -LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value); -LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, - __u64 flags); -LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, - void *value); -LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, - void *value, __u64 flags); -LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); -LIBBPF_API int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags); -LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); -LIBBPF_API int bpf_map_freeze(int fd); - -struct bpf_map_batch_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - __u64 elem_flags; - __u64 flags; -}; -#define bpf_map_batch_opts__last_field flags - - -/** - * @brief **bpf_map_delete_batch()** allows for batch deletion of multiple - * elements in a BPF map. - * - * @param fd BPF map file descriptor - * @param keys pointer to an array of *count* keys - * @param count input and output parameter; on input **count** represents the - * number of elements in the map to delete in batch; - * on output if a non-EFAULT error is returned, **count** represents the number of deleted - * elements if the output **count** value is not equal to the input **count** value - * If EFAULT is returned, **count** should not be trusted to be correct. - * @param opts options for configuring the way the batch deletion works - * @return 0, on success; negative error code, otherwise (errno is also set to - * the error code) - */ -LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys, - __u32 *count, - const struct bpf_map_batch_opts *opts); - -/** - * @brief **bpf_map_lookup_batch()** allows for batch lookup of BPF map elements. - * - * The parameter *in_batch* is the address of the first element in the batch to read. - * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent - * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate - * that the batched lookup starts from the beginning of the map. - * - * The *keys* and *values* are output parameters which must point to memory large enough to - * hold *count* items based on the key and value size of the map *map_fd*. The *keys* - * buffer must be of *key_size* * *count*. The *values* buffer must be of - * *value_size* * *count*. - * - * @param fd BPF map file descriptor - * @param in_batch address of the first element in batch to read, can pass NULL to - * indicate that the batched lookup starts from the beginning of the map. - * @param out_batch output parameter that should be passed to next call as *in_batch* - * @param keys pointer to an array large enough for *count* keys - * @param values pointer to an array large enough for *count* values - * @param count input and output parameter; on input it's the number of elements - * in the map to read in batch; on output it's the number of elements that were - * successfully read. - * If a non-EFAULT error is returned, count will be set as the number of elements - * that were read before the error occurred. - * If EFAULT is returned, **count** should not be trusted to be correct. - * @param opts options for configuring the way the batch lookup works - * @return 0, on success; negative error code, otherwise (errno is also set to - * the error code) - */ -LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, - void *keys, void *values, __u32 *count, - const struct bpf_map_batch_opts *opts); - -/** - * @brief **bpf_map_lookup_and_delete_batch()** allows for batch lookup and deletion - * of BPF map elements where each element is deleted after being retrieved. - * - * @param fd BPF map file descriptor - * @param in_batch address of the first element in batch to read, can pass NULL to - * get address of the first element in *out_batch* - * @param out_batch output parameter that should be passed to next call as *in_batch* - * @param keys pointer to an array of *count* keys - * @param values pointer to an array large enough for *count* values - * @param count input and output parameter; on input it's the number of elements - * in the map to read and delete in batch; on output it represents the number of - * elements that were successfully read and deleted - * If a non-**EFAULT** error code is returned and if the output **count** value - * is not equal to the input **count** value, up to **count** elements may - * have been deleted. - * if **EFAULT** is returned up to *count* elements may have been deleted without - * being returned via the *keys* and *values* output parameters. - * @param opts options for configuring the way the batch lookup and delete works - * @return 0, on success; negative error code, otherwise (errno is also set to - * the error code) - */ -LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, - void *out_batch, void *keys, - void *values, __u32 *count, - const struct bpf_map_batch_opts *opts); - -/** - * @brief **bpf_map_update_batch()** updates multiple elements in a map - * by specifying keys and their corresponding values. - * - * The *keys* and *values* parameters must point to memory large enough - * to hold *count* items based on the key and value size of the map. - * - * The *opts* parameter can be used to control how *bpf_map_update_batch()* - * should handle keys that either do or do not already exist in the map. - * In particular the *flags* parameter of *bpf_map_batch_opts* can be - * one of the following: - * - * Note that *count* is an input and output parameter, where on output it - * represents how many elements were successfully updated. Also note that if - * **EFAULT** then *count* should not be trusted to be correct. - * - * **BPF_ANY** - * Create new elements or update existing. - * - * **BPF_NOEXIST** - * Create new elements only if they do not exist. - * - * **BPF_EXIST** - * Update existing elements. - * - * **BPF_F_LOCK** - * Update spin_lock-ed map elements. This must be - * specified if the map value contains a spinlock. - * - * @param fd BPF map file descriptor - * @param keys pointer to an array of *count* keys - * @param values pointer to an array of *count* values - * @param count input and output parameter; on input it's the number of elements - * in the map to update in batch; on output if a non-EFAULT error is returned, - * **count** represents the number of updated elements if the output **count** - * value is not equal to the input **count** value. - * If EFAULT is returned, **count** should not be trusted to be correct. - * @param opts options for configuring the way the batch update works - * @return 0, on success; negative error code, otherwise (errno is also set to - * the error code) - */ -LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values, - __u32 *count, - const struct bpf_map_batch_opts *opts); - -LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); -LIBBPF_API int bpf_obj_get(const char *pathname); - -struct bpf_prog_attach_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - unsigned int flags; - int replace_prog_fd; -}; -#define bpf_prog_attach_opts__last_field replace_prog_fd - -LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, - enum bpf_attach_type type, unsigned int flags); -LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd, - enum bpf_attach_type type, - const struct bpf_prog_attach_opts *opts); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead") -LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd, - enum bpf_attach_type type, - const struct bpf_prog_attach_opts *opts); -LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); -LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, - enum bpf_attach_type type); - -union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */ -struct bpf_link_create_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - __u32 flags; - union bpf_iter_link_info *iter_info; - __u32 iter_info_len; - __u32 target_btf_id; - union { - struct { - __u64 bpf_cookie; - } perf_event; - struct { - __u32 flags; - __u32 cnt; - const char **syms; - const unsigned long *addrs; - const __u64 *cookies; - } kprobe_multi; - struct { - __u64 cookie; - } tracing; - }; - size_t :0; -}; -#define bpf_link_create_opts__last_field kprobe_multi.cookies - -LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, - enum bpf_attach_type attach_type, - const struct bpf_link_create_opts *opts); - -LIBBPF_API int bpf_link_detach(int link_fd); - -struct bpf_link_update_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - __u32 flags; /* extra flags */ - __u32 old_prog_fd; /* expected old program FD */ -}; -#define bpf_link_update_opts__last_field old_prog_fd - -LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd, - const struct bpf_link_update_opts *opts); - -LIBBPF_API int bpf_iter_create(int link_fd); - -struct bpf_prog_test_run_attr { - int prog_fd; - int repeat; - const void *data_in; - __u32 data_size_in; - void *data_out; /* optional */ - __u32 data_size_out; /* in: max length of data_out - * out: length of data_out */ - __u32 retval; /* out: return code of the BPF program */ - __u32 duration; /* out: average per repetition in ns */ - const void *ctx_in; /* optional */ - __u32 ctx_size_in; - void *ctx_out; /* optional */ - __u32 ctx_size_out; /* in: max length of ctx_out - * out: length of cxt_out */ -}; - -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead") -LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr); - -/* - * bpf_prog_test_run does not check that data_out is large enough. Consider - * using bpf_prog_test_run_opts instead. - */ -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead") -LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, - __u32 size, void *data_out, __u32 *size_out, - __u32 *retval, __u32 *duration); -LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); -LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); -LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id); -LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id); -LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); -LIBBPF_API int bpf_map_get_fd_by_id(__u32 id); -LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id); -LIBBPF_API int bpf_link_get_fd_by_id(__u32 id); -LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len); -LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, - __u32 query_flags, __u32 *attach_flags, - __u32 *prog_ids, __u32 *prog_cnt); -LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd); -LIBBPF_API 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); - -enum bpf_stats_type; /* defined in up-to-date linux/bpf.h */ -LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type); - -struct bpf_prog_bind_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - __u32 flags; -}; -#define bpf_prog_bind_opts__last_field flags - -LIBBPF_API int bpf_prog_bind_map(int prog_fd, int map_fd, - const struct bpf_prog_bind_opts *opts); - -struct bpf_test_run_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - const void *data_in; /* optional */ - void *data_out; /* optional */ - __u32 data_size_in; - __u32 data_size_out; /* in: max length of data_out - * out: length of data_out - */ - const void *ctx_in; /* optional */ - void *ctx_out; /* optional */ - __u32 ctx_size_in; - __u32 ctx_size_out; /* in: max length of ctx_out - * out: length of cxt_out - */ - __u32 retval; /* out: return code of the BPF program */ - int repeat; - __u32 duration; /* out: average per repetition in ns */ - __u32 flags; - __u32 cpu; - __u32 batch_size; -}; -#define bpf_test_run_opts__last_field batch_size - -LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, - struct bpf_test_run_opts *opts); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* __LIBBPF_BPF_H */ diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_core_read.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_core_read.h deleted file mode 100644 index fd48b1ff59cad2cd2bb84480d063763b7429738e..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_core_read.h +++ /dev/null @@ -1,473 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __BPF_CORE_READ_H__ -#define __BPF_CORE_READ_H__ - -/* - * enum bpf_field_info_kind is passed as a second argument into - * __builtin_preserve_field_info() built-in to get a specific aspect of - * a field, captured as a first argument. __builtin_preserve_field_info(field, - * info_kind) returns __u32 integer and produces BTF field relocation, which - * is understood and processed by libbpf during BPF object loading. See - * selftests/bpf for examples. - */ -enum bpf_field_info_kind { - BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ - BPF_FIELD_BYTE_SIZE = 1, - BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ - BPF_FIELD_SIGNED = 3, - BPF_FIELD_LSHIFT_U64 = 4, - BPF_FIELD_RSHIFT_U64 = 5, -}; - -/* second argument to __builtin_btf_type_id() built-in */ -enum bpf_type_id_kind { - BPF_TYPE_ID_LOCAL = 0, /* BTF type ID in local program */ - BPF_TYPE_ID_TARGET = 1, /* BTF type ID in target kernel */ -}; - -/* second argument to __builtin_preserve_type_info() built-in */ -enum bpf_type_info_kind { - BPF_TYPE_EXISTS = 0, /* type existence in target kernel */ - BPF_TYPE_SIZE = 1, /* type size in target kernel */ -}; - -/* second argument to __builtin_preserve_enum_value() built-in */ -enum bpf_enum_value_kind { - BPF_ENUMVAL_EXISTS = 0, /* enum value existence in kernel */ - BPF_ENUMVAL_VALUE = 1, /* enum value value relocation */ -}; - -#define __CORE_RELO(src, field, info) \ - __builtin_preserve_field_info((src)->field, BPF_FIELD_##info) - -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ -#define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ - bpf_probe_read_kernel( \ - (void *)dst, \ - __CORE_RELO(src, fld, BYTE_SIZE), \ - (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) -#else -/* semantics of LSHIFT_64 assumes loading values into low-ordered bytes, so - * for big-endian we need to adjust destination pointer accordingly, based on - * field byte size - */ -#define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ - bpf_probe_read_kernel( \ - (void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)), \ - __CORE_RELO(src, fld, BYTE_SIZE), \ - (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) -#endif - -/* - * Extract bitfield, identified by s->field, and return its value as u64. - * All this is done in relocatable manner, so bitfield changes such as - * signedness, bit size, offset changes, this will be handled automatically. - * This version of macro is using bpf_probe_read_kernel() to read underlying - * integer storage. Macro functions as an expression and its return type is - * bpf_probe_read_kernel()'s return value: 0, on success, <0 on error. - */ -#define BPF_CORE_READ_BITFIELD_PROBED(s, field) ({ \ - unsigned long long val = 0; \ - \ - __CORE_BITFIELD_PROBE_READ(&val, s, field); \ - val <<= __CORE_RELO(s, field, LSHIFT_U64); \ - if (__CORE_RELO(s, field, SIGNED)) \ - val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64); \ - else \ - val = val >> __CORE_RELO(s, field, RSHIFT_U64); \ - val; \ -}) - -/* - * Extract bitfield, identified by s->field, and return its value as u64. - * This version of macro is using direct memory reads and should be used from - * BPF program types that support such functionality (e.g., typed raw - * tracepoints). - */ -#define BPF_CORE_READ_BITFIELD(s, field) ({ \ - const void *p = (const void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \ - unsigned long long val; \ - \ - /* This is a so-called barrier_var() operation that makes specified \ - * variable "a black box" for optimizing compiler. \ - * It forces compiler to perform BYTE_OFFSET relocation on p and use \ - * its calculated value in the switch below, instead of applying \ - * the same relocation 4 times for each individual memory load. \ - */ \ - asm volatile("" : "=r"(p) : "0"(p)); \ - \ - switch (__CORE_RELO(s, field, BYTE_SIZE)) { \ - case 1: val = *(const unsigned char *)p; break; \ - case 2: val = *(const unsigned short *)p; break; \ - case 4: val = *(const unsigned int *)p; break; \ - case 8: val = *(const unsigned long long *)p; break; \ - } \ - val <<= __CORE_RELO(s, field, LSHIFT_U64); \ - if (__CORE_RELO(s, field, SIGNED)) \ - val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64); \ - else \ - val = val >> __CORE_RELO(s, field, RSHIFT_U64); \ - val; \ -}) - -#define ___bpf_field_ref1(field) (field) -#define ___bpf_field_ref2(type, field) (((typeof(type) *)0)->field) -#define ___bpf_field_ref(args...) \ - ___bpf_apply(___bpf_field_ref, ___bpf_narg(args))(args) - -/* - * Convenience macro to check that field actually exists in target kernel's. - * Returns: - * 1, if matching field is present in target kernel; - * 0, if no matching field found. - * - * Supports two forms: - * - field reference through variable access: - * bpf_core_field_exists(p->my_field); - * - field reference through type and field names: - * bpf_core_field_exists(struct my_type, my_field). - */ -#define bpf_core_field_exists(field...) \ - __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_EXISTS) - -/* - * Convenience macro to get the byte size of a field. Works for integers, - * struct/unions, pointers, arrays, and enums. - * - * Supports two forms: - * - field reference through variable access: - * bpf_core_field_size(p->my_field); - * - field reference through type and field names: - * bpf_core_field_size(struct my_type, my_field). - */ -#define bpf_core_field_size(field...) \ - __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_SIZE) - -/* - * Convenience macro to get field's byte offset. - * - * Supports two forms: - * - field reference through variable access: - * bpf_core_field_offset(p->my_field); - * - field reference through type and field names: - * bpf_core_field_offset(struct my_type, my_field). - */ -#define bpf_core_field_offset(field...) \ - __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_OFFSET) - -/* - * Convenience macro to get BTF type ID of a specified type, using a local BTF - * information. Return 32-bit unsigned integer with type ID from program's own - * BTF. Always succeeds. - */ -#define bpf_core_type_id_local(type) \ - __builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_LOCAL) - -/* - * Convenience macro to get BTF type ID of a target kernel's type that matches - * specified local type. - * Returns: - * - valid 32-bit unsigned type ID in kernel BTF; - * - 0, if no matching type was found in a target kernel BTF. - */ -#define bpf_core_type_id_kernel(type) \ - __builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_TARGET) - -/* - * Convenience macro to check that provided named type - * (struct/union/enum/typedef) exists in a target kernel. - * Returns: - * 1, if such type is present in target kernel's BTF; - * 0, if no matching type is found. - */ -#define bpf_core_type_exists(type) \ - __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS) - -/* - * Convenience macro to get the byte size of a provided named type - * (struct/union/enum/typedef) in a target kernel. - * Returns: - * >= 0 size (in bytes), if type is present in target kernel's BTF; - * 0, if no matching type is found. - */ -#define bpf_core_type_size(type) \ - __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_SIZE) - -/* - * Convenience macro to check that provided enumerator value is defined in - * a target kernel. - * Returns: - * 1, if specified enum type and its enumerator value are present in target - * kernel's BTF; - * 0, if no matching enum and/or enum value within that enum is found. - */ -#define bpf_core_enum_value_exists(enum_type, enum_value) \ - __builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_EXISTS) - -/* - * Convenience macro to get the integer value of an enumerator value in - * a target kernel. - * Returns: - * 64-bit value, if specified enum type and its enumerator value are - * present in target kernel's BTF; - * 0, if no matching enum and/or enum value within that enum is found. - */ -#define bpf_core_enum_value(enum_type, enum_value) \ - __builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_VALUE) - -/* - * bpf_core_read() abstracts away bpf_probe_read_kernel() call and captures - * offset relocation for source address using __builtin_preserve_access_index() - * built-in, provided by Clang. - * - * __builtin_preserve_access_index() takes as an argument an expression of - * taking an address of a field within struct/union. It makes compiler emit - * a relocation, which records BTF type ID describing root struct/union and an - * accessor string which describes exact embedded field that was used to take - * an address. See detailed description of this relocation format and - * semantics in comments to struct bpf_field_reloc in libbpf_internal.h. - * - * This relocation allows libbpf to adjust BPF instruction to use correct - * actual field offset, based on target kernel BTF type that matches original - * (local) BTF, used to record relocation. - */ -#define bpf_core_read(dst, sz, src) \ - bpf_probe_read_kernel(dst, sz, (const void *)__builtin_preserve_access_index(src)) - -/* NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. */ -#define bpf_core_read_user(dst, sz, src) \ - bpf_probe_read_user(dst, sz, (const void *)__builtin_preserve_access_index(src)) -/* - * bpf_core_read_str() is a thin wrapper around bpf_probe_read_str() - * additionally emitting BPF CO-RE field relocation for specified source - * argument. - */ -#define bpf_core_read_str(dst, sz, src) \ - bpf_probe_read_kernel_str(dst, sz, (const void *)__builtin_preserve_access_index(src)) - -/* NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. */ -#define bpf_core_read_user_str(dst, sz, src) \ - bpf_probe_read_user_str(dst, sz, (const void *)__builtin_preserve_access_index(src)) - -#define ___concat(a, b) a ## b -#define ___apply(fn, n) ___concat(fn, n) -#define ___nth(_1, _2, _3, _4, _5, _6, _7, _8, _9, _10, __11, N, ...) N - -/* - * return number of provided arguments; used for switch-based variadic macro - * definitions (see ___last, ___arrow, etc below) - */ -#define ___narg(...) ___nth(_, ##__VA_ARGS__, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) -/* - * return 0 if no arguments are passed, N - otherwise; used for - * recursively-defined macros to specify termination (0) case, and generic - * (N) case (e.g., ___read_ptrs, ___core_read) - */ -#define ___empty(...) ___nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0) - -#define ___last1(x) x -#define ___last2(a, x) x -#define ___last3(a, b, x) x -#define ___last4(a, b, c, x) x -#define ___last5(a, b, c, d, x) x -#define ___last6(a, b, c, d, e, x) x -#define ___last7(a, b, c, d, e, f, x) x -#define ___last8(a, b, c, d, e, f, g, x) x -#define ___last9(a, b, c, d, e, f, g, h, x) x -#define ___last10(a, b, c, d, e, f, g, h, i, x) x -#define ___last(...) ___apply(___last, ___narg(__VA_ARGS__))(__VA_ARGS__) - -#define ___nolast2(a, _) a -#define ___nolast3(a, b, _) a, b -#define ___nolast4(a, b, c, _) a, b, c -#define ___nolast5(a, b, c, d, _) a, b, c, d -#define ___nolast6(a, b, c, d, e, _) a, b, c, d, e -#define ___nolast7(a, b, c, d, e, f, _) a, b, c, d, e, f -#define ___nolast8(a, b, c, d, e, f, g, _) a, b, c, d, e, f, g -#define ___nolast9(a, b, c, d, e, f, g, h, _) a, b, c, d, e, f, g, h -#define ___nolast10(a, b, c, d, e, f, g, h, i, _) a, b, c, d, e, f, g, h, i -#define ___nolast(...) ___apply(___nolast, ___narg(__VA_ARGS__))(__VA_ARGS__) - -#define ___arrow1(a) a -#define ___arrow2(a, b) a->b -#define ___arrow3(a, b, c) a->b->c -#define ___arrow4(a, b, c, d) a->b->c->d -#define ___arrow5(a, b, c, d, e) a->b->c->d->e -#define ___arrow6(a, b, c, d, e, f) a->b->c->d->e->f -#define ___arrow7(a, b, c, d, e, f, g) a->b->c->d->e->f->g -#define ___arrow8(a, b, c, d, e, f, g, h) a->b->c->d->e->f->g->h -#define ___arrow9(a, b, c, d, e, f, g, h, i) a->b->c->d->e->f->g->h->i -#define ___arrow10(a, b, c, d, e, f, g, h, i, j) a->b->c->d->e->f->g->h->i->j -#define ___arrow(...) ___apply(___arrow, ___narg(__VA_ARGS__))(__VA_ARGS__) - -#define ___type(...) typeof(___arrow(__VA_ARGS__)) - -#define ___read(read_fn, dst, src_type, src, accessor) \ - read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor) - -/* "recursively" read a sequence of inner pointers using local __t var */ -#define ___rd_first(fn, src, a) ___read(fn, &__t, ___type(src), src, a); -#define ___rd_last(fn, ...) \ - ___read(fn, &__t, ___type(___nolast(__VA_ARGS__)), __t, ___last(__VA_ARGS__)); -#define ___rd_p1(fn, ...) const void *__t; ___rd_first(fn, __VA_ARGS__) -#define ___rd_p2(fn, ...) ___rd_p1(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) -#define ___rd_p3(fn, ...) ___rd_p2(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) -#define ___rd_p4(fn, ...) ___rd_p3(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) -#define ___rd_p5(fn, ...) ___rd_p4(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) -#define ___rd_p6(fn, ...) ___rd_p5(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) -#define ___rd_p7(fn, ...) ___rd_p6(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) -#define ___rd_p8(fn, ...) ___rd_p7(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) -#define ___rd_p9(fn, ...) ___rd_p8(fn, ___nolast(__VA_ARGS__)) ___rd_last(fn, __VA_ARGS__) -#define ___read_ptrs(fn, src, ...) \ - ___apply(___rd_p, ___narg(__VA_ARGS__))(fn, src, __VA_ARGS__) - -#define ___core_read0(fn, fn_ptr, dst, src, a) \ - ___read(fn, dst, ___type(src), src, a); -#define ___core_readN(fn, fn_ptr, dst, src, ...) \ - ___read_ptrs(fn_ptr, src, ___nolast(__VA_ARGS__)) \ - ___read(fn, dst, ___type(src, ___nolast(__VA_ARGS__)), __t, \ - ___last(__VA_ARGS__)); -#define ___core_read(fn, fn_ptr, dst, src, a, ...) \ - ___apply(___core_read, ___empty(__VA_ARGS__))(fn, fn_ptr, dst, \ - src, a, ##__VA_ARGS__) - -/* - * BPF_CORE_READ_INTO() is a more performance-conscious variant of - * BPF_CORE_READ(), in which final field is read into user-provided storage. - * See BPF_CORE_READ() below for more details on general usage. - */ -#define BPF_CORE_READ_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_core_read, bpf_core_read, \ - dst, (src), a, ##__VA_ARGS__) \ -}) - -/* - * Variant of BPF_CORE_READ_INTO() for reading from user-space memory. - * - * NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. - */ -#define BPF_CORE_READ_USER_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_core_read_user, bpf_core_read_user, \ - dst, (src), a, ##__VA_ARGS__) \ -}) - -/* Non-CO-RE variant of BPF_CORE_READ_INTO() */ -#define BPF_PROBE_READ_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read, bpf_probe_read, \ - dst, (src), a, ##__VA_ARGS__) \ -}) - -/* Non-CO-RE variant of BPF_CORE_READ_USER_INTO(). - * - * As no CO-RE relocations are emitted, source types can be arbitrary and are - * not restricted to kernel types only. - */ -#define BPF_PROBE_READ_USER_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read_user, bpf_probe_read_user, \ - dst, (src), a, ##__VA_ARGS__) \ -}) - -/* - * BPF_CORE_READ_STR_INTO() does same "pointer chasing" as - * BPF_CORE_READ() for intermediate pointers, but then executes (and returns - * corresponding error code) bpf_core_read_str() for final string read. - */ -#define BPF_CORE_READ_STR_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_core_read_str, bpf_core_read, \ - dst, (src), a, ##__VA_ARGS__) \ -}) - -/* - * Variant of BPF_CORE_READ_STR_INTO() for reading from user-space memory. - * - * NOTE: see comments for BPF_CORE_READ_USER() about the proper types use. - */ -#define BPF_CORE_READ_USER_STR_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_core_read_user_str, bpf_core_read_user, \ - dst, (src), a, ##__VA_ARGS__) \ -}) - -/* Non-CO-RE variant of BPF_CORE_READ_STR_INTO() */ -#define BPF_PROBE_READ_STR_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read_str, bpf_probe_read, \ - dst, (src), a, ##__VA_ARGS__) \ -}) - -/* - * Non-CO-RE variant of BPF_CORE_READ_USER_STR_INTO(). - * - * As no CO-RE relocations are emitted, source types can be arbitrary and are - * not restricted to kernel types only. - */ -#define BPF_PROBE_READ_USER_STR_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read_user_str, bpf_probe_read_user, \ - dst, (src), a, ##__VA_ARGS__) \ -}) - -/* - * BPF_CORE_READ() is used to simplify BPF CO-RE relocatable read, especially - * when there are few pointer chasing steps. - * E.g., what in non-BPF world (or in BPF w/ BCC) would be something like: - * int x = s->a.b.c->d.e->f->g; - * can be succinctly achieved using BPF_CORE_READ as: - * int x = BPF_CORE_READ(s, a.b.c, d.e, f, g); - * - * BPF_CORE_READ will decompose above statement into 4 bpf_core_read (BPF - * CO-RE relocatable bpf_probe_read_kernel() wrapper) calls, logically - * equivalent to: - * 1. const void *__t = s->a.b.c; - * 2. __t = __t->d.e; - * 3. __t = __t->f; - * 4. return __t->g; - * - * Equivalence is logical, because there is a heavy type casting/preservation - * involved, as well as all the reads are happening through - * bpf_probe_read_kernel() calls using __builtin_preserve_access_index() to - * emit CO-RE relocations. - * - * N.B. Only up to 9 "field accessors" are supported, which should be more - * than enough for any practical purpose. - */ -#define BPF_CORE_READ(src, a, ...) ({ \ - ___type((src), a, ##__VA_ARGS__) __r; \ - BPF_CORE_READ_INTO(&__r, (src), a, ##__VA_ARGS__); \ - __r; \ -}) - -/* - * Variant of BPF_CORE_READ() for reading from user-space memory. - * - * NOTE: all the source types involved are still *kernel types* and need to - * exist in kernel (or kernel module) BTF, otherwise CO-RE relocation will - * fail. Custom user types are not relocatable with CO-RE. - * The typical situation in which BPF_CORE_READ_USER() might be used is to - * read kernel UAPI types from the user-space memory passed in as a syscall - * input argument. - */ -#define BPF_CORE_READ_USER(src, a, ...) ({ \ - ___type((src), a, ##__VA_ARGS__) __r; \ - BPF_CORE_READ_USER_INTO(&__r, (src), a, ##__VA_ARGS__); \ - __r; \ -}) - -/* Non-CO-RE variant of BPF_CORE_READ() */ -#define BPF_PROBE_READ(src, a, ...) ({ \ - ___type((src), a, ##__VA_ARGS__) __r; \ - BPF_PROBE_READ_INTO(&__r, (src), a, ##__VA_ARGS__); \ - __r; \ -}) - -/* - * Non-CO-RE variant of BPF_CORE_READ_USER(). - * - * As no CO-RE relocations are emitted, source types can be arbitrary and are - * not restricted to kernel types only. - */ -#define BPF_PROBE_READ_USER(src, a, ...) ({ \ - ___type((src), a, ##__VA_ARGS__) __r; \ - BPF_PROBE_READ_USER_INTO(&__r, (src), a, ##__VA_ARGS__); \ - __r; \ -}) - -#endif - diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_endian.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_endian.h deleted file mode 100644 index ec9db4feca9f2f308254732bd411098ad6585556..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_endian.h +++ /dev/null @@ -1,99 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __BPF_ENDIAN__ -#define __BPF_ENDIAN__ - -/* - * Isolate byte #n and put it into byte #m, for __u##b type. - * E.g., moving byte #6 (nnnnnnnn) into byte #1 (mmmmmmmm) for __u64: - * 1) xxxxxxxx nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx - * 2) nnnnnnnn xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx mmmmmmmm xxxxxxxx 00000000 - * 3) 00000000 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn - * 4) 00000000 00000000 00000000 00000000 00000000 00000000 nnnnnnnn 00000000 - */ -#define ___bpf_mvb(x, b, n, m) ((__u##b)(x) << (b-(n+1)*8) >> (b-8) << (m*8)) - -#define ___bpf_swab16(x) ((__u16)( \ - ___bpf_mvb(x, 16, 0, 1) | \ - ___bpf_mvb(x, 16, 1, 0))) - -#define ___bpf_swab32(x) ((__u32)( \ - ___bpf_mvb(x, 32, 0, 3) | \ - ___bpf_mvb(x, 32, 1, 2) | \ - ___bpf_mvb(x, 32, 2, 1) | \ - ___bpf_mvb(x, 32, 3, 0))) - -#define ___bpf_swab64(x) ((__u64)( \ - ___bpf_mvb(x, 64, 0, 7) | \ - ___bpf_mvb(x, 64, 1, 6) | \ - ___bpf_mvb(x, 64, 2, 5) | \ - ___bpf_mvb(x, 64, 3, 4) | \ - ___bpf_mvb(x, 64, 4, 3) | \ - ___bpf_mvb(x, 64, 5, 2) | \ - ___bpf_mvb(x, 64, 6, 1) | \ - ___bpf_mvb(x, 64, 7, 0))) - -/* LLVM's BPF target selects the endianness of the CPU - * it compiles on, or the user specifies (bpfel/bpfeb), - * respectively. The used __BYTE_ORDER__ is defined by - * the compiler, we cannot rely on __BYTE_ORDER from - * libc headers, since it doesn't reflect the actual - * requested byte order. - * - * Note, LLVM's BPF target has different __builtin_bswapX() - * semantics. It does map to BPF_ALU | BPF_END | BPF_TO_BE - * in bpfel and bpfeb case, which means below, that we map - * to cpu_to_be16(). We could use it unconditionally in BPF - * case, but better not rely on it, so that this header here - * can be used from application and BPF program side, which - * use different targets. - */ -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ -# define __bpf_ntohs(x) __builtin_bswap16(x) -# define __bpf_htons(x) __builtin_bswap16(x) -# define __bpf_constant_ntohs(x) ___bpf_swab16(x) -# define __bpf_constant_htons(x) ___bpf_swab16(x) -# define __bpf_ntohl(x) __builtin_bswap32(x) -# define __bpf_htonl(x) __builtin_bswap32(x) -# define __bpf_constant_ntohl(x) ___bpf_swab32(x) -# define __bpf_constant_htonl(x) ___bpf_swab32(x) -# define __bpf_be64_to_cpu(x) __builtin_bswap64(x) -# define __bpf_cpu_to_be64(x) __builtin_bswap64(x) -# define __bpf_constant_be64_to_cpu(x) ___bpf_swab64(x) -# define __bpf_constant_cpu_to_be64(x) ___bpf_swab64(x) -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ -# define __bpf_ntohs(x) (x) -# define __bpf_htons(x) (x) -# define __bpf_constant_ntohs(x) (x) -# define __bpf_constant_htons(x) (x) -# define __bpf_ntohl(x) (x) -# define __bpf_htonl(x) (x) -# define __bpf_constant_ntohl(x) (x) -# define __bpf_constant_htonl(x) (x) -# define __bpf_be64_to_cpu(x) (x) -# define __bpf_cpu_to_be64(x) (x) -# define __bpf_constant_be64_to_cpu(x) (x) -# define __bpf_constant_cpu_to_be64(x) (x) -#else -# error "Fix your compiler's __BYTE_ORDER__?!" -#endif - -#define bpf_htons(x) \ - (__builtin_constant_p(x) ? \ - __bpf_constant_htons(x) : __bpf_htons(x)) -#define bpf_ntohs(x) \ - (__builtin_constant_p(x) ? \ - __bpf_constant_ntohs(x) : __bpf_ntohs(x)) -#define bpf_htonl(x) \ - (__builtin_constant_p(x) ? \ - __bpf_constant_htonl(x) : __bpf_htonl(x)) -#define bpf_ntohl(x) \ - (__builtin_constant_p(x) ? \ - __bpf_constant_ntohl(x) : __bpf_ntohl(x)) -#define bpf_cpu_to_be64(x) \ - (__builtin_constant_p(x) ? \ - __bpf_constant_cpu_to_be64(x) : __bpf_cpu_to_be64(x)) -#define bpf_be64_to_cpu(x) \ - (__builtin_constant_p(x) ? \ - __bpf_constant_be64_to_cpu(x) : __bpf_be64_to_cpu(x)) - -#endif /* __BPF_ENDIAN__ */ diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_helper_defs.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_helper_defs.h deleted file mode 100644 index abe612ea82969c92f2494b76040f6325720ec037..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_helper_defs.h +++ /dev/null @@ -1,4373 +0,0 @@ -/* This is auto-generated file. See bpf_doc.py for details. */ - -/* Forward declarations of BPF structs */ -struct bpf_fib_lookup; -struct bpf_sk_lookup; -struct bpf_perf_event_data; -struct bpf_perf_event_value; -struct bpf_pidns_info; -struct bpf_redir_neigh; -struct bpf_sock; -struct bpf_sock_addr; -struct bpf_sock_ops; -struct bpf_sock_tuple; -struct bpf_spin_lock; -struct bpf_sysctl; -struct bpf_tcp_sock; -struct bpf_tunnel_key; -struct bpf_xfrm_state; -struct linux_binprm; -struct pt_regs; -struct sk_reuseport_md; -struct sockaddr; -struct tcphdr; -struct seq_file; -struct tcp6_sock; -struct tcp_sock; -struct tcp_timewait_sock; -struct tcp_request_sock; -struct udp6_sock; -struct unix_sock; -struct task_struct; -struct __sk_buff; -struct sk_msg_md; -struct xdp_md; -struct path; -struct btf_ptr; -struct inode; -struct socket; -struct file; -struct bpf_timer; - -/* - * bpf_map_lookup_elem - * - * Perform a lookup in *map* for an entry associated to *key*. - * - * Returns - * Map value associated to *key*, or **NULL** if no entry was - * found. - */ -static void *(*bpf_map_lookup_elem)(void *map, const void *key) = (void *) 1; - -/* - * bpf_map_update_elem - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_map_update_elem)(void *map, const void *key, const void *value, __u64 flags) = (void *) 2; - -/* - * bpf_map_delete_elem - * - * Delete entry with *key* from *map*. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_map_delete_elem)(void *map, const void *key) = (void *) 3; - -/* - * bpf_probe_read - * - * For tracing programs, safely attempt to read *size* bytes from - * kernel space address *unsafe_ptr* and store the data in *dst*. - * - * Generally, use **bpf_probe_read_user**\ () or - * **bpf_probe_read_kernel**\ () instead. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_probe_read)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 4; - -/* - * bpf_ktime_get_ns - * - * Return the time elapsed since system boot, in nanoseconds. - * Does not include time the system was suspended. - * See: **clock_gettime**\ (**CLOCK_MONOTONIC**) - * - * Returns - * Current *ktime*. - */ -static __u64 (*bpf_ktime_get_ns)(void) = (void *) 5; - -/* - * bpf_trace_printk - * - * 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. - * Lines are discarded while *\/sys/kernel/debug/tracing/trace* is - * open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this. - * 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 - * block (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. - * - * Returns - * The number of bytes written to the buffer, or a negative error - * in case of failure. - */ -static long (*bpf_trace_printk)(const char *fmt, __u32 fmt_size, ...) = (void *) 6; - -/* - * bpf_get_prandom_u32 - * - * 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. - * - * Returns - * A random 32-bit unsigned value. - */ -static __u32 (*bpf_get_prandom_u32)(void) = (void *) 7; - -/* - * bpf_get_smp_processor_id - * - * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with migration disabled, which means that the - * SMP processor id is stable during all the execution of the - * program. - * - * Returns - * The SMP id of the processor running the program. - */ -static __u32 (*bpf_get_smp_processor_id)(void) = (void *) 8; - -/* - * bpf_skb_store_bytes - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_store_bytes)(struct __sk_buff *skb, __u32 offset, const void *from, __u32 len, __u64 flags) = (void *) 9; - -/* - * bpf_l3_csum_replace - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_l3_csum_replace)(struct __sk_buff *skb, __u32 offset, __u64 from, __u64 to, __u64 size) = (void *) 10; - -/* - * bpf_l4_csum_replace - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_l4_csum_replace)(struct __sk_buff *skb, __u32 offset, __u64 from, __u64 to, __u64 flags) = (void *) 11; - -/* - * bpf_tail_call - * - * 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 33. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_tail_call)(void *ctx, void *prog_array_map, __u32 index) = (void *) 12; - -/* - * bpf_clone_redirect - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_clone_redirect)(struct __sk_buff *skb, __u32 ifindex, __u64 flags) = (void *) 13; - -/* - * bpf_get_current_pid_tgid - * - * Get the current pid and tgid. - * - * Returns - * A 64-bit integer containing the current tgid and pid, and - * created as such: - * *current_task*\ **->tgid << 32 \|** - * *current_task*\ **->pid**. - */ -static __u64 (*bpf_get_current_pid_tgid)(void) = (void *) 14; - -/* - * bpf_get_current_uid_gid - * - * Get the current uid and gid. - * - * Returns - * A 64-bit integer containing the current GID and UID, and - * created as such: *current_gid* **<< 32 \|** *current_uid*. - */ -static __u64 (*bpf_get_current_uid_gid)(void) = (void *) 15; - -/* - * bpf_get_current_comm - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_get_current_comm)(void *buf, __u32 size_of_buf) = (void *) 16; - -/* - * bpf_get_cgroup_classid - * - * 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/admin-guide/cgroup-v1/net_cls.rst*. - * - * 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**". - * - * Returns - * The classid, or 0 for the default unconfigured classid. - */ -static __u32 (*bpf_get_cgroup_classid)(struct __sk_buff *skb) = (void *) 17; - -/* - * bpf_skb_vlan_push - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_vlan_push)(struct __sk_buff *skb, __be16 vlan_proto, __u16 vlan_tci) = (void *) 18; - -/* - * bpf_skb_vlan_pop - * - * Pop a VLAN header from the packet associated to *skb*. - * - * A call to this helper is susceptible to change the underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_vlan_pop)(struct __sk_buff *skb) = (void *) 19; - -/* - * bpf_skb_get_tunnel_key - * - * 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). - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_get_tunnel_key)(struct __sk_buff *skb, struct bpf_tunnel_key *key, __u32 size, __u64 flags) = (void *) 20; - -/* - * bpf_skb_set_tunnel_key - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_set_tunnel_key)(struct __sk_buff *skb, struct bpf_tunnel_key *key, __u32 size, __u64 flags) = (void *) 21; - -/* - * bpf_perf_event_read - * - * 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. - * - * Returns - * The value of the perf event counter read from the map, or a - * negative error code in case of failure. - */ -static __u64 (*bpf_perf_event_read)(void *map, __u64 flags) = (void *) 22; - -/* - * bpf_redirect - * - * 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 also be attained with the more generic - * **bpf_redirect_map**\ (), which uses a BPF map to store the - * redirect target instead of providing it directly to the helper. - * - * Returns - * 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. - */ -static long (*bpf_redirect)(__u32 ifindex, __u64 flags) = (void *) 23; - -/* - * bpf_get_route_realm - * - * Retrieve the realm or the route, that is to say the - * **tclassid** field of the destination for the *skb*. The - * identifier 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. - * - * Returns - * The realm of the route for the packet associated to *skb*, or 0 - * if none was found. - */ -static __u32 (*bpf_get_route_realm)(struct __sk_buff *skb) = (void *) 24; - -/* - * bpf_perf_event_output - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_perf_event_output)(void *ctx, void *map, __u64 flags, void *data, __u64 size) = (void *) 25; - -/* - * bpf_skb_load_bytes - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_load_bytes)(const void *skb, __u32 offset, void *to, __u32 len) = (void *) 26; - -/* - * bpf_get_stackid - * - * 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= - * - * Returns - * The positive or null stack id on success, or a negative error - * in case of failure. - */ -static long (*bpf_get_stackid)(void *ctx, void *map, __u64 flags) = (void *) 27; - -/* - * bpf_csum_diff - * - * 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**\ (). - * - * Returns - * The checksum result, or a negative error code in case of - * failure. - */ -static __s64 (*bpf_csum_diff)(__be32 *from, __u32 from_size, __be32 *to, __u32 to_size, __wsum seed) = (void *) 28; - -/* - * bpf_skb_get_tunnel_opt - * - * 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. - * - * Returns - * The size of the option data retrieved. - */ -static long (*bpf_skb_get_tunnel_opt)(struct __sk_buff *skb, void *opt, __u32 size) = (void *) 29; - -/* - * bpf_skb_set_tunnel_opt - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_set_tunnel_opt)(struct __sk_buff *skb, void *opt, __u32 size) = (void *) 30; - -/* - * bpf_skb_change_proto - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_change_proto)(struct __sk_buff *skb, __be16 proto, __u64 flags) = (void *) 31; - -/* - * bpf_skb_change_type - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_change_type)(struct __sk_buff *skb, __u32 type) = (void *) 32; - -/* - * bpf_skb_under_cgroup - * - * Check whether *skb* is a descendant of the cgroup2 held by - * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. - * - * Returns - * 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. - */ -static long (*bpf_skb_under_cgroup)(struct __sk_buff *skb, void *map, __u32 index) = (void *) 33; - -/* - * bpf_get_hash_recalc - * - * 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**\ (). - * - * Returns - * The 32-bit hash. - */ -static __u32 (*bpf_get_hash_recalc)(struct __sk_buff *skb) = (void *) 34; - -/* - * bpf_get_current_task - * - * Get the current task. - * - * Returns - * A pointer to the current task struct. - */ -static __u64 (*bpf_get_current_task)(void) = (void *) 35; - -/* - * bpf_probe_write_user - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_probe_write_user)(void *dst, const void *src, __u32 len) = (void *) 36; - -/* - * bpf_current_task_under_cgroup - * - * 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*. - * - * Returns - * The return value depends on the result of the test, and can be: - * - * * 1, if current task belongs to the cgroup2. - * * 0, if current task does not belong to the cgroup2. - * * A negative error code, if an error occurred. - */ -static long (*bpf_current_task_under_cgroup)(void *map, __u32 index) = (void *) 37; - -/* - * bpf_skb_change_tail - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_change_tail)(struct __sk_buff *skb, __u32 len, __u64 flags) = (void *) 38; - -/* - * bpf_skb_pull_data - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_pull_data)(struct __sk_buff *skb, __u32 len) = (void *) 39; - -/* - * bpf_csum_update - * - * 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. - * - * Returns - * The checksum on success, or a negative error code in case of - * failure. - */ -static __s64 (*bpf_csum_update)(struct __sk_buff *skb, __wsum csum) = (void *) 40; - -/* - * bpf_set_hash_invalid - * - * 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. - * - * Returns - * void. - */ -static void (*bpf_set_hash_invalid)(struct __sk_buff *skb) = (void *) 41; - -/* - * bpf_get_numa_node_id - * - * 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**\ (). - * - * Returns - * The id of current NUMA node. - */ -static long (*bpf_get_numa_node_id)(void) = (void *) 42; - -/* - * bpf_skb_change_head - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_change_head)(struct __sk_buff *skb, __u32 len, __u64 flags) = (void *) 43; - -/* - * bpf_xdp_adjust_head - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_xdp_adjust_head)(struct xdp_md *xdp_md, int delta) = (void *) 44; - -/* - * bpf_probe_read_str - * - * Copy a NUL terminated string from an unsafe kernel address - * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for - * more details. - * - * Generally, use **bpf_probe_read_user_str**\ () or - * **bpf_probe_read_kernel_str**\ () instead. - * - * Returns - * On success, the strictly positive length of the string, - * including the trailing NUL character. On error, a negative - * value. - */ -static long (*bpf_probe_read_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 45; - -/* - * bpf_get_socket_cookie - * - * 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 global socket - * identifier that can be assumed unique. - * - * Returns - * A 8-byte long unique number on success, or 0 if the socket - * field is missing inside *skb*. - */ -static __u64 (*bpf_get_socket_cookie)(void *ctx) = (void *) 46; - -/* - * bpf_get_socket_uid - * - * Get the owner UID of the socked associated to *skb*. - * - * Returns - * 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). - */ -static __u32 (*bpf_get_socket_uid)(struct __sk_buff *skb) = (void *) 47; - -/* - * bpf_set_hash - * - * Set the full hash for *skb* (set the field *skb*\ **->hash**) - * to value *hash*. - * - * Returns - * 0 - */ -static long (*bpf_set_hash)(struct __sk_buff *skb, __u32 hash) = (void *) 48; - -/* - * bpf_setsockopt - * - * 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*. - * - * *bpf_socket* should be one of the following: - * - * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. - * - * 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**, - * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. - * * **IPPROTO_TCP**, which supports the following *optname*\ s: - * **TCP_CONGESTION**, **TCP_BPF_IW**, - * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, - * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, - * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**. - * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_setsockopt)(void *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 49; - -/* - * bpf_skb_adjust_room - * - * Grow or shrink the room for data in the packet associated to - * *skb* by *len_diff*, and according to the selected *mode*. - * - * By default, the helper will reset any offloaded checksum - * indicator of the skb to CHECKSUM_NONE. This can be avoided - * by the following flag: - * - * * **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded - * checksum data of the skb to CHECKSUM_NONE. - * - * There are two supported modes at this time: - * - * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer - * (room space is added or removed below the layer 2 header). - * - * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer - * (room space is added or removed below the layer 3 header). - * - * The following flags are supported at this time: - * - * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size. - * Adjusting mss in this way is not allowed for datagrams. - * - * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**, - * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**: - * Any new space is reserved to hold a tunnel header. - * Configure skb offsets and other fields accordingly. - * - * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**, - * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**: - * Use with ENCAP_L3 flags to further specify the tunnel type. - * - * * **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*): - * Use with ENCAP_L3/L4 flags to further specify the tunnel - * type; *len* is the length of the inner MAC header. - * - * * **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**: - * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the - * L2 type as Ethernet. - * - * A call to this helper is susceptible to change the underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_adjust_room)(struct __sk_buff *skb, __s32 len_diff, __u32 mode, __u64 flags) = (void *) 50; - -/* - * bpf_redirect_map - * - * 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). - * - * The lower two bits of *flags* are used as the return code if - * the map lookup fails. This is so that the return value can be - * one of the XDP program return codes up to **XDP_TX**, as chosen - * by the caller. The higher bits of *flags* can be set to - * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below. - * - * With BPF_F_BROADCAST the packet will be broadcasted to all the - * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress - * interface will be excluded when do broadcasting. - * - * See also **bpf_redirect**\ (), which only supports redirecting - * to an ifindex, but doesn't require a map to do so. - * - * Returns - * **XDP_REDIRECT** on success, or the value of the two lower bits - * of the *flags* argument on error. - */ -static long (*bpf_redirect_map)(void *map, __u32 key, __u64 flags) = (void *) 51; - -/* - * bpf_sk_redirect_map - * - * 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. - * - * Returns - * **SK_PASS** on success, or **SK_DROP** on error. - */ -static long (*bpf_sk_redirect_map)(struct __sk_buff *skb, void *map, __u32 key, __u64 flags) = (void *) 52; - -/* - * bpf_sock_map_update - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_sock_map_update)(struct bpf_sock_ops *skops, void *map, void *key, __u64 flags) = (void *) 53; - -/* - * bpf_xdp_adjust_meta - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_xdp_adjust_meta)(struct xdp_md *xdp_md, int delta) = (void *) 54; - -/* - * bpf_perf_event_read_value - * - * 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 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_perf_event_read_value)(void *map, __u64 flags, struct bpf_perf_event_value *buf, __u32 buf_size) = (void *) 55; - -/* - * bpf_perf_prog_read_value - * - * 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). - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_perf_prog_read_value)(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, __u32 buf_size) = (void *) 56; - -/* - * bpf_getsockopt - * - * 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*. - * - * *bpf_socket* should be one of the following: - * - * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. - * - * 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**. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_getsockopt)(void *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 57; - -/* - * bpf_override_return - * - * 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 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. - * - * Returns - * 0 - */ -static long (*bpf_override_return)(struct pt_regs *regs, __u64 rc) = (void *) 58; - -/* - * bpf_sock_ops_cb_flags_set - * - * 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. - * - * *argval* is a flag array which can combine these flags: - * - * * **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) - * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) - * - * Therefore, this function can be used to clear a callback flag by - * setting the appropriate bit to zero. e.g. to disable the RTO - * callback: - * - * **bpf_sock_ops_cb_flags_set(bpf_sock,** - * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)** - * - * 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. - * - * Returns - * 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). - */ -static long (*bpf_sock_ops_cb_flags_set)(struct bpf_sock_ops *bpf_sock, int argval) = (void *) 59; - -/* - * bpf_msg_redirect_map - * - * 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. - * - * Returns - * **SK_PASS** on success, or **SK_DROP** on error. - */ -static long (*bpf_msg_redirect_map)(struct sk_msg_md *msg, void *map, __u32 key, __u64 flags) = (void *) 60; - -/* - * bpf_msg_apply_bytes - * - * 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. - * - * Returns - * 0 - */ -static long (*bpf_msg_apply_bytes)(struct sk_msg_md *msg, __u32 bytes) = (void *) 61; - -/* - * bpf_msg_cork_bytes - * - * 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. - * - * Returns - * 0 - */ -static long (*bpf_msg_cork_bytes)(struct sk_msg_md *msg, __u32 bytes) = (void *) 62; - -/* - * bpf_msg_pull_data - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_msg_pull_data)(struct sk_msg_md *msg, __u32 start, __u32 end, __u64 flags) = (void *) 63; - -/* - * bpf_bind - * - * 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**). It's advised to pass zero port (**sin_port** - * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like - * behavior and lets the kernel efficiently pick up an unused - * port as long as 4-tuple is unique. Passing non-zero port might - * lead to degraded performance. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_bind)(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) = (void *) 64; - -/* - * bpf_xdp_adjust_tail - * - * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is - * possible to both shrink and grow the packet tail. - * Shrink done via *delta* being a negative integer. - * - * A call to this helper is susceptible to change the underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_xdp_adjust_tail)(struct xdp_md *xdp_md, int delta) = (void *) 65; - -/* - * bpf_skb_get_xfrm_state - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_get_xfrm_state)(struct __sk_buff *skb, __u32 index, struct bpf_xfrm_state *xfrm_state, __u32 size, __u64 flags) = (void *) 66; - -/* - * bpf_get_stack - * - * 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= - * - * Returns - * The non-negative copied *buf* length equal to or less than - * *size* on success, or a negative error in case of failure. - */ -static long (*bpf_get_stack)(void *ctx, void *buf, __u32 size, __u64 flags) = (void *) 67; - -/* - * bpf_skb_load_bytes_relative - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_load_bytes_relative)(const void *skb, __u32 offset, void *to, __u32 len, __u32 start_header) = (void *) 68; - -/* - * bpf_fib_lookup - * - * 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. - * - * Returns - * * < 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 - * - * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU - * was exceeded and output params->mtu_result contains the MTU. - */ -static long (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params, int plen, __u32 flags) = (void *) 69; - -/* - * bpf_sock_hash_update - * - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_sock_hash_update)(struct bpf_sock_ops *skops, void *map, void *key, __u64 flags) = (void *) 70; - -/* - * bpf_msg_redirect_hash - * - * 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. - * - * Returns - * **SK_PASS** on success, or **SK_DROP** on error. - */ -static long (*bpf_msg_redirect_hash)(struct sk_msg_md *msg, void *map, void *key, __u64 flags) = (void *) 71; - -/* - * bpf_sk_redirect_hash - * - * 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 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 otherwise). This is the only flag supported for now. - * - * Returns - * **SK_PASS** on success, or **SK_DROP** on error. - */ -static long (*bpf_sk_redirect_hash)(struct __sk_buff *skb, void *map, void *key, __u64 flags) = (void *) 72; - -/* - * bpf_lwt_push_encap - * - * 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. - * **BPF_LWT_ENCAP_IP** - * IP encapsulation (GRE/GUE/IPIP/etc). The outer header - * must be IPv4 or IPv6, followed by zero or more - * additional headers, up to **LWT_BPF_MAX_HEADROOM** - * total bytes in all prepended headers. Please note that - * if **skb_is_gso**\ (*skb*) is true, no more than two - * headers can be prepended, and the inner header, if - * present, should be either GRE or UDP/GUE. - * - * **BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs - * of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can - * be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and - * **BPF_PROG_TYPE_LWT_XMIT**. - * - * A call to this helper is susceptible to change the underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_lwt_push_encap)(struct __sk_buff *skb, __u32 type, void *hdr, __u32 len) = (void *) 73; - -/* - * bpf_lwt_seg6_store_bytes - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_lwt_seg6_store_bytes)(struct __sk_buff *skb, __u32 offset, const void *from, __u32 len) = (void *) 74; - -/* - * bpf_lwt_seg6_adjust_srh - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_lwt_seg6_adjust_srh)(struct __sk_buff *skb, __u32 offset, __s32 delta) = (void *) 75; - -/* - * bpf_lwt_seg6_action - * - * 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 underlying - * 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. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_lwt_seg6_action)(struct __sk_buff *skb, __u32 action, void *param, __u32 param_len) = (void *) 76; - -/* - * bpf_rc_repeat - * - * 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**". - * - * Returns - * 0 - */ -static long (*bpf_rc_repeat)(void *ctx) = (void *) 77; - -/* - * bpf_rc_keydown - * - * 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**". - * - * Returns - * 0 - */ -static long (*bpf_rc_keydown)(void *ctx, __u32 protocol, __u64 scancode, __u32 toggle) = (void *) 78; - -/* - * bpf_skb_cgroup_id - * - * 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. - * - * Returns - * The id is returned or 0 in case the id could not be retrieved. - */ -static __u64 (*bpf_skb_cgroup_id)(struct __sk_buff *skb) = (void *) 79; - -/* - * bpf_get_current_cgroup_id - * - * Get the current cgroup id based on the cgroup within which - * the current task is running. - * - * Returns - * A 64-bit integer containing the current cgroup id based - * on the cgroup within which the current task is running. - */ -static __u64 (*bpf_get_current_cgroup_id)(void) = (void *) 80; - -/* - * bpf_get_local_storage - * - * 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_ATOMIC** instructions to alter - * the shared data. - * - * Returns - * A pointer to the local storage area. - */ -static void *(*bpf_get_local_storage)(void *map, __u64 flags) = (void *) 81; - -/* - * bpf_sk_select_reuseport - * - * Select a **SO_REUSEPORT** socket from a - * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*. - * It checks the selected socket is matching the incoming - * request in the socket buffer. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_sk_select_reuseport)(struct sk_reuseport_md *reuse, void *map, void *key, __u64 flags) = (void *) 82; - -/* - * bpf_skb_ancestor_cgroup_id - * - * 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**\ (). - * - * Returns - * The id is returned or 0 in case the id could not be retrieved. - */ -static __u64 (*bpf_skb_ancestor_cgroup_id)(struct __sk_buff *skb, int ancestor_level) = (void *) 83; - -/* - * bpf_sk_lookup_tcp - * - * 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 a negative signed 32-bit integer, then the - * socket lookup table in the netns associated with the *ctx* - * will be used. For the TC hooks, this is the netns of the device - * in the skb. For socket hooks, this is the netns of the socket. - * If *netns* is any other signed 32-bit value greater than or - * equal to zero then it specifies the ID of the netns relative to - * the netns associated with the *ctx*. *netns* values beyond the - * range of 32-bit integers are reserved for future use. - * - * 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. - * - * Returns - * Pointer to **struct bpf_sock**, or **NULL** in case of failure. - * For sockets with reuseport option, the **struct bpf_sock** - * result is from *reuse*\ **->socks**\ [] using the hash of the - * tuple. - */ -static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx, struct bpf_sock_tuple *tuple, __u32 tuple_size, __u64 netns, __u64 flags) = (void *) 84; - -/* - * bpf_sk_lookup_udp - * - * 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 a negative signed 32-bit integer, then the - * socket lookup table in the netns associated with the *ctx* - * will be used. For the TC hooks, this is the netns of the device - * in the skb. For socket hooks, this is the netns of the socket. - * If *netns* is any other signed 32-bit value greater than or - * equal to zero then it specifies the ID of the netns relative to - * the netns associated with the *ctx*. *netns* values beyond the - * range of 32-bit integers are reserved for future use. - * - * 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. - * - * Returns - * Pointer to **struct bpf_sock**, or **NULL** in case of failure. - * For sockets with reuseport option, the **struct bpf_sock** - * result is from *reuse*\ **->socks**\ [] using the hash of the - * tuple. - */ -static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx, struct bpf_sock_tuple *tuple, __u32 tuple_size, __u64 netns, __u64 flags) = (void *) 85; - -/* - * bpf_sk_release - * - * Release the reference held by *sock*. *sock* must be a - * non-**NULL** pointer that was returned from - * **bpf_sk_lookup_xxx**\ (). - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_sk_release)(void *sock) = (void *) 86; - -/* - * bpf_map_push_elem - * - * Push an element *value* in *map*. *flags* is one of: - * - * **BPF_EXIST** - * If the queue/stack is full, the oldest element is - * removed to make room for this. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_map_push_elem)(void *map, const void *value, __u64 flags) = (void *) 87; - -/* - * bpf_map_pop_elem - * - * Pop an element from *map*. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_map_pop_elem)(void *map, void *value) = (void *) 88; - -/* - * bpf_map_peek_elem - * - * Get an element from *map* without removing it. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_map_peek_elem)(void *map, void *value) = (void *) 89; - -/* - * bpf_msg_push_data - * - * For socket policies, insert *len* bytes into *msg* at offset - * *start*. - * - * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a - * *msg* it may want to insert metadata or options into the *msg*. - * This can later be read and used by any of the lower layer BPF - * hooks. - * - * This helper may fail if under memory pressure (a malloc - * fails) in these cases BPF programs will get an appropriate - * error and BPF programs will need to handle them. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_msg_push_data)(struct sk_msg_md *msg, __u32 start, __u32 len, __u64 flags) = (void *) 90; - -/* - * bpf_msg_pop_data - * - * Will remove *len* bytes from a *msg* starting at byte *start*. - * This may result in **ENOMEM** errors under certain situations if - * an allocation and copy are required due to a full ring buffer. - * However, the helper will try to avoid doing the allocation - * if possible. Other errors can occur if input parameters are - * invalid either due to *start* byte not being valid part of *msg* - * payload and/or *pop* value being to large. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_msg_pop_data)(struct sk_msg_md *msg, __u32 start, __u32 len, __u64 flags) = (void *) 91; - -/* - * bpf_rc_pointer_rel - * - * This helper is used in programs implementing IR decoding, to - * report a successfully decoded pointer movement. - * - * 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**". - * - * Returns - * 0 - */ -static long (*bpf_rc_pointer_rel)(void *ctx, __s32 rel_x, __s32 rel_y) = (void *) 92; - -/* - * bpf_spin_lock - * - * Acquire a spinlock represented by the pointer *lock*, which is - * stored as part of a value of a map. Taking the lock allows to - * safely update the rest of the fields in that value. The - * spinlock can (and must) later be released with a call to - * **bpf_spin_unlock**\ (\ *lock*\ ). - * - * Spinlocks in BPF programs come with a number of restrictions - * and constraints: - * - * * **bpf_spin_lock** objects are only allowed inside maps of - * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this - * list could be extended in the future). - * * BTF description of the map is mandatory. - * * The BPF program can take ONE lock at a time, since taking two - * or more could cause dead locks. - * * Only one **struct bpf_spin_lock** is allowed per map element. - * * When the lock is taken, calls (either BPF to BPF or helpers) - * are not allowed. - * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not - * allowed inside a spinlock-ed region. - * * The BPF program MUST call **bpf_spin_unlock**\ () to release - * the lock, on all execution paths, before it returns. - * * The BPF program can access **struct bpf_spin_lock** only via - * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () - * helpers. Loading or storing data into the **struct - * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. - * * To use the **bpf_spin_lock**\ () helper, the BTF description - * of the map value must be a struct and have **struct - * bpf_spin_lock** *anyname*\ **;** field at the top level. - * Nested lock inside another struct is not allowed. - * * The **struct bpf_spin_lock** *lock* field in a map value must - * be aligned on a multiple of 4 bytes in that value. - * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy - * the **bpf_spin_lock** field to user space. - * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from - * a BPF program, do not update the **bpf_spin_lock** field. - * * **bpf_spin_lock** cannot be on the stack or inside a - * networking packet (it can only be inside of a map values). - * * **bpf_spin_lock** is available to root only. - * * Tracing programs and socket filter programs cannot use - * **bpf_spin_lock**\ () due to insufficient preemption checks - * (but this may change in the future). - * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. - * - * Returns - * 0 - */ -static long (*bpf_spin_lock)(struct bpf_spin_lock *lock) = (void *) 93; - -/* - * bpf_spin_unlock - * - * Release the *lock* previously locked by a call to - * **bpf_spin_lock**\ (\ *lock*\ ). - * - * Returns - * 0 - */ -static long (*bpf_spin_unlock)(struct bpf_spin_lock *lock) = (void *) 94; - -/* - * bpf_sk_fullsock - * - * This helper gets a **struct bpf_sock** pointer such - * that all the fields in this **bpf_sock** can be accessed. - * - * Returns - * A **struct bpf_sock** pointer on success, or **NULL** in - * case of failure. - */ -static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) = (void *) 95; - -/* - * bpf_tcp_sock - * - * This helper gets a **struct bpf_tcp_sock** pointer from a - * **struct bpf_sock** pointer. - * - * Returns - * A **struct bpf_tcp_sock** pointer on success, or **NULL** in - * case of failure. - */ -static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) = (void *) 96; - -/* - * bpf_skb_ecn_set_ce - * - * Set ECN (Explicit Congestion Notification) field of IP header - * to **CE** (Congestion Encountered) if current value is **ECT** - * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 - * and IPv4. - * - * Returns - * 1 if the **CE** flag is set (either by the current helper call - * or because it was already present), 0 if it is not set. - */ -static long (*bpf_skb_ecn_set_ce)(struct __sk_buff *skb) = (void *) 97; - -/* - * bpf_get_listener_sock - * - * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. - * **bpf_sk_release**\ () is unnecessary and not allowed. - * - * Returns - * A **struct bpf_sock** pointer on success, or **NULL** in - * case of failure. - */ -static struct bpf_sock *(*bpf_get_listener_sock)(struct bpf_sock *sk) = (void *) 98; - -/* - * bpf_skc_lookup_tcp - * - * 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**\ (). - * - * This function is identical to **bpf_sk_lookup_tcp**\ (), except - * that it also returns timewait or request sockets. Use - * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the - * full structure. - * - * This helper is available only if the kernel was compiled with - * **CONFIG_NET** configuration option. - * - * Returns - * Pointer to **struct bpf_sock**, or **NULL** in case of failure. - * For sockets with reuseport option, the **struct bpf_sock** - * result is from *reuse*\ **->socks**\ [] using the hash of the - * tuple. - */ -static struct bpf_sock *(*bpf_skc_lookup_tcp)(void *ctx, struct bpf_sock_tuple *tuple, __u32 tuple_size, __u64 netns, __u64 flags) = (void *) 99; - -/* - * bpf_tcp_check_syncookie - * - * Check whether *iph* and *th* contain a valid SYN cookie ACK for - * the listening socket in *sk*. - * - * *iph* points to the start of the IPv4 or IPv6 header, while - * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). - * - * *th* points to the start of the TCP header, while *th_len* - * contains **sizeof**\ (**struct tcphdr**). - * - * Returns - * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative - * error otherwise. - */ -static long (*bpf_tcp_check_syncookie)(void *sk, void *iph, __u32 iph_len, struct tcphdr *th, __u32 th_len) = (void *) 100; - -/* - * bpf_sysctl_get_name - * - * Get name of sysctl in /proc/sys/ and copy it into provided by - * program buffer *buf* of size *buf_len*. - * - * The buffer is always NUL terminated, unless it's zero-sized. - * - * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is - * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name - * only (e.g. "tcp_mem"). - * - * Returns - * Number of character copied (not including the trailing NUL). - * - * **-E2BIG** if the buffer wasn't big enough (*buf* will contain - * truncated name in this case). - */ -static long (*bpf_sysctl_get_name)(struct bpf_sysctl *ctx, char *buf, unsigned long buf_len, __u64 flags) = (void *) 101; - -/* - * bpf_sysctl_get_current_value - * - * Get current value of sysctl as it is presented in /proc/sys - * (incl. newline, etc), and copy it as a string into provided - * by program buffer *buf* of size *buf_len*. - * - * The whole value is copied, no matter what file position user - * space issued e.g. sys_read at. - * - * The buffer is always NUL terminated, unless it's zero-sized. - * - * Returns - * Number of character copied (not including the trailing NUL). - * - * **-E2BIG** if the buffer wasn't big enough (*buf* will contain - * truncated name in this case). - * - * **-EINVAL** if current value was unavailable, e.g. because - * sysctl is uninitialized and read returns -EIO for it. - */ -static long (*bpf_sysctl_get_current_value)(struct bpf_sysctl *ctx, char *buf, unsigned long buf_len) = (void *) 102; - -/* - * bpf_sysctl_get_new_value - * - * Get new value being written by user space to sysctl (before - * the actual write happens) and copy it as a string into - * provided by program buffer *buf* of size *buf_len*. - * - * User space may write new value at file position > 0. - * - * The buffer is always NUL terminated, unless it's zero-sized. - * - * Returns - * Number of character copied (not including the trailing NUL). - * - * **-E2BIG** if the buffer wasn't big enough (*buf* will contain - * truncated name in this case). - * - * **-EINVAL** if sysctl is being read. - */ -static long (*bpf_sysctl_get_new_value)(struct bpf_sysctl *ctx, char *buf, unsigned long buf_len) = (void *) 103; - -/* - * bpf_sysctl_set_new_value - * - * Override new value being written by user space to sysctl with - * value provided by program in buffer *buf* of size *buf_len*. - * - * *buf* should contain a string in same form as provided by user - * space on sysctl write. - * - * User space may write new value at file position > 0. To override - * the whole sysctl value file position should be set to zero. - * - * Returns - * 0 on success. - * - * **-E2BIG** if the *buf_len* is too big. - * - * **-EINVAL** if sysctl is being read. - */ -static long (*bpf_sysctl_set_new_value)(struct bpf_sysctl *ctx, const char *buf, unsigned long buf_len) = (void *) 104; - -/* - * bpf_strtol - * - * Convert the initial part of the string from buffer *buf* of - * size *buf_len* to a long integer according to the given base - * and save the result in *res*. - * - * The string may begin with an arbitrary amount of white space - * (as determined by **isspace**\ (3)) followed by a single - * optional '**-**' sign. - * - * Five least significant bits of *flags* encode base, other bits - * are currently unused. - * - * Base must be either 8, 10, 16 or 0 to detect it automatically - * similar to user space **strtol**\ (3). - * - * Returns - * Number of characters consumed on success. Must be positive but - * no more than *buf_len*. - * - * **-EINVAL** if no valid digits were found or unsupported base - * was provided. - * - * **-ERANGE** if resulting value was out of range. - */ -static long (*bpf_strtol)(const char *buf, unsigned long buf_len, __u64 flags, long *res) = (void *) 105; - -/* - * bpf_strtoul - * - * Convert the initial part of the string from buffer *buf* of - * size *buf_len* to an unsigned long integer according to the - * given base and save the result in *res*. - * - * The string may begin with an arbitrary amount of white space - * (as determined by **isspace**\ (3)). - * - * Five least significant bits of *flags* encode base, other bits - * are currently unused. - * - * Base must be either 8, 10, 16 or 0 to detect it automatically - * similar to user space **strtoul**\ (3). - * - * Returns - * Number of characters consumed on success. Must be positive but - * no more than *buf_len*. - * - * **-EINVAL** if no valid digits were found or unsupported base - * was provided. - * - * **-ERANGE** if resulting value was out of range. - */ -static long (*bpf_strtoul)(const char *buf, unsigned long buf_len, __u64 flags, unsigned long *res) = (void *) 106; - -/* - * bpf_sk_storage_get - * - * Get a bpf-local-storage from a *sk*. - * - * Logically, it could be thought of getting the value from - * a *map* with *sk* as the **key**. From this - * perspective, the usage is not much different from - * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this - * helper enforces the key must be a full socket and the map must - * be a **BPF_MAP_TYPE_SK_STORAGE** also. - * - * Underneath, the value is stored locally at *sk* instead of - * the *map*. The *map* is used as the bpf-local-storage - * "type". The bpf-local-storage "type" (i.e. the *map*) is - * searched against all bpf-local-storages residing at *sk*. - * - * *sk* is a kernel **struct sock** pointer for LSM program. - * *sk* is a **struct bpf_sock** pointer for other program types. - * - * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be - * used such that a new bpf-local-storage will be - * created if one does not exist. *value* can be used - * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify - * the initial value of a bpf-local-storage. If *value* is - * **NULL**, the new bpf-local-storage will be zero initialized. - * - * Returns - * A bpf-local-storage pointer is returned on success. - * - * **NULL** if not found or there was an error in adding - * a new bpf-local-storage. - */ -static void *(*bpf_sk_storage_get)(void *map, void *sk, void *value, __u64 flags) = (void *) 107; - -/* - * bpf_sk_storage_delete - * - * Delete a bpf-local-storage from a *sk*. - * - * Returns - * 0 on success. - * - * **-ENOENT** if the bpf-local-storage cannot be found. - * **-EINVAL** if sk is not a fullsock (e.g. a request_sock). - */ -static long (*bpf_sk_storage_delete)(void *map, void *sk) = (void *) 108; - -/* - * bpf_send_signal - * - * Send signal *sig* to the process of the current task. - * The signal may be delivered to any of this process's threads. - * - * Returns - * 0 on success or successfully queued. - * - * **-EBUSY** if work queue under nmi is full. - * - * **-EINVAL** if *sig* is invalid. - * - * **-EPERM** if no permission to send the *sig*. - * - * **-EAGAIN** if bpf program can try again. - */ -static long (*bpf_send_signal)(__u32 sig) = (void *) 109; - -/* - * bpf_tcp_gen_syncookie - * - * Try to issue a SYN cookie for the packet with corresponding - * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. - * - * *iph* points to the start of the IPv4 or IPv6 header, while - * *iph_len* contains **sizeof**\ (**struct iphdr**) or - * **sizeof**\ (**struct ip6hdr**). - * - * *th* points to the start of the TCP header, while *th_len* - * contains the length of the TCP header. - * - * Returns - * On success, lower 32 bits hold the generated SYN cookie in - * followed by 16 bits which hold the MSS value for that cookie, - * and the top 16 bits are unused. - * - * On failure, the returned value is one of the following: - * - * **-EINVAL** SYN cookie cannot be issued due to error - * - * **-ENOENT** SYN cookie should not be issued (no SYN flood) - * - * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies - * - * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 - */ -static __s64 (*bpf_tcp_gen_syncookie)(void *sk, void *iph, __u32 iph_len, struct tcphdr *th, __u32 th_len) = (void *) 110; - -/* - * bpf_skb_output - * - * Write raw *data* blob into a special BPF perf event held by - * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf - * event must have the following attributes: **PERF_SAMPLE_RAW** - * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and - * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. - * - * The *flags* are used to indicate the index in *map* for which - * the value must be put, masked with **BPF_F_INDEX_MASK**. - * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** - * to indicate that the index of the current CPU core should be - * used. - * - * The value to write, of *size*, is passed through eBPF stack and - * pointed by *data*. - * - * *ctx* is a pointer to in-kernel struct sk_buff. - * - * This helper is similar to **bpf_perf_event_output**\ () but - * restricted to raw_tracepoint bpf programs. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_skb_output)(void *ctx, void *map, __u64 flags, void *data, __u64 size) = (void *) 111; - -/* - * bpf_probe_read_user - * - * Safely attempt to read *size* bytes from user space address - * *unsafe_ptr* and store the data in *dst*. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_probe_read_user)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 112; - -/* - * bpf_probe_read_kernel - * - * Safely attempt to read *size* bytes from kernel space address - * *unsafe_ptr* and store the data in *dst*. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_probe_read_kernel)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 113; - -/* - * bpf_probe_read_user_str - * - * Copy a NUL terminated string from an unsafe user address - * *unsafe_ptr* to *dst*. The *size* should include the - * terminating NUL byte. In case the string length is smaller than - * *size*, the target is not padded with further NUL bytes. If the - * string length is larger than *size*, just *size*-1 bytes are - * copied and the last byte is set to NUL. - * - * On success, returns the number of bytes that were written, - * including the terminal NUL. This makes this helper useful in - * tracing programs for reading strings, and more importantly to - * get its length at runtime. See the following snippet: - * - * :: - * - * SEC("kprobe/sys_open") - * void bpf_sys_open(struct pt_regs *ctx) - * { - * char buf[PATHLEN]; // PATHLEN is defined to 256 - * int res = bpf_probe_read_user_str(buf, sizeof(buf), - * ctx->di); - * - * // Consume buf, for example push it to - * // userspace via bpf_perf_event_output(); we - * // can use res (the string length) as event - * // size, after checking its boundaries. - * } - * - * In comparison, using **bpf_probe_read_user**\ () helper here - * instead to read the string would require to estimate the length - * at compile time, and would often result in copying more memory - * than necessary. - * - * Another useful use case is when parsing individual process - * arguments or individual environment variables navigating - * *current*\ **->mm->arg_start** and *current*\ - * **->mm->env_start**: using this helper and the return value, - * one can quickly iterate at the right offset of the memory area. - * - * Returns - * On success, the strictly positive length of the output string, - * including the trailing NUL character. On error, a negative - * value. - */ -static long (*bpf_probe_read_user_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 114; - -/* - * bpf_probe_read_kernel_str - * - * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* - * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply. - * - * Returns - * On success, the strictly positive length of the string, including - * the trailing NUL character. On error, a negative value. - */ -static long (*bpf_probe_read_kernel_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 115; - -/* - * bpf_tcp_send_ack - * - * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**. - * *rcv_nxt* is the ack_seq to be sent out. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_tcp_send_ack)(void *tp, __u32 rcv_nxt) = (void *) 116; - -/* - * bpf_send_signal_thread - * - * Send signal *sig* to the thread corresponding to the current task. - * - * Returns - * 0 on success or successfully queued. - * - * **-EBUSY** if work queue under nmi is full. - * - * **-EINVAL** if *sig* is invalid. - * - * **-EPERM** if no permission to send the *sig*. - * - * **-EAGAIN** if bpf program can try again. - */ -static long (*bpf_send_signal_thread)(__u32 sig) = (void *) 117; - -/* - * bpf_jiffies64 - * - * Obtain the 64bit jiffies - * - * Returns - * The 64 bit jiffies - */ -static __u64 (*bpf_jiffies64)(void) = (void *) 118; - -/* - * bpf_read_branch_records - * - * For an eBPF program attached to a perf event, retrieve the - * branch records (**struct perf_branch_entry**) associated to *ctx* - * and store it in the buffer pointed by *buf* up to size - * *size* bytes. - * - * Returns - * On success, number of bytes written to *buf*. On error, a - * negative value. - * - * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to - * instead return the number of bytes required to store all the - * branch entries. If this flag is set, *buf* may be NULL. - * - * **-EINVAL** if arguments invalid or **size** not a multiple - * of **sizeof**\ (**struct perf_branch_entry**\ ). - * - * **-ENOENT** if architecture does not support branch records. - */ -static long (*bpf_read_branch_records)(struct bpf_perf_event_data *ctx, void *buf, __u32 size, __u64 flags) = (void *) 119; - -/* - * bpf_get_ns_current_pid_tgid - * - * Returns 0 on success, values for *pid* and *tgid* as seen from the current - * *namespace* will be returned in *nsdata*. - * - * Returns - * 0 on success, or one of the following in case of failure: - * - * **-EINVAL** if dev and inum supplied don't match dev_t and inode number - * with nsfs of current task, or if dev conversion to dev_t lost high bits. - * - * **-ENOENT** if pidns does not exists for the current task. - */ -static long (*bpf_get_ns_current_pid_tgid)(__u64 dev, __u64 ino, struct bpf_pidns_info *nsdata, __u32 size) = (void *) 120; - -/* - * bpf_xdp_output - * - * Write raw *data* blob into a special BPF perf event held by - * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf - * event must have the following attributes: **PERF_SAMPLE_RAW** - * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and - * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. - * - * The *flags* are used to indicate the index in *map* for which - * the value must be put, masked with **BPF_F_INDEX_MASK**. - * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** - * to indicate that the index of the current CPU core should be - * used. - * - * The value to write, of *size*, is passed through eBPF stack and - * pointed by *data*. - * - * *ctx* is a pointer to in-kernel struct xdp_buff. - * - * This helper is similar to **bpf_perf_eventoutput**\ () but - * restricted to raw_tracepoint bpf programs. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_xdp_output)(void *ctx, void *map, __u64 flags, void *data, __u64 size) = (void *) 121; - -/* - * bpf_get_netns_cookie - * - * Retrieve the cookie (generated by the kernel) of the network - * namespace the input *ctx* is associated with. The network - * namespace cookie remains stable for its lifetime and provides - * a global identifier that can be assumed unique. If *ctx* is - * NULL, then the helper returns the cookie for the initial - * network namespace. The cookie itself is very similar to that - * of **bpf_get_socket_cookie**\ () helper, but for network - * namespaces instead of sockets. - * - * Returns - * A 8-byte long opaque number. - */ -static __u64 (*bpf_get_netns_cookie)(void *ctx) = (void *) 122; - -/* - * bpf_get_current_ancestor_cgroup_id - * - * Return id of cgroup v2 that is ancestor of the cgroup associated - * with the current task at the *ancestor_level*. The root cgroup - * is at *ancestor_level* zero and each step down the hierarchy - * increments the level. If *ancestor_level* == level of cgroup - * associated with the current task, then return value will be the - * same as that of **bpf_get_current_cgroup_id**\ (). - * - * The helper is useful to implement policies based on cgroups - * that are upper in hierarchy than immediate cgroup associated - * with the current task. - * - * The format of returned id and helper limitations are same as in - * **bpf_get_current_cgroup_id**\ (). - * - * Returns - * The id is returned or 0 in case the id could not be retrieved. - */ -static __u64 (*bpf_get_current_ancestor_cgroup_id)(int ancestor_level) = (void *) 123; - -/* - * bpf_sk_assign - * - * Helper is overloaded depending on BPF program type. This - * description applies to **BPF_PROG_TYPE_SCHED_CLS** and - * **BPF_PROG_TYPE_SCHED_ACT** programs. - * - * Assign the *sk* to the *skb*. When combined with appropriate - * routing configuration to receive the packet towards the socket, - * will cause *skb* to be delivered to the specified socket. - * Subsequent redirection of *skb* via **bpf_redirect**\ (), - * **bpf_clone_redirect**\ () or other methods outside of BPF may - * interfere with successful delivery to the socket. - * - * This operation is only valid from TC ingress path. - * - * The *flags* argument must be zero. - * - * Returns - * 0 on success, or a negative error in case of failure: - * - * **-EINVAL** if specified *flags* are not supported. - * - * **-ENOENT** if the socket is unavailable for assignment. - * - * **-ENETUNREACH** if the socket is unreachable (wrong netns). - * - * **-EOPNOTSUPP** if the operation is not supported, for example - * a call from outside of TC ingress. - * - * **-ESOCKTNOSUPPORT** if the socket type is not supported - * (reuseport). - */ -static long (*bpf_sk_assign)(void *ctx, void *sk, __u64 flags) = (void *) 124; - -/* - * bpf_ktime_get_boot_ns - * - * Return the time elapsed since system boot, in nanoseconds. - * Does include the time the system was suspended. - * See: **clock_gettime**\ (**CLOCK_BOOTTIME**) - * - * Returns - * Current *ktime*. - */ -static __u64 (*bpf_ktime_get_boot_ns)(void) = (void *) 125; - -/* - * bpf_seq_printf - * - * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print - * out the format string. - * The *m* represents the seq_file. The *fmt* and *fmt_size* are for - * the format string itself. The *data* and *data_len* are format string - * arguments. The *data* are a **u64** array and corresponding format string - * values are stored in the array. For strings and pointers where pointees - * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes - must be a multiple of 8. - * - * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. - * Reading kernel memory may fail due to either invalid address or - * valid address but requiring a major memory fault. If reading kernel memory - * fails, the string for **%s** will be an empty string, and the ip - * address for **%p{i,I}{4,6}** will be 0. Not returning error to - * bpf program is consistent with what **bpf_trace_printk**\ () does for now. - * - * Returns - * 0 on success, or a negative error in case of failure: - * - * **-EBUSY** if per-CPU memory copy buffer is busy, can try again - * by returning 1 from bpf program. - * - * **-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported. - * - * **-E2BIG** if *fmt* contains too many format specifiers. - * - * **-EOVERFLOW** if an overflow happened: The same object will be tried again. - */ -static long (*bpf_seq_printf)(struct seq_file *m, const char *fmt, __u32 fmt_size, const void *data, __u32 data_len) = (void *) 126; - -/* - * bpf_seq_write - * - * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data. - * The *m* represents the seq_file. The *data* and *len* represent the - * data to write in bytes. - * - * Returns - * 0 on success, or a negative error in case of failure: - * - * **-EOVERFLOW** if an overflow happened: The same object will be tried again. - */ -static long (*bpf_seq_write)(struct seq_file *m, const void *data, __u32 len) = (void *) 127; - -/* - * bpf_sk_cgroup_id - * - * Return the cgroup v2 id of the socket *sk*. - * - * *sk* must be a non-**NULL** pointer to a socket, e.g. one - * returned from **bpf_sk_lookup_xxx**\ (), - * **bpf_sk_fullsock**\ (), etc. The format of returned id is - * same as in **bpf_skb_cgroup_id**\ (). - * - * This helper is available only if the kernel was compiled with - * the **CONFIG_SOCK_CGROUP_DATA** configuration option. - * - * Returns - * The id is returned or 0 in case the id could not be retrieved. - */ -static __u64 (*bpf_sk_cgroup_id)(void *sk) = (void *) 128; - -/* - * bpf_sk_ancestor_cgroup_id - * - * Return id of cgroup v2 that is ancestor of cgroup associated - * with the *sk* 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 *sk*, then return value will be same as that - * of **bpf_sk_cgroup_id**\ (). - * - * The helper is useful to implement policies based on cgroups - * that are upper in hierarchy than immediate cgroup associated - * with *sk*. - * - * The format of returned id and helper limitations are same as in - * **bpf_sk_cgroup_id**\ (). - * - * Returns - * The id is returned or 0 in case the id could not be retrieved. - */ -static __u64 (*bpf_sk_ancestor_cgroup_id)(void *sk, int ancestor_level) = (void *) 129; - -/* - * bpf_ringbuf_output - * - * Copy *size* bytes from *data* into a ring buffer *ringbuf*. - * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification - * of new data availability is sent. - * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification - * of new data availability is sent unconditionally. - * If **0** is specified in *flags*, an adaptive notification - * of new data availability is sent. - * - * An adaptive notification is a notification sent whenever the user-space - * process has caught up and consumed all available payloads. In case the user-space - * process is still processing a previous payload, then no notification is needed - * as it will process the newly added payload automatically. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_ringbuf_output)(void *ringbuf, void *data, __u64 size, __u64 flags) = (void *) 130; - -/* - * bpf_ringbuf_reserve - * - * Reserve *size* bytes of payload in a ring buffer *ringbuf*. - * *flags* must be 0. - * - * Returns - * Valid pointer with *size* bytes of memory available; NULL, - * otherwise. - */ -static void *(*bpf_ringbuf_reserve)(void *ringbuf, __u64 size, __u64 flags) = (void *) 131; - -/* - * bpf_ringbuf_submit - * - * Submit reserved ring buffer sample, pointed to by *data*. - * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification - * of new data availability is sent. - * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification - * of new data availability is sent unconditionally. - * If **0** is specified in *flags*, an adaptive notification - * of new data availability is sent. - * - * See 'bpf_ringbuf_output()' for the definition of adaptive notification. - * - * Returns - * Nothing. Always succeeds. - */ -static void (*bpf_ringbuf_submit)(void *data, __u64 flags) = (void *) 132; - -/* - * bpf_ringbuf_discard - * - * Discard reserved ring buffer sample, pointed to by *data*. - * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification - * of new data availability is sent. - * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification - * of new data availability is sent unconditionally. - * If **0** is specified in *flags*, an adaptive notification - * of new data availability is sent. - * - * See 'bpf_ringbuf_output()' for the definition of adaptive notification. - * - * Returns - * Nothing. Always succeeds. - */ -static void (*bpf_ringbuf_discard)(void *data, __u64 flags) = (void *) 133; - -/* - * bpf_ringbuf_query - * - * Query various characteristics of provided ring buffer. What - * exactly is queries is determined by *flags*: - * - * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed. - * * **BPF_RB_RING_SIZE**: The size of ring buffer. - * * **BPF_RB_CONS_POS**: Consumer position (can wrap around). - * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around). - * - * Data returned is just a momentary snapshot of actual values - * and could be inaccurate, so this facility should be used to - * power heuristics and for reporting, not to make 100% correct - * calculation. - * - * Returns - * Requested value, or 0, if *flags* are not recognized. - */ -static __u64 (*bpf_ringbuf_query)(void *ringbuf, __u64 flags) = (void *) 134; - -/* - * bpf_csum_level - * - * Change the skbs checksum level by one layer up or down, or - * reset it entirely to none in order to have the stack perform - * checksum validation. The level is applicable to the following - * protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of - * | ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP | - * through **bpf_skb_adjust_room**\ () helper with passing in - * **BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one call - * to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since - * the UDP header is removed. Similarly, an encap of the latter - * into the former could be accompanied by a helper call to - * **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the - * skb is still intended to be processed in higher layers of the - * stack instead of just egressing at tc. - * - * There are three supported level settings at this time: - * - * * **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs - * with CHECKSUM_UNNECESSARY. - * * **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs - * with CHECKSUM_UNNECESSARY. - * * **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and - * sets CHECKSUM_NONE to force checksum validation by the stack. - * * **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current - * skb->csum_level. - * - * Returns - * 0 on success, or a negative error in case of failure. In the - * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level - * is returned or the error code -EACCES in case the skb is not - * subject to CHECKSUM_UNNECESSARY. - */ -static long (*bpf_csum_level)(struct __sk_buff *skb, __u64 level) = (void *) 135; - -/* - * bpf_skc_to_tcp6_sock - * - * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer. - * - * Returns - * *sk* if casting is valid, or **NULL** otherwise. - */ -static struct tcp6_sock *(*bpf_skc_to_tcp6_sock)(void *sk) = (void *) 136; - -/* - * bpf_skc_to_tcp_sock - * - * Dynamically cast a *sk* pointer to a *tcp_sock* pointer. - * - * Returns - * *sk* if casting is valid, or **NULL** otherwise. - */ -static struct tcp_sock *(*bpf_skc_to_tcp_sock)(void *sk) = (void *) 137; - -/* - * bpf_skc_to_tcp_timewait_sock - * - * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer. - * - * Returns - * *sk* if casting is valid, or **NULL** otherwise. - */ -static struct tcp_timewait_sock *(*bpf_skc_to_tcp_timewait_sock)(void *sk) = (void *) 138; - -/* - * bpf_skc_to_tcp_request_sock - * - * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer. - * - * Returns - * *sk* if casting is valid, or **NULL** otherwise. - */ -static struct tcp_request_sock *(*bpf_skc_to_tcp_request_sock)(void *sk) = (void *) 139; - -/* - * bpf_skc_to_udp6_sock - * - * Dynamically cast a *sk* pointer to a *udp6_sock* pointer. - * - * Returns - * *sk* if casting is valid, or **NULL** otherwise. - */ -static struct udp6_sock *(*bpf_skc_to_udp6_sock)(void *sk) = (void *) 140; - -/* - * bpf_get_task_stack - * - * Return a user or a kernel stack in bpf program provided buffer. - * To achieve this, the helper needs *task*, which is a valid - * pointer to **struct task_struct**. 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_task_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= - * - * Returns - * The non-negative copied *buf* length equal to or less than - * *size* on success, or a negative error in case of failure. - */ -static long (*bpf_get_task_stack)(struct task_struct *task, void *buf, __u32 size, __u64 flags) = (void *) 141; - -/* - * bpf_load_hdr_opt - * - * Load header option. Support reading a particular TCP header - * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**). - * - * If *flags* is 0, it will search the option from the - * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops** - * has details on what skb_data contains under different - * *skops*\ **->op**. - * - * The first byte of the *searchby_res* specifies the - * kind that it wants to search. - * - * If the searching kind is an experimental kind - * (i.e. 253 or 254 according to RFC6994). It also - * needs to specify the "magic" which is either - * 2 bytes or 4 bytes. It then also needs to - * specify the size of the magic by using - * the 2nd byte which is "kind-length" of a TCP - * header option and the "kind-length" also - * includes the first 2 bytes "kind" and "kind-length" - * itself as a normal TCP header option also does. - * - * For example, to search experimental kind 254 with - * 2 byte magic 0xeB9F, the searchby_res should be - * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. - * - * To search for the standard window scale option (3), - * the *searchby_res* should be [ 3, 0, 0, .... 0 ]. - * Note, kind-length must be 0 for regular option. - * - * Searching for No-Op (0) and End-of-Option-List (1) are - * not supported. - * - * *len* must be at least 2 bytes which is the minimal size - * of a header option. - * - * Supported flags: - * - * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the - * saved_syn packet or the just-received syn packet. - * - * - * Returns - * > 0 when found, the header option is copied to *searchby_res*. - * The return value is the total length copied. On failure, a - * negative error code is returned: - * - * **-EINVAL** if a parameter is invalid. - * - * **-ENOMSG** if the option is not found. - * - * **-ENOENT** if no syn packet is available when - * **BPF_LOAD_HDR_OPT_TCP_SYN** is used. - * - * **-ENOSPC** if there is not enough space. Only *len* number of - * bytes are copied. - * - * **-EFAULT** on failure to parse the header options in the - * packet. - * - * **-EPERM** if the helper cannot be used under the current - * *skops*\ **->op**. - */ -static long (*bpf_load_hdr_opt)(struct bpf_sock_ops *skops, void *searchby_res, __u32 len, __u64 flags) = (void *) 142; - -/* - * bpf_store_hdr_opt - * - * Store header option. The data will be copied - * from buffer *from* with length *len* to the TCP header. - * - * The buffer *from* should have the whole option that - * includes the kind, kind-length, and the actual - * option data. The *len* must be at least kind-length - * long. The kind-length does not have to be 4 byte - * aligned. The kernel will take care of the padding - * and setting the 4 bytes aligned value to th->doff. - * - * This helper will check for duplicated option - * by searching the same option in the outgoing skb. - * - * This helper can only be called during - * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. - * - * - * Returns - * 0 on success, or negative error in case of failure: - * - * **-EINVAL** If param is invalid. - * - * **-ENOSPC** if there is not enough space in the header. - * Nothing has been written - * - * **-EEXIST** if the option already exists. - * - * **-EFAULT** on failrue to parse the existing header options. - * - * **-EPERM** if the helper cannot be used under the current - * *skops*\ **->op**. - */ -static long (*bpf_store_hdr_opt)(struct bpf_sock_ops *skops, const void *from, __u32 len, __u64 flags) = (void *) 143; - -/* - * bpf_reserve_hdr_opt - * - * Reserve *len* bytes for the bpf header option. The - * space will be used by **bpf_store_hdr_opt**\ () later in - * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. - * - * If **bpf_reserve_hdr_opt**\ () is called multiple times, - * the total number of bytes will be reserved. - * - * This helper can only be called during - * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**. - * - * - * Returns - * 0 on success, or negative error in case of failure: - * - * **-EINVAL** if a parameter is invalid. - * - * **-ENOSPC** if there is not enough space in the header. - * - * **-EPERM** if the helper cannot be used under the current - * *skops*\ **->op**. - */ -static long (*bpf_reserve_hdr_opt)(struct bpf_sock_ops *skops, __u32 len, __u64 flags) = (void *) 144; - -/* - * bpf_inode_storage_get - * - * Get a bpf_local_storage from an *inode*. - * - * Logically, it could be thought of as getting the value from - * a *map* with *inode* as the **key**. From this - * perspective, the usage is not much different from - * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this - * helper enforces the key must be an inode and the map must also - * be a **BPF_MAP_TYPE_INODE_STORAGE**. - * - * Underneath, the value is stored locally at *inode* instead of - * the *map*. The *map* is used as the bpf-local-storage - * "type". The bpf-local-storage "type" (i.e. the *map*) is - * searched against all bpf_local_storage residing at *inode*. - * - * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be - * used such that a new bpf_local_storage will be - * created if one does not exist. *value* can be used - * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify - * the initial value of a bpf_local_storage. If *value* is - * **NULL**, the new bpf_local_storage will be zero initialized. - * - * Returns - * A bpf_local_storage pointer is returned on success. - * - * **NULL** if not found or there was an error in adding - * a new bpf_local_storage. - */ -static void *(*bpf_inode_storage_get)(void *map, void *inode, void *value, __u64 flags) = (void *) 145; - -/* - * bpf_inode_storage_delete - * - * Delete a bpf_local_storage from an *inode*. - * - * Returns - * 0 on success. - * - * **-ENOENT** if the bpf_local_storage cannot be found. - */ -static int (*bpf_inode_storage_delete)(void *map, void *inode) = (void *) 146; - -/* - * bpf_d_path - * - * Return full path for given **struct path** object, which - * needs to be the kernel BTF *path* object. The path is - * returned in the provided buffer *buf* of size *sz* and - * is zero terminated. - * - * - * Returns - * On success, the strictly positive length of the string, - * including the trailing NUL character. On error, a negative - * value. - */ -static long (*bpf_d_path)(struct path *path, char *buf, __u32 sz) = (void *) 147; - -/* - * bpf_copy_from_user - * - * Read *size* bytes from user space address *user_ptr* and store - * the data in *dst*. This is a wrapper of **copy_from_user**\ (). - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_copy_from_user)(void *dst, __u32 size, const void *user_ptr) = (void *) 148; - -/* - * bpf_snprintf_btf - * - * Use BTF to store a string representation of *ptr*->ptr in *str*, - * using *ptr*->type_id. This value should specify the type - * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1) - * can be used to look up vmlinux BTF type ids. Traversing the - * data structure using BTF, the type information and values are - * stored in the first *str_size* - 1 bytes of *str*. Safe copy of - * the pointer data is carried out to avoid kernel crashes during - * operation. Smaller types can use string space on the stack; - * larger programs can use map data to store the string - * representation. - * - * The string can be subsequently shared with userspace via - * bpf_perf_event_output() or ring buffer interfaces. - * bpf_trace_printk() is to be avoided as it places too small - * a limit on string size to be useful. - * - * *flags* is a combination of - * - * **BTF_F_COMPACT** - * no formatting around type information - * **BTF_F_NONAME** - * no struct/union member names/types - * **BTF_F_PTR_RAW** - * show raw (unobfuscated) pointer values; - * equivalent to printk specifier %px. - * **BTF_F_ZERO** - * show zero-valued struct/union members; they - * are not displayed by default - * - * - * Returns - * The number of bytes that were written (or would have been - * written if output had to be truncated due to string size), - * or a negative error in cases of failure. - */ -static long (*bpf_snprintf_btf)(char *str, __u32 str_size, struct btf_ptr *ptr, __u32 btf_ptr_size, __u64 flags) = (void *) 149; - -/* - * bpf_seq_printf_btf - * - * Use BTF to write to seq_write a string representation of - * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf(). - * *flags* are identical to those used for bpf_snprintf_btf. - * - * Returns - * 0 on success or a negative error in case of failure. - */ -static long (*bpf_seq_printf_btf)(struct seq_file *m, struct btf_ptr *ptr, __u32 ptr_size, __u64 flags) = (void *) 150; - -/* - * bpf_skb_cgroup_classid - * - * See **bpf_get_cgroup_classid**\ () for the main description. - * This helper differs from **bpf_get_cgroup_classid**\ () in that - * the cgroup v1 net_cls class is retrieved only from the *skb*'s - * associated socket instead of the current process. - * - * Returns - * The id is returned or 0 in case the id could not be retrieved. - */ -static __u64 (*bpf_skb_cgroup_classid)(struct __sk_buff *skb) = (void *) 151; - -/* - * bpf_redirect_neigh - * - * Redirect the packet to another net device of index *ifindex* - * and fill in L2 addresses from neighboring subsystem. This helper - * is somewhat similar to **bpf_redirect**\ (), except that it - * populates L2 addresses as well, meaning, internally, the helper - * relies on the neighbor lookup for the L2 address of the nexthop. - * - * The helper will perform a FIB lookup based on the skb's - * networking header to get the address of the next hop, unless - * this is supplied by the caller in the *params* argument. The - * *plen* argument indicates the len of *params* and should be set - * to 0 if *params* is NULL. - * - * The *flags* argument is reserved and must be 0. The helper is - * currently only supported for tc BPF program types, and enabled - * for IPv4 and IPv6 protocols. - * - * Returns - * The helper returns **TC_ACT_REDIRECT** on success or - * **TC_ACT_SHOT** on error. - */ -static long (*bpf_redirect_neigh)(__u32 ifindex, struct bpf_redir_neigh *params, int plen, __u64 flags) = (void *) 152; - -/* - * bpf_per_cpu_ptr - * - * Take a pointer to a percpu ksym, *percpu_ptr*, and return a - * pointer to the percpu kernel variable on *cpu*. A ksym is an - * extern variable decorated with '__ksym'. For ksym, there is a - * global var (either static or global) defined of the same name - * in the kernel. The ksym is percpu if the global var is percpu. - * The returned pointer points to the global percpu var on *cpu*. - * - * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the - * kernel, except that bpf_per_cpu_ptr() may return NULL. This - * happens if *cpu* is larger than nr_cpu_ids. The caller of - * bpf_per_cpu_ptr() must check the returned value. - * - * Returns - * A pointer pointing to the kernel percpu variable on *cpu*, or - * NULL, if *cpu* is invalid. - */ -static void *(*bpf_per_cpu_ptr)(const void *percpu_ptr, __u32 cpu) = (void *) 153; - -/* - * bpf_this_cpu_ptr - * - * Take a pointer to a percpu ksym, *percpu_ptr*, and return a - * pointer to the percpu kernel variable on this cpu. See the - * description of 'ksym' in **bpf_per_cpu_ptr**\ (). - * - * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in - * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would - * never return NULL. - * - * Returns - * A pointer pointing to the kernel percpu variable on this cpu. - */ -static void *(*bpf_this_cpu_ptr)(const void *percpu_ptr) = (void *) 154; - -/* - * bpf_redirect_peer - * - * Redirect the packet to another net device of index *ifindex*. - * This helper is somewhat similar to **bpf_redirect**\ (), except - * that the redirection happens to the *ifindex*' peer device and - * the netns switch takes place from ingress to ingress without - * going through the CPU's backlog queue. - * - * The *flags* argument is reserved and must be 0. The helper is - * currently only supported for tc BPF program types at the ingress - * hook and for veth device types. The peer device must reside in a - * different network namespace. - * - * Returns - * The helper returns **TC_ACT_REDIRECT** on success or - * **TC_ACT_SHOT** on error. - */ -static long (*bpf_redirect_peer)(__u32 ifindex, __u64 flags) = (void *) 155; - -/* - * bpf_task_storage_get - * - * Get a bpf_local_storage from the *task*. - * - * Logically, it could be thought of as getting the value from - * a *map* with *task* as the **key**. From this - * perspective, the usage is not much different from - * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this - * helper enforces the key must be an task_struct and the map must also - * be a **BPF_MAP_TYPE_TASK_STORAGE**. - * - * Underneath, the value is stored locally at *task* instead of - * the *map*. The *map* is used as the bpf-local-storage - * "type". The bpf-local-storage "type" (i.e. the *map*) is - * searched against all bpf_local_storage residing at *task*. - * - * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be - * used such that a new bpf_local_storage will be - * created if one does not exist. *value* can be used - * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify - * the initial value of a bpf_local_storage. If *value* is - * **NULL**, the new bpf_local_storage will be zero initialized. - * - * Returns - * A bpf_local_storage pointer is returned on success. - * - * **NULL** if not found or there was an error in adding - * a new bpf_local_storage. - */ -static void *(*bpf_task_storage_get)(void *map, struct task_struct *task, void *value, __u64 flags) = (void *) 156; - -/* - * bpf_task_storage_delete - * - * Delete a bpf_local_storage from a *task*. - * - * Returns - * 0 on success. - * - * **-ENOENT** if the bpf_local_storage cannot be found. - */ -static long (*bpf_task_storage_delete)(void *map, struct task_struct *task) = (void *) 157; - -/* - * bpf_get_current_task_btf - * - * Return a BTF pointer to the "current" task. - * This pointer can also be used in helpers that accept an - * *ARG_PTR_TO_BTF_ID* of type *task_struct*. - * - * Returns - * Pointer to the current task. - */ -static struct task_struct *(*bpf_get_current_task_btf)(void) = (void *) 158; - -/* - * bpf_bprm_opts_set - * - * Set or clear certain options on *bprm*: - * - * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit - * which sets the **AT_SECURE** auxv for glibc. The bit - * is cleared if the flag is not specified. - * - * Returns - * **-EINVAL** if invalid *flags* are passed, zero otherwise. - */ -static long (*bpf_bprm_opts_set)(struct linux_binprm *bprm, __u64 flags) = (void *) 159; - -/* - * bpf_ktime_get_coarse_ns - * - * Return a coarse-grained version of the time elapsed since - * system boot, in nanoseconds. Does not include time the system - * was suspended. - * - * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) - * - * Returns - * Current *ktime*. - */ -static __u64 (*bpf_ktime_get_coarse_ns)(void) = (void *) 160; - -/* - * bpf_ima_inode_hash - * - * Returns the stored IMA hash of the *inode* (if it's avaialable). - * If the hash is larger than *size*, then only *size* - * bytes will be copied to *dst* - * - * Returns - * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if - * invalid arguments are passed. - */ -static long (*bpf_ima_inode_hash)(struct inode *inode, void *dst, __u32 size) = (void *) 161; - -/* - * bpf_sock_from_file - * - * If the given file represents a socket, returns the associated - * socket. - * - * Returns - * A pointer to a struct socket on success or NULL if the file is - * not a socket. - */ -static struct socket *(*bpf_sock_from_file)(struct file *file) = (void *) 162; - -/* - * bpf_check_mtu - * - * Check packet size against exceeding MTU of net device (based - * on *ifindex*). This helper will likely be used in combination - * with helpers that adjust/change the packet size. - * - * The argument *len_diff* can be used for querying with a planned - * size change. This allows to check MTU prior to changing packet - * ctx. Providing an *len_diff* adjustment that is larger than the - * actual packet size (resulting in negative packet size) will in - * principle not exceed the MTU, why it is not considered a - * failure. Other BPF-helpers are needed for performing the - * planned size change, why the responsability for catch a negative - * packet size belong in those helpers. - * - * Specifying *ifindex* zero means the MTU check is performed - * against the current net device. This is practical if this isn't - * used prior to redirect. - * - * On input *mtu_len* must be a valid pointer, else verifier will - * reject BPF program. If the value *mtu_len* is initialized to - * zero then the ctx packet size is use. When value *mtu_len* is - * provided as input this specify the L3 length that the MTU check - * is done against. Remember XDP and TC length operate at L2, but - * this value is L3 as this correlate to MTU and IP-header tot_len - * values which are L3 (similar behavior as bpf_fib_lookup). - * - * The Linux kernel route table can configure MTUs on a more - * specific per route level, which is not provided by this helper. - * For route level MTU checks use the **bpf_fib_lookup**\ () - * helper. - * - * *ctx* is either **struct xdp_md** for XDP programs or - * **struct sk_buff** for tc cls_act programs. - * - * The *flags* argument can be a combination of one or more of the - * following values: - * - * **BPF_MTU_CHK_SEGS** - * This flag will only works for *ctx* **struct sk_buff**. - * If packet context contains extra packet segment buffers - * (often knows as GSO skb), then MTU check is harder to - * check at this point, because in transmit path it is - * possible for the skb packet to get re-segmented - * (depending on net device features). This could still be - * a MTU violation, so this flag enables performing MTU - * check against segments, with a different violation - * return code to tell it apart. Check cannot use len_diff. - * - * On return *mtu_len* pointer contains the MTU value of the net - * device. Remember the net device configured MTU is the L3 size, - * which is returned here and XDP and TC length operate at L2. - * Helper take this into account for you, but remember when using - * MTU value in your BPF-code. - * - * - * Returns - * * 0 on success, and populate MTU value in *mtu_len* pointer. - * - * * < 0 if any input argument is invalid (*mtu_len* not updated) - * - * MTU violations return positive values, but also populate MTU - * value in *mtu_len* pointer, as this can be needed for - * implementing PMTU handing: - * - * * **BPF_MTU_CHK_RET_FRAG_NEEDED** - * * **BPF_MTU_CHK_RET_SEGS_TOOBIG** - */ -static long (*bpf_check_mtu)(void *ctx, __u32 ifindex, __u32 *mtu_len, __s32 len_diff, __u64 flags) = (void *) 163; - -/* - * bpf_for_each_map_elem - * - * For each element in **map**, call **callback_fn** function with - * **map**, **callback_ctx** and other map-specific parameters. - * The **callback_fn** should be a static function and - * the **callback_ctx** should be a pointer to the stack. - * The **flags** is used to control certain aspects of the helper. - * Currently, the **flags** must be 0. - * - * The following are a list of supported map types and their - * respective expected callback signatures: - * - * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH, - * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH, - * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY - * - * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx); - * - * For per_cpu maps, the map_value is the value on the cpu where the - * bpf_prog is running. - * - * If **callback_fn** return 0, the helper will continue to the next - * element. If return value is 1, the helper will skip the rest of - * elements and return. Other return values are not used now. - * - * - * Returns - * The number of traversed map elements for success, **-EINVAL** for - * invalid **flags**. - */ -static long (*bpf_for_each_map_elem)(void *map, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 164; - -/* - * bpf_snprintf - * - * Outputs a string into the **str** buffer of size **str_size** - * based on a format string stored in a read-only map pointed by - * **fmt**. - * - * Each format specifier in **fmt** corresponds to one u64 element - * in the **data** array. For strings and pointers where pointees - * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes - must be - * a multiple of 8. - * - * Formats **%s** and **%p{i,I}{4,6}** require to read kernel - * memory. Reading kernel memory may fail due to either invalid - * address or valid address but requiring a major memory fault. If - * reading kernel memory fails, the string for **%s** will be an - * empty string, and the ip address for **%p{i,I}{4,6}** will be 0. - * Not returning error to bpf program is consistent with what - * **bpf_trace_printk**\ () does for now. - * - * - * Returns - * The strictly positive length of the formatted string, including - * the trailing zero character. If the return value is greater than - * **str_size**, **str** contains a truncated string, guaranteed to - * be zero-terminated except when **str_size** is 0. - * - * Or **-EBUSY** if the per-CPU memory copy buffer is busy. - */ -static long (*bpf_snprintf)(char *str, __u32 str_size, const char *fmt, __u64 *data, __u32 data_len) = (void *) 165; - -/* - * bpf_sys_bpf - * - * Execute bpf syscall with given arguments. - * - * Returns - * A syscall result. - */ -static long (*bpf_sys_bpf)(__u32 cmd, void *attr, __u32 attr_size) = (void *) 166; - -/* - * bpf_btf_find_by_name_kind - * - * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. - * - * Returns - * Returns btf_id and btf_obj_fd in lower and upper 32 bits. - */ -static long (*bpf_btf_find_by_name_kind)(char *name, int name_sz, __u32 kind, int flags) = (void *) 167; - -/* - * bpf_sys_close - * - * Execute close syscall for given FD. - * - * Returns - * A syscall result. - */ -static long (*bpf_sys_close)(__u32 fd) = (void *) 168; - -/* - * bpf_timer_init - * - * Initialize the timer. - * First 4 bits of *flags* specify clockid. - * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. - * All other bits of *flags* are reserved. - * The verifier will reject the program if *timer* is not from - * the same *map*. - * - * Returns - * 0 on success. - * **-EBUSY** if *timer* is already initialized. - * **-EINVAL** if invalid *flags* are passed. - * **-EPERM** if *timer* is in a map that doesn't have any user references. - * The user space should either hold a file descriptor to a map with timers - * or pin such map in bpffs. When map is unpinned or file descriptor is - * closed all timers in the map will be cancelled and freed. - */ -static long (*bpf_timer_init)(struct bpf_timer *timer, void *map, __u64 flags) = (void *) 169; - -/* - * bpf_timer_set_callback - * - * Configure the timer to call *callback_fn* static function. - * - * Returns - * 0 on success. - * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. - * **-EPERM** if *timer* is in a map that doesn't have any user references. - * The user space should either hold a file descriptor to a map with timers - * or pin such map in bpffs. When map is unpinned or file descriptor is - * closed all timers in the map will be cancelled and freed. - */ -static long (*bpf_timer_set_callback)(struct bpf_timer *timer, void *callback_fn) = (void *) 170; - -/* - * bpf_timer_start - * - * Set timer expiration N nanoseconds from the current time. The - * configured callback will be invoked in soft irq context on some cpu - * and will not repeat unless another bpf_timer_start() is made. - * In such case the next invocation can migrate to a different cpu. - * Since struct bpf_timer is a field inside map element the map - * owns the timer. The bpf_timer_set_callback() will increment refcnt - * of BPF program to make sure that callback_fn code stays valid. - * When user space reference to a map reaches zero all timers - * in a map are cancelled and corresponding program's refcnts are - * decremented. This is done to make sure that Ctrl-C of a user - * process doesn't leave any timers running. If map is pinned in - * bpffs the callback_fn can re-arm itself indefinitely. - * bpf_map_update/delete_elem() helpers and user space sys_bpf commands - * cancel and free the timer in the given map element. - * The map can contain timers that invoke callback_fn-s from different - * programs. The same callback_fn can serve different timers from - * different maps if key/value layout matches across maps. - * Every bpf_timer_set_callback() can have different callback_fn. - * - * - * Returns - * 0 on success. - * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier - * or invalid *flags* are passed. - */ -static long (*bpf_timer_start)(struct bpf_timer *timer, __u64 nsecs, __u64 flags) = (void *) 171; - -/* - * bpf_timer_cancel - * - * Cancel the timer and wait for callback_fn to finish if it was running. - * - * Returns - * 0 if the timer was not active. - * 1 if the timer was active. - * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. - * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its - * own timer which would have led to a deadlock otherwise. - */ -static long (*bpf_timer_cancel)(struct bpf_timer *timer) = (void *) 172; - -/* - * bpf_get_func_ip - * - * Get address of the traced function (for tracing and kprobe programs). - * - * Returns - * Address of the traced function. - */ -static __u64 (*bpf_get_func_ip)(void *ctx) = (void *) 173; - -/* - * bpf_get_attach_cookie - * - * Get bpf_cookie value provided (optionally) during the program - * attachment. It might be different for each individual - * attachment, even if BPF program itself is the same. - * Expects BPF program context *ctx* as a first argument. - * - * Supported for the following program types: - * - kprobe/uprobe; - * - tracepoint; - * - perf_event. - * - * Returns - * Value specified by user at BPF link creation/attachment time - * or 0, if it was not specified. - */ -static __u64 (*bpf_get_attach_cookie)(void *ctx) = (void *) 174; - -/* - * bpf_task_pt_regs - * - * Get the struct pt_regs associated with **task**. - * - * Returns - * A pointer to struct pt_regs. - */ -static long (*bpf_task_pt_regs)(struct task_struct *task) = (void *) 175; - -/* - * bpf_get_branch_snapshot - * - * Get branch trace from hardware engines like Intel LBR. The - * hardware engine is stopped shortly after the helper is - * called. Therefore, the user need to filter branch entries - * based on the actual use case. To capture branch trace - * before the trigger point of the BPF program, the helper - * should be called at the beginning of the BPF program. - * - * The data is stored as struct perf_branch_entry into output - * buffer *entries*. *size* is the size of *entries* in bytes. - * *flags* is reserved for now and must be zero. - * - * - * Returns - * On success, number of bytes written to *buf*. On error, a - * negative value. - * - * **-EINVAL** if *flags* is not zero. - * - * **-ENOENT** if architecture does not support branch records. - */ -static long (*bpf_get_branch_snapshot)(void *entries, __u32 size, __u64 flags) = (void *) 176; - -/* - * bpf_trace_vprintk - * - * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 - * to format and can handle more format args as a result. - * - * Arguments are to be used as in **bpf_seq_printf**\ () helper. - * - * Returns - * The number of bytes written to the buffer, or a negative error - * in case of failure. - */ -static long (*bpf_trace_vprintk)(const char *fmt, __u32 fmt_size, const void *data, __u32 data_len) = (void *) 177; - -/* - * bpf_skc_to_unix_sock - * - * Dynamically cast a *sk* pointer to a *unix_sock* pointer. - * - * Returns - * *sk* if casting is valid, or **NULL** otherwise. - */ -static struct unix_sock *(*bpf_skc_to_unix_sock)(void *sk) = (void *) 178; - -/* - * bpf_kallsyms_lookup_name - * - * Get the address of a kernel symbol, returned in *res*. *res* is - * set to 0 if the symbol is not found. - * - * Returns - * On success, zero. On error, a negative value. - * - * **-EINVAL** if *flags* is not zero. - * - * **-EINVAL** if string *name* is not the same size as *name_sz*. - * - * **-ENOENT** if symbol is not found. - * - * **-EPERM** if caller does not have permission to obtain kernel address. - */ -static long (*bpf_kallsyms_lookup_name)(const char *name, int name_sz, int flags, __u64 *res) = (void *) 179; - -/* - * bpf_find_vma - * - * Find vma of *task* that contains *addr*, call *callback_fn* - * function with *task*, *vma*, and *callback_ctx*. - * The *callback_fn* should be a static function and - * the *callback_ctx* should be a pointer to the stack. - * The *flags* is used to control certain aspects of the helper. - * Currently, the *flags* must be 0. - * - * The expected callback signature is - * - * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); - * - * - * Returns - * 0 on success. - * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. - * **-EBUSY** if failed to try lock mmap_lock. - * **-EINVAL** for invalid **flags**. - */ -static long (*bpf_find_vma)(struct task_struct *task, __u64 addr, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 180; - -/* - * bpf_loop - * - * For **nr_loops**, call **callback_fn** function - * with **callback_ctx** as the context parameter. - * The **callback_fn** should be a static function and - * the **callback_ctx** should be a pointer to the stack. - * The **flags** is used to control certain aspects of the helper. - * Currently, the **flags** must be 0. Currently, nr_loops is - * limited to 1 << 23 (~8 million) loops. - * - * long (\*callback_fn)(u32 index, void \*ctx); - * - * where **index** is the current index in the loop. The index - * is zero-indexed. - * - * If **callback_fn** returns 0, the helper will continue to the next - * loop. If return value is 1, the helper will skip the rest of - * the loops and return. Other return values are not used now, - * and will be rejected by the verifier. - * - * - * Returns - * The number of loops performed, **-EINVAL** for invalid **flags**, - * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. - */ -static long (*bpf_loop)(__u32 nr_loops, void *callback_fn, void *callback_ctx, __u64 flags) = (void *) 181; - -/* - * bpf_strncmp - * - * Do strncmp() between **s1** and **s2**. **s1** doesn't need - * to be null-terminated and **s1_sz** is the maximum storage - * size of **s1**. **s2** must be a read-only string. - * - * Returns - * An integer less than, equal to, or greater than zero - * if the first **s1_sz** bytes of **s1** is found to be - * less than, to match, or be greater than **s2**. - */ -static long (*bpf_strncmp)(const char *s1, __u32 s1_sz, const char *s2) = (void *) 182; - -/* - * bpf_get_func_arg - * - * Get **n**-th argument (zero based) of the traced function (for tracing programs) - * returned in **value**. - * - * - * Returns - * 0 on success. - * **-EINVAL** if n >= arguments count of traced function. - */ -static long (*bpf_get_func_arg)(void *ctx, __u32 n, __u64 *value) = (void *) 183; - -/* - * bpf_get_func_ret - * - * Get return value of the traced function (for tracing programs) - * in **value**. - * - * - * Returns - * 0 on success. - * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. - */ -static long (*bpf_get_func_ret)(void *ctx, __u64 *value) = (void *) 184; - -/* - * bpf_get_func_arg_cnt - * - * Get number of arguments of the traced function (for tracing programs). - * - * - * Returns - * The number of arguments of the traced function. - */ -static long (*bpf_get_func_arg_cnt)(void *ctx) = (void *) 185; - -/* - * bpf_get_retval - * - * Get the syscall's return value that will be returned to userspace. - * - * This helper is currently supported by cgroup programs only. - * - * Returns - * The syscall's return value. - */ -static int (*bpf_get_retval)(void) = (void *) 186; - -/* - * bpf_set_retval - * - * Set the syscall's return value that will be returned to userspace. - * - * This helper is currently supported by cgroup programs only. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static int (*bpf_set_retval)(int retval) = (void *) 187; - -/* - * bpf_xdp_get_buff_len - * - * Get the total size of a given xdp buff (linear and paged area) - * - * Returns - * The total size of a given xdp buffer. - */ -static __u64 (*bpf_xdp_get_buff_len)(struct xdp_md *xdp_md) = (void *) 188; - -/* - * bpf_xdp_load_bytes - * - * This helper is provided as an easy way to load data from a - * xdp buffer. It can be used to load *len* bytes from *offset* from - * the frame associated to *xdp_md*, into the buffer pointed by - * *buf*. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_xdp_load_bytes)(struct xdp_md *xdp_md, __u32 offset, void *buf, __u32 len) = (void *) 189; - -/* - * bpf_xdp_store_bytes - * - * Store *len* bytes from buffer *buf* into the frame - * associated to *xdp_md*, at *offset*. - * - * Returns - * 0 on success, or a negative error in case of failure. - */ -static long (*bpf_xdp_store_bytes)(struct xdp_md *xdp_md, __u32 offset, void *buf, __u32 len) = (void *) 190; - -/* - * bpf_copy_from_user_task - * - * Read *size* bytes from user space address *user_ptr* in *tsk*'s - * address space, and stores the data in *dst*. *flags* is not - * used yet and is provided for future extensibility. This helper - * can only be used by sleepable programs. - * - * Returns - * 0 on success, or a negative error in case of failure. On error - * *dst* buffer is zeroed out. - */ -static long (*bpf_copy_from_user_task)(void *dst, __u32 size, const void *user_ptr, struct task_struct *tsk, __u64 flags) = (void *) 191; - -/* - * bpf_skb_set_tstamp - * - * Change the __sk_buff->tstamp_type to *tstamp_type* - * and set *tstamp* to the __sk_buff->tstamp together. - * - * If there is no need to change the __sk_buff->tstamp_type, - * the tstamp value can be directly written to __sk_buff->tstamp - * instead. - * - * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that - * will be kept during bpf_redirect_*(). A non zero - * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO - * *tstamp_type*. - * - * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used - * with a zero *tstamp*. - * - * Only IPv4 and IPv6 skb->protocol are supported. - * - * This function is most useful when it needs to set a - * mono delivery time to __sk_buff->tstamp and then - * bpf_redirect_*() to the egress of an iface. For example, - * changing the (rcv) timestamp in __sk_buff->tstamp at - * ingress to a mono delivery time and then bpf_redirect_*() - * to sch_fq@phy-dev. - * - * Returns - * 0 on success. - * **-EINVAL** for invalid input - * **-EOPNOTSUPP** for unsupported protocol - */ -static long (*bpf_skb_set_tstamp)(struct __sk_buff *skb, __u64 tstamp, __u32 tstamp_type) = (void *) 192; - -/* - * bpf_ima_file_hash - * - * Returns a calculated IMA hash of the *file*. - * If the hash is larger than *size*, then only *size* - * bytes will be copied to *dst* - * - * Returns - * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if - * invalid arguments are passed. - */ -static long (*bpf_ima_file_hash)(struct file *file, void *dst, __u32 size) = (void *) 193; - -/* - * bpf_kptr_xchg - * - * Exchange kptr at pointer *map_value* with *ptr*, and return the - * old value. *ptr* can be NULL, otherwise it must be a referenced - * pointer which will be released when this helper is called. - * - * Returns - * The old value of kptr (which can be NULL). The returned pointer - * if not NULL, is a reference which must be released using its - * corresponding release function, or moved into a BPF map before - * program exit. - */ -static void *(*bpf_kptr_xchg)(void *map_value, void *ptr) = (void *) 194; - -/* - * bpf_map_lookup_percpu_elem - * - * Perform a lookup in *percpu map* for an entry associated to - * *key* on *cpu*. - * - * Returns - * Map value associated to *key* on *cpu*, or **NULL** if no entry - * was found or *cpu* is invalid. - */ -static void *(*bpf_map_lookup_percpu_elem)(void *map, const void *key, __u32 cpu) = (void *) 195; - - diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_helpers.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_helpers.h deleted file mode 100644 index fb04eaf367f1713f1e4b653e6c9ad883926eb598..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_helpers.h +++ /dev/null @@ -1,288 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __BPF_HELPERS__ -#define __BPF_HELPERS__ - -/* - * Note that bpf programs need to include either - * vmlinux.h (auto-generated from BTF) or linux/types.h - * in advance since bpf_helper_defs.h uses such types - * as __u64. - */ -#include "bpf_helper_defs.h" - -#define __uint(name, val) int (*name)[val] -#define __type(name, val) typeof(val) *name -#define __array(name, val) typeof(val) *name[] - -/* - * Helper macro to place programs, maps, license in - * different sections in elf_bpf file. Section names - * are interpreted by libbpf depending on the context (BPF programs, BPF maps, - * extern variables, etc). - * To allow use of SEC() with externs (e.g., for extern .maps declarations), - * make sure __attribute__((unused)) doesn't trigger compilation warning. - */ -#define SEC(name) \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wignored-attributes\"") \ - __attribute__((section(name), used)) \ - _Pragma("GCC diagnostic pop") \ - -/* Avoid 'linux/stddef.h' definition of '__always_inline'. */ -#undef __always_inline -#define __always_inline inline __attribute__((always_inline)) - -#ifndef __noinline -#define __noinline __attribute__((noinline)) -#endif -#ifndef __weak -#define __weak __attribute__((weak)) -#endif - -/* - * Use __hidden attribute to mark a non-static BPF subprogram effectively - * static for BPF verifier's verification algorithm purposes, allowing more - * extensive and permissive BPF verification process, taking into account - * subprogram's caller context. - */ -#define __hidden __attribute__((visibility("hidden"))) - -/* When utilizing vmlinux.h with BPF CO-RE, user BPF programs can't include - * any system-level headers (such as stddef.h, linux/version.h, etc), and - * commonly-used macros like NULL and KERNEL_VERSION aren't available through - * vmlinux.h. This just adds unnecessary hurdles and forces users to re-define - * them on their own. So as a convenience, provide such definitions here. - */ -#ifndef NULL -#define NULL ((void *)0) -#endif - -#ifndef KERNEL_VERSION -#define KERNEL_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + ((c) > 255 ? 255 : (c))) -#endif - -/* - * Helper macros to manipulate data structures - */ -#ifndef offsetof -#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) -#endif -#ifndef container_of -#define container_of(ptr, type, member) \ - ({ \ - void *__mptr = (void *)(ptr); \ - ((type *)(__mptr - offsetof(type, member))); \ - }) -#endif - -/* - * Compiler (optimization) barrier. - */ -#ifndef barrier -#define barrier() asm volatile("" ::: "memory") -#endif - -/* Variable-specific compiler (optimization) barrier. It's a no-op which makes - * compiler believe that there is some black box modification of a given - * variable and thus prevents compiler from making extra assumption about its - * value and potential simplifications and optimizations on this variable. - * - * E.g., compiler might often delay or even omit 32-bit to 64-bit casting of - * a variable, making some code patterns unverifiable. Putting barrier_var() - * in place will ensure that cast is performed before the barrier_var() - * invocation, because compiler has to pessimistically assume that embedded - * asm section might perform some extra operations on that variable. - * - * This is a variable-specific variant of more global barrier(). - */ -#ifndef barrier_var -#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var)) -#endif - -/* - * Helper macro to throw a compilation error if __bpf_unreachable() gets - * built into the resulting code. This works given BPF back end does not - * implement __builtin_trap(). This is useful to assert that certain paths - * of the program code are never used and hence eliminated by the compiler. - * - * For example, consider a switch statement that covers known cases used by - * the program. __bpf_unreachable() can then reside in the default case. If - * the program gets extended such that a case is not covered in the switch - * statement, then it will throw a build error due to the default case not - * being compiled out. - */ -#ifndef __bpf_unreachable -# define __bpf_unreachable() __builtin_trap() -#endif - -/* - * Helper function to perform a tail call with a constant/immediate map slot. - */ -#if __clang_major__ >= 8 && defined(__bpf__) -static __always_inline void -bpf_tail_call_static(void *ctx, const void *map, const __u32 slot) -{ - if (!__builtin_constant_p(slot)) - __bpf_unreachable(); - - /* - * Provide a hard guarantee that LLVM won't optimize setting r2 (map - * pointer) and r3 (constant map index) from _different paths_ ending - * up at the _same_ call insn as otherwise we won't be able to use the - * jmpq/nopl retpoline-free patching by the x86-64 JIT in the kernel - * given they mismatch. See also d2e4c1e6c294 ("bpf: Constant map key - * tracking for prog array pokes") for details on verifier tracking. - * - * Note on clobber list: we need to stay in-line with BPF calling - * convention, so even if we don't end up using r0, r4, r5, we need - * to mark them as clobber so that LLVM doesn't end up using them - * before / after the call. - */ - asm volatile("r1 = %[ctx]\n\t" - "r2 = %[map]\n\t" - "r3 = %[slot]\n\t" - "call 12" - :: [ctx]"r"(ctx), [map]"r"(map), [slot]"i"(slot) - : "r0", "r1", "r2", "r3", "r4", "r5"); -} -#endif - -/* - * Helper structure used by eBPF C program - * to describe BPF map attributes to libbpf loader - */ -struct bpf_map_def { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; - unsigned int map_flags; -} __attribute__((deprecated("use BTF-defined maps in .maps section"))); - -enum libbpf_pin_type { - LIBBPF_PIN_NONE, - /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ - LIBBPF_PIN_BY_NAME, -}; - -enum libbpf_tristate { - TRI_NO = 0, - TRI_YES = 1, - TRI_MODULE = 2, -}; - -#define __kconfig __attribute__((section(".kconfig"))) -#define __ksym __attribute__((section(".ksyms"))) -#define __kptr __attribute__((btf_type_tag("kptr"))) -#define __kptr_ref __attribute__((btf_type_tag("kptr_ref"))) - -#ifndef ___bpf_concat -#define ___bpf_concat(a, b) a ## b -#endif -#ifndef ___bpf_apply -#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) -#endif -#ifndef ___bpf_nth -#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N -#endif -#ifndef ___bpf_narg -#define ___bpf_narg(...) \ - ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) -#endif - -#define ___bpf_fill0(arr, p, x) do {} while (0) -#define ___bpf_fill1(arr, p, x) arr[p] = x -#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args) -#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args) -#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args) -#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args) -#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args) -#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args) -#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args) -#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args) -#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args) -#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args) -#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args) -#define ___bpf_fill(arr, args...) \ - ___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args) - -/* - * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values - * in a structure. - */ -#define BPF_SEQ_PRINTF(seq, fmt, args...) \ -({ \ - static const char ___fmt[] = fmt; \ - unsigned long long ___param[___bpf_narg(args)]; \ - \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - ___bpf_fill(___param, args); \ - _Pragma("GCC diagnostic pop") \ - \ - bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \ - ___param, sizeof(___param)); \ -}) - -/* - * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of - * an array of u64. - */ -#define BPF_SNPRINTF(out, out_size, fmt, args...) \ -({ \ - static const char ___fmt[] = fmt; \ - unsigned long long ___param[___bpf_narg(args)]; \ - \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - ___bpf_fill(___param, args); \ - _Pragma("GCC diagnostic pop") \ - \ - bpf_snprintf(out, out_size, ___fmt, \ - ___param, sizeof(___param)); \ -}) - -#ifdef BPF_NO_GLOBAL_DATA -#define BPF_PRINTK_FMT_MOD -#else -#define BPF_PRINTK_FMT_MOD static const -#endif - -#define __bpf_printk(fmt, ...) \ -({ \ - BPF_PRINTK_FMT_MOD char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - -/* - * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments - * instead of an array of u64. - */ -#define __bpf_vprintk(fmt, args...) \ -({ \ - static const char ___fmt[] = fmt; \ - unsigned long long ___param[___bpf_narg(args)]; \ - \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - ___bpf_fill(___param, args); \ - _Pragma("GCC diagnostic pop") \ - \ - bpf_trace_vprintk(___fmt, sizeof(___fmt), \ - ___param, sizeof(___param)); \ -}) - -/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args - * Otherwise use __bpf_vprintk - */ -#define ___bpf_pick_printk(...) \ - ___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ - __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ - __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\ - __bpf_printk /*1*/, __bpf_printk /*0*/) - -/* Helper macro to print out debug messages */ -#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args) - -#endif diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_tracing.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_tracing.h deleted file mode 100644 index 01ce121c302dfeeff2f0887d9c30c2449581ca92..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/bpf_tracing.h +++ /dev/null @@ -1,531 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __BPF_TRACING_H__ -#define __BPF_TRACING_H__ - -/* Scan the ARCH passed in from ARCH env variable (see Makefile) */ -#if defined(__TARGET_ARCH_x86) - #define bpf_target_x86 - #define bpf_target_defined -#elif defined(__TARGET_ARCH_s390) - #define bpf_target_s390 - #define bpf_target_defined -#elif defined(__TARGET_ARCH_arm) - #define bpf_target_arm - #define bpf_target_defined -#elif defined(__TARGET_ARCH_arm64) - #define bpf_target_arm64 - #define bpf_target_defined -#elif defined(__TARGET_ARCH_mips) - #define bpf_target_mips - #define bpf_target_defined -#elif defined(__TARGET_ARCH_powerpc) - #define bpf_target_powerpc - #define bpf_target_defined -#elif defined(__TARGET_ARCH_sparc) - #define bpf_target_sparc - #define bpf_target_defined -#elif defined(__TARGET_ARCH_riscv) - #define bpf_target_riscv - #define bpf_target_defined -#elif defined(__TARGET_ARCH_arc) - #define bpf_target_arc - #define bpf_target_defined -#else - -/* Fall back to what the compiler says */ -#if defined(__x86_64__) - #define bpf_target_x86 - #define bpf_target_defined -#elif defined(__s390__) - #define bpf_target_s390 - #define bpf_target_defined -#elif defined(__arm__) - #define bpf_target_arm - #define bpf_target_defined -#elif defined(__aarch64__) - #define bpf_target_arm64 - #define bpf_target_defined -#elif defined(__mips__) - #define bpf_target_mips - #define bpf_target_defined -#elif defined(__powerpc__) - #define bpf_target_powerpc - #define bpf_target_defined -#elif defined(__sparc__) - #define bpf_target_sparc - #define bpf_target_defined -#elif defined(__riscv) && __riscv_xlen == 64 - #define bpf_target_riscv - #define bpf_target_defined -#elif defined(__arc__) - #define bpf_target_arc - #define bpf_target_defined -#endif /* no compiler target */ - -#endif - -#ifndef __BPF_TARGET_MISSING -#define __BPF_TARGET_MISSING "GCC error \"Must specify a BPF target arch via __TARGET_ARCH_xxx\"" -#endif - -#if defined(bpf_target_x86) - -#if defined(__KERNEL__) || defined(__VMLINUX_H__) - -#define __PT_PARM1_REG di -#define __PT_PARM2_REG si -#define __PT_PARM3_REG dx -#define __PT_PARM4_REG cx -#define __PT_PARM5_REG r8 -#define __PT_RET_REG sp -#define __PT_FP_REG bp -#define __PT_RC_REG ax -#define __PT_SP_REG sp -#define __PT_IP_REG ip -/* syscall uses r10 for PARM4 */ -#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) -#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) - -#else - -#ifdef __i386__ - -#define __PT_PARM1_REG eax -#define __PT_PARM2_REG edx -#define __PT_PARM3_REG ecx -/* i386 kernel is built with -mregparm=3 */ -#define __PT_PARM4_REG __unsupported__ -#define __PT_PARM5_REG __unsupported__ -#define __PT_RET_REG esp -#define __PT_FP_REG ebp -#define __PT_RC_REG eax -#define __PT_SP_REG esp -#define __PT_IP_REG eip - -#else /* __i386__ */ - -#define __PT_PARM1_REG rdi -#define __PT_PARM2_REG rsi -#define __PT_PARM3_REG rdx -#define __PT_PARM4_REG rcx -#define __PT_PARM5_REG r8 -#define __PT_RET_REG rsp -#define __PT_FP_REG rbp -#define __PT_RC_REG rax -#define __PT_SP_REG rsp -#define __PT_IP_REG rip -/* syscall uses r10 for PARM4 */ -#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) -#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) - -#endif /* __i386__ */ - -#endif /* __KERNEL__ || __VMLINUX_H__ */ - -#elif defined(bpf_target_s390) - -struct pt_regs___s390 { - unsigned long orig_gpr2; -}; - -/* s390 provides user_pt_regs instead of struct pt_regs to userspace */ -#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) -#define __PT_PARM1_REG gprs[2] -#define __PT_PARM2_REG gprs[3] -#define __PT_PARM3_REG gprs[4] -#define __PT_PARM4_REG gprs[5] -#define __PT_PARM5_REG gprs[6] -#define __PT_RET_REG grps[14] -#define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */ -#define __PT_RC_REG gprs[2] -#define __PT_SP_REG gprs[15] -#define __PT_IP_REG psw.addr -#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; }) -#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2) - -#elif defined(bpf_target_arm) - -#define __PT_PARM1_REG uregs[0] -#define __PT_PARM2_REG uregs[1] -#define __PT_PARM3_REG uregs[2] -#define __PT_PARM4_REG uregs[3] -#define __PT_PARM5_REG uregs[4] -#define __PT_RET_REG uregs[14] -#define __PT_FP_REG uregs[11] /* Works only with CONFIG_FRAME_POINTER */ -#define __PT_RC_REG uregs[0] -#define __PT_SP_REG uregs[13] -#define __PT_IP_REG uregs[12] - -#elif defined(bpf_target_arm64) - -struct pt_regs___arm64 { - unsigned long orig_x0; -}; - -/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ -#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) -#define __PT_PARM1_REG regs[0] -#define __PT_PARM2_REG regs[1] -#define __PT_PARM3_REG regs[2] -#define __PT_PARM4_REG regs[3] -#define __PT_PARM5_REG regs[4] -#define __PT_RET_REG regs[30] -#define __PT_FP_REG regs[29] /* Works only with CONFIG_FRAME_POINTER */ -#define __PT_RC_REG regs[0] -#define __PT_SP_REG sp -#define __PT_IP_REG pc -#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; }) -#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0) - -#elif defined(bpf_target_mips) - -#define __PT_PARM1_REG regs[4] -#define __PT_PARM2_REG regs[5] -#define __PT_PARM3_REG regs[6] -#define __PT_PARM4_REG regs[7] -#define __PT_PARM5_REG regs[8] -#define __PT_RET_REG regs[31] -#define __PT_FP_REG regs[30] /* Works only with CONFIG_FRAME_POINTER */ -#define __PT_RC_REG regs[2] -#define __PT_SP_REG regs[29] -#define __PT_IP_REG cp0_epc - -#elif defined(bpf_target_powerpc) - -#define __PT_PARM1_REG gpr[3] -#define __PT_PARM2_REG gpr[4] -#define __PT_PARM3_REG gpr[5] -#define __PT_PARM4_REG gpr[6] -#define __PT_PARM5_REG gpr[7] -#define __PT_RET_REG regs[31] -#define __PT_FP_REG __unsupported__ -#define __PT_RC_REG gpr[3] -#define __PT_SP_REG sp -#define __PT_IP_REG nip -/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ -#define PT_REGS_SYSCALL_REGS(ctx) ctx - -#elif defined(bpf_target_sparc) - -#define __PT_PARM1_REG u_regs[UREG_I0] -#define __PT_PARM2_REG u_regs[UREG_I1] -#define __PT_PARM3_REG u_regs[UREG_I2] -#define __PT_PARM4_REG u_regs[UREG_I3] -#define __PT_PARM5_REG u_regs[UREG_I4] -#define __PT_RET_REG u_regs[UREG_I7] -#define __PT_FP_REG __unsupported__ -#define __PT_RC_REG u_regs[UREG_I0] -#define __PT_SP_REG u_regs[UREG_FP] -/* Should this also be a bpf_target check for the sparc case? */ -#if defined(__arch64__) -#define __PT_IP_REG tpc -#else -#define __PT_IP_REG pc -#endif - -#elif defined(bpf_target_riscv) - -#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) -#define __PT_PARM1_REG a0 -#define __PT_PARM2_REG a1 -#define __PT_PARM3_REG a2 -#define __PT_PARM4_REG a3 -#define __PT_PARM5_REG a4 -#define __PT_RET_REG ra -#define __PT_FP_REG s0 -#define __PT_RC_REG a5 -#define __PT_SP_REG sp -#define __PT_IP_REG pc -/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */ -#define PT_REGS_SYSCALL_REGS(ctx) ctx - -#elif defined(bpf_target_arc) - -/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */ -#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) -#define __PT_PARM1_REG scratch.r0 -#define __PT_PARM2_REG scratch.r1 -#define __PT_PARM3_REG scratch.r2 -#define __PT_PARM4_REG scratch.r3 -#define __PT_PARM5_REG scratch.r4 -#define __PT_RET_REG scratch.blink -#define __PT_FP_REG __unsupported__ -#define __PT_RC_REG scratch.r0 -#define __PT_SP_REG scratch.sp -#define __PT_IP_REG scratch.ret -/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */ -#define PT_REGS_SYSCALL_REGS(ctx) ctx - -#endif - -#if defined(bpf_target_defined) - -struct pt_regs; - -/* allow some architecutres to override `struct pt_regs` */ -#ifndef __PT_REGS_CAST -#define __PT_REGS_CAST(x) (x) -#endif - -#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG) -#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG) -#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG) -#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG) -#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG) -#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG) -#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG) -#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG) -#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG) -#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG) - -#if defined(bpf_target_powerpc) - -#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) -#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP - -#elif defined(bpf_target_sparc) - -#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) -#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP - -#else - -#define BPF_KPROBE_READ_RET_IP(ip, ctx) \ - ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) -#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \ - ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) - -#endif - -#ifndef PT_REGS_PARM1_SYSCALL -#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x) -#endif -#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x) -#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x) -#ifndef PT_REGS_PARM4_SYSCALL -#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x) -#endif -#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x) - -#ifndef PT_REGS_PARM1_CORE_SYSCALL -#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x) -#endif -#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x) -#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x) -#ifndef PT_REGS_PARM4_CORE_SYSCALL -#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x) -#endif -#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x) - -#else /* defined(bpf_target_defined) */ - -#define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_SP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_IP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) - -#define PT_REGS_PARM1_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM2_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_SP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_IP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) - -#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) - -#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) - -#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) -#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) - -#endif /* defined(bpf_target_defined) */ - -/* - * When invoked from a syscall handler kprobe, returns a pointer to a - * struct pt_regs containing syscall arguments and suitable for passing to - * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL(). - */ -#ifndef PT_REGS_SYSCALL_REGS -/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */ -#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx)) -#endif - -#ifndef ___bpf_concat -#define ___bpf_concat(a, b) a ## b -#endif -#ifndef ___bpf_apply -#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) -#endif -#ifndef ___bpf_nth -#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N -#endif -#ifndef ___bpf_narg -#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) -#endif - -#define ___bpf_ctx_cast0() ctx -#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] -#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] -#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] -#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] -#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] -#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] -#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] -#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] -#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] -#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9] -#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10] -#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11] -#define ___bpf_ctx_cast(args...) ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) - -/* - * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and - * similar kinds of BPF programs, that accept input arguments as a single - * pointer to untyped u64 array, where each u64 can actually be a typed - * pointer or integer of different size. Instead of requring user to write - * manual casts and work with array elements by index, BPF_PROG macro - * allows user to declare a list of named and typed input arguments in the - * same syntax as for normal C function. All the casting is hidden and - * performed transparently, while user code can just assume working with - * function arguments of specified type and name. - * - * Original raw context argument is preserved as well as 'ctx' argument. - * This is useful when using BPF helpers that expect original context - * as one of the parameters (e.g., for bpf_perf_event_output()). - */ -#define BPF_PROG(name, args...) \ -name(unsigned long long *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ -____##name(unsigned long long *ctx, ##args); \ -typeof(name(0)) name(unsigned long long *ctx) \ -{ \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - return ____##name(___bpf_ctx_cast(args)); \ - _Pragma("GCC diagnostic pop") \ -} \ -static __attribute__((always_inline)) typeof(name(0)) \ -____##name(unsigned long long *ctx, ##args) - -struct pt_regs; - -#define ___bpf_kprobe_args0() ctx -#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) -#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) -#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) -#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) -#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) -#define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) - -/* - * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for - * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific - * low-level way of getting kprobe input arguments from struct pt_regs, and - * provides a familiar typed and named function arguments syntax and - * semantics of accessing kprobe input paremeters. - * - * Original struct pt_regs* context is preserved as 'ctx' argument. This might - * be necessary when using BPF helpers like bpf_perf_event_output(). - */ -#define BPF_KPROBE(name, args...) \ -name(struct pt_regs *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ -____##name(struct pt_regs *ctx, ##args); \ -typeof(name(0)) name(struct pt_regs *ctx) \ -{ \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - return ____##name(___bpf_kprobe_args(args)); \ - _Pragma("GCC diagnostic pop") \ -} \ -static __attribute__((always_inline)) typeof(name(0)) \ -____##name(struct pt_regs *ctx, ##args) - -#define ___bpf_kretprobe_args0() ctx -#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) -#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) - -/* - * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional - * return value (in addition to `struct pt_regs *ctx`), but no input - * arguments, because they will be clobbered by the time probed function - * returns. - */ -#define BPF_KRETPROBE(name, args...) \ -name(struct pt_regs *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ -____##name(struct pt_regs *ctx, ##args); \ -typeof(name(0)) name(struct pt_regs *ctx) \ -{ \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - return ____##name(___bpf_kretprobe_args(args)); \ - _Pragma("GCC diagnostic pop") \ -} \ -static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) - -#define ___bpf_syscall_args0() ctx -#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs) -#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs) -#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) -#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) -#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) -#define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) - -/* - * BPF_KPROBE_SYSCALL is a variant of BPF_KPROBE, which is intended for - * tracing syscall functions, like __x64_sys_close. It hides the underlying - * platform-specific low-level way of getting syscall input arguments from - * struct pt_regs, and provides a familiar typed and named function arguments - * syntax and semantics of accessing syscall input parameters. - * - * Original struct pt_regs* context is preserved as 'ctx' argument. This might - * be necessary when using BPF helpers like bpf_perf_event_output(). - * - * This macro relies on BPF CO-RE support. - */ -#define BPF_KPROBE_SYSCALL(name, args...) \ -name(struct pt_regs *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ -____##name(struct pt_regs *ctx, ##args); \ -typeof(name(0)) name(struct pt_regs *ctx) \ -{ \ - struct pt_regs *regs = PT_REGS_SYSCALL_REGS(ctx); \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - return ____##name(___bpf_syscall_args(args)); \ - _Pragma("GCC diagnostic pop") \ -} \ -static __attribute__((always_inline)) typeof(name(0)) \ -____##name(struct pt_regs *ctx, ##args) - -#endif diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/btf.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/btf.h deleted file mode 100644 index 951ac74757948fd473a7ab18273f06b21c54d3a6..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/btf.h +++ /dev/null @@ -1,605 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -/* Copyright (c) 2018 Facebook */ -/*! \file */ - -#ifndef __LIBBPF_BTF_H -#define __LIBBPF_BTF_H - -#include -#include -#include -#include - -#include "libbpf_common.h" - -#ifdef __cplusplus -extern "C" { -#endif - -#define BTF_ELF_SEC ".BTF" -#define BTF_EXT_ELF_SEC ".BTF.ext" -#define MAPS_ELF_SEC ".maps" - -struct btf; -struct btf_ext; -struct btf_type; - -struct bpf_object; - -enum btf_endianness { - BTF_LITTLE_ENDIAN = 0, - BTF_BIG_ENDIAN = 1, -}; - -/** - * @brief **btf__free()** frees all data of a BTF object - * @param btf BTF object to free - */ -LIBBPF_API void btf__free(struct btf *btf); - -/** - * @brief **btf__new()** creates a new instance of a BTF object from the raw - * bytes of an ELF's BTF section - * @param data raw bytes - * @param size number of bytes passed in `data` - * @return new BTF object instance which has to be eventually freed with - * **btf__free()** - * - * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract - * error code from such a pointer `libbpf_get_error()` should be used. If - * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is - * returned on error instead. In both cases thread-local `errno` variable is - * always set to error code as well. - */ -LIBBPF_API struct btf *btf__new(const void *data, __u32 size); - -/** - * @brief **btf__new_split()** create a new instance of a BTF object from the - * provided raw data bytes. It takes another BTF instance, **base_btf**, which - * serves as a base BTF, which is extended by types in a newly created BTF - * instance - * @param data raw bytes - * @param size length of raw bytes - * @param base_btf the base BTF object - * @return new BTF object instance which has to be eventually freed with - * **btf__free()** - * - * If *base_btf* is NULL, `btf__new_split()` is equivalent to `btf__new()` and - * creates non-split BTF. - * - * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract - * error code from such a pointer `libbpf_get_error()` should be used. If - * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is - * returned on error instead. In both cases thread-local `errno` variable is - * always set to error code as well. - */ -LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf); - -/** - * @brief **btf__new_empty()** creates an empty BTF object. Use - * `btf__add_*()` to populate such BTF object. - * @return new BTF object instance which has to be eventually freed with - * **btf__free()** - * - * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract - * error code from such a pointer `libbpf_get_error()` should be used. If - * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is - * returned on error instead. In both cases thread-local `errno` variable is - * always set to error code as well. - */ -LIBBPF_API struct btf *btf__new_empty(void); - -/** - * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an - * ELF BTF section except with a base BTF on top of which split BTF should be - * based - * @return new BTF object instance which has to be eventually freed with - * **btf__free()** - * - * If *base_btf* is NULL, `btf__new_empty_split()` is equivalent to - * `btf__new_empty()` and creates non-split BTF. - * - * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract - * error code from such a pointer `libbpf_get_error()` should be used. If - * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is - * returned on error instead. In both cases thread-local `errno` variable is - * always set to error code as well. - */ -LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf); - -LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext); -LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf); -LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext); -LIBBPF_API struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf); -LIBBPF_API struct btf *btf__parse_raw(const char *path); -LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf); - -LIBBPF_API struct btf *btf__load_vmlinux_btf(void); -LIBBPF_API struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_btf); -LIBBPF_API struct btf *libbpf_find_kernel_btf(void); - -LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id); -LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf); -LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead") -LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf); - -LIBBPF_DEPRECATED_SINCE(0, 6, "intended for internal libbpf use only") -LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); -LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead") -LIBBPF_API int btf__load(struct btf *btf); -LIBBPF_API int btf__load_into_kernel(struct btf *btf); -LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, - const char *type_name); -LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, - const char *type_name, __u32 kind); -LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__type_cnt() instead; note that btf__get_nr_types() == btf__type_cnt() - 1") -LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); -LIBBPF_API __u32 btf__type_cnt(const struct btf *btf); -LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf); -LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, - __u32 id); -LIBBPF_API size_t btf__pointer_size(const struct btf *btf); -LIBBPF_API int btf__set_pointer_size(struct btf *btf, size_t ptr_sz); -LIBBPF_API enum btf_endianness btf__endianness(const struct btf *btf); -LIBBPF_API int btf__set_endianness(struct btf *btf, enum btf_endianness endian); -LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); -LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); -LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); -LIBBPF_API int btf__fd(const struct btf *btf); -LIBBPF_API void btf__set_fd(struct btf *btf, int fd); -LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size); -LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); -LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset); -LIBBPF_DEPRECATED_SINCE(0, 7, "this API is not necessary when BTF-defined maps are used") -LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, - __u32 expected_key_size, - __u32 expected_value_size, - __u32 *key_type_id, __u32 *value_type_id); - -LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size); -LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); -LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size); -LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions") -int btf_ext__reloc_func_info(const struct btf *btf, - const struct btf_ext *btf_ext, - const char *sec_name, __u32 insns_cnt, - void **func_info, __u32 *cnt); -LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions") -int btf_ext__reloc_line_info(const struct btf *btf, - const struct btf_ext *btf_ext, - const char *sec_name, __u32 insns_cnt, - void **line_info, __u32 *cnt); -LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info is deprecated; write custom func_info parsing to fetch rec_size") -__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); -LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info is deprecated; write custom line_info parsing to fetch rec_size") -__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); - -LIBBPF_API int btf__find_str(struct btf *btf, const char *s); -LIBBPF_API int btf__add_str(struct btf *btf, const char *s); -LIBBPF_API int btf__add_type(struct btf *btf, const struct btf *src_btf, - const struct btf_type *src_type); -/** - * @brief **btf__add_btf()** appends all the BTF types from *src_btf* into *btf* - * @param btf BTF object which all the BTF types and strings are added to - * @param src_btf BTF object which all BTF types and referenced strings are copied from - * @return BTF type ID of the first appended BTF type, or negative error code - * - * **btf__add_btf()** can be used to simply and efficiently append the entire - * contents of one BTF object to another one. All the BTF type data is copied - * over, all referenced type IDs are adjusted by adding a necessary ID offset. - * Only strings referenced from BTF types are copied over and deduplicated, so - * if there were some unused strings in *src_btf*, those won't be copied over, - * which is consistent with the general string deduplication semantics of BTF - * writing APIs. - * - * If any error is encountered during this process, the contents of *btf* is - * left intact, which means that **btf__add_btf()** follows the transactional - * semantics and the operation as a whole is all-or-nothing. - * - * *src_btf* has to be non-split BTF, as of now copying types from split BTF - * is not supported and will result in -ENOTSUP error code returned. - */ -LIBBPF_API int btf__add_btf(struct btf *btf, const struct btf *src_btf); - -LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding); -LIBBPF_API int btf__add_float(struct btf *btf, const char *name, size_t byte_sz); -LIBBPF_API int btf__add_ptr(struct btf *btf, int ref_type_id); -LIBBPF_API int btf__add_array(struct btf *btf, - int index_type_id, int elem_type_id, __u32 nr_elems); -/* struct/union construction APIs */ -LIBBPF_API int btf__add_struct(struct btf *btf, const char *name, __u32 sz); -LIBBPF_API int btf__add_union(struct btf *btf, const char *name, __u32 sz); -LIBBPF_API int btf__add_field(struct btf *btf, const char *name, int field_type_id, - __u32 bit_offset, __u32 bit_size); - -/* enum construction APIs */ -LIBBPF_API int btf__add_enum(struct btf *btf, const char *name, __u32 bytes_sz); -LIBBPF_API int btf__add_enum_value(struct btf *btf, const char *name, __s64 value); - -enum btf_fwd_kind { - BTF_FWD_STRUCT = 0, - BTF_FWD_UNION = 1, - BTF_FWD_ENUM = 2, -}; - -LIBBPF_API int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind); -LIBBPF_API int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id); -LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id); -LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id); -LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id); -LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id); - -/* func and func_proto construction APIs */ -LIBBPF_API int btf__add_func(struct btf *btf, const char *name, - enum btf_func_linkage linkage, int proto_type_id); -LIBBPF_API int btf__add_func_proto(struct btf *btf, int ret_type_id); -LIBBPF_API int btf__add_func_param(struct btf *btf, const char *name, int type_id); - -/* var & datasec construction APIs */ -LIBBPF_API int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id); -LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz); -LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, - __u32 offset, __u32 byte_sz); - -/* tag construction API */ -LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, - int component_idx); - -struct btf_dedup_opts { - size_t sz; - /* optional .BTF.ext info to dedup along the main BTF info */ - struct btf_ext *btf_ext; - /* force hash collisions (used for testing) */ - bool force_collisions; - size_t :0; -}; -#define btf_dedup_opts__last_field force_collisions - -LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts); - -LIBBPF_API int btf__dedup_v0_6_0(struct btf *btf, const struct btf_dedup_opts *opts); - -LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__dedup() instead") -LIBBPF_API int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *opts); -#define btf__dedup(...) ___libbpf_overload(___btf_dedup, __VA_ARGS__) -#define ___btf_dedup3(btf, btf_ext, opts) btf__dedup_deprecated(btf, btf_ext, opts) -#define ___btf_dedup2(btf, opts) btf__dedup(btf, opts) - -struct btf_dump; - -struct btf_dump_opts { - union { - size_t sz; - void *ctx; /* DEPRECATED: will be gone in v1.0 */ - }; -}; - -typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args); - -LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf, - btf_dump_printf_fn_t printf_fn, - void *ctx, - const struct btf_dump_opts *opts); - -LIBBPF_API struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf, - btf_dump_printf_fn_t printf_fn, - void *ctx, - const struct btf_dump_opts *opts); - -LIBBPF_API struct btf_dump *btf_dump__new_deprecated(const struct btf *btf, - const struct btf_ext *btf_ext, - const struct btf_dump_opts *opts, - btf_dump_printf_fn_t printf_fn); - -/* Choose either btf_dump__new() or btf_dump__new_deprecated() based on the - * type of 4th argument. If it's btf_dump's print callback, use deprecated - * API; otherwise, choose the new btf_dump__new(). ___libbpf_override() - * doesn't work here because both variants have 4 input arguments. - * - * (void *) casts are necessary to avoid compilation warnings about type - * mismatches, because even though __builtin_choose_expr() only ever evaluates - * one side the other side still has to satisfy type constraints (this is - * compiler implementation limitation which might be lifted eventually, - * according to the documentation). So passing struct btf_ext in place of - * btf_dump_printf_fn_t would be generating compilation warning. Casting to - * void * avoids this issue. - * - * Also, two type compatibility checks for a function and function pointer are - * required because passing function reference into btf_dump__new() as - * btf_dump__new(..., my_callback, ...) and as btf_dump__new(..., - * &my_callback, ...) (not explicit ampersand in the latter case) actually - * differs as far as __builtin_types_compatible_p() is concerned. Thus two - * checks are combined to detect callback argument. - * - * The rest works just like in case of ___libbpf_override() usage with symbol - * versioning. - * - * C++ compilers don't support __builtin_types_compatible_p(), so at least - * don't screw up compilation for them and let C++ users pick btf_dump__new - * vs btf_dump__new_deprecated explicitly. - */ -#ifndef __cplusplus -#define btf_dump__new(a1, a2, a3, a4) __builtin_choose_expr( \ - __builtin_types_compatible_p(typeof(a4), btf_dump_printf_fn_t) || \ - __builtin_types_compatible_p(typeof(a4), void(void *, const char *, va_list)), \ - btf_dump__new_deprecated((void *)a1, (void *)a2, (void *)a3, (void *)a4), \ - btf_dump__new((void *)a1, (void *)a2, (void *)a3, (void *)a4)) -#endif - -LIBBPF_API void btf_dump__free(struct btf_dump *d); - -LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); - -struct btf_dump_emit_type_decl_opts { - /* size of this struct, for forward/backward compatiblity */ - size_t sz; - /* optional field name for type declaration, e.g.: - * - struct my_struct - * - void (*)(int) - * - char (*)[123] - */ - const char *field_name; - /* extra indentation level (in number of tabs) to emit for multi-line - * type declarations (e.g., anonymous struct); applies for lines - * starting from the second one (first line is assumed to have - * necessary indentation already - */ - int indent_level; - /* strip all the const/volatile/restrict mods */ - bool strip_mods; - size_t :0; -}; -#define btf_dump_emit_type_decl_opts__last_field strip_mods - -LIBBPF_API int -btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, - const struct btf_dump_emit_type_decl_opts *opts); - - -struct btf_dump_type_data_opts { - /* size of this struct, for forward/backward compatibility */ - size_t sz; - const char *indent_str; - int indent_level; - /* below match "show" flags for bpf_show_snprintf() */ - bool compact; /* no newlines/indentation */ - bool skip_names; /* skip member/type names */ - bool emit_zeroes; /* show 0-valued fields */ - size_t :0; -}; -#define btf_dump_type_data_opts__last_field emit_zeroes - -LIBBPF_API int -btf_dump__dump_type_data(struct btf_dump *d, __u32 id, - const void *data, size_t data_sz, - const struct btf_dump_type_data_opts *opts); - -/* - * A set of helpers for easier BTF types handling. - * - * The inline functions below rely on constants from the kernel headers which - * may not be available for applications including this header file. To avoid - * compilation errors, we define all the constants here that were added after - * the initial introduction of the BTF_KIND* constants. - */ -#ifndef BTF_KIND_FUNC -#define BTF_KIND_FUNC 12 /* Function */ -#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#endif -#ifndef BTF_KIND_VAR -#define BTF_KIND_VAR 14 /* Variable */ -#define BTF_KIND_DATASEC 15 /* Section */ -#endif -#ifndef BTF_KIND_FLOAT -#define BTF_KIND_FLOAT 16 /* Floating point */ -#endif -/* The kernel header switched to enums, so these two were never #defined */ -#define BTF_KIND_DECL_TAG 17 /* Decl Tag */ -#define BTF_KIND_TYPE_TAG 18 /* Type Tag */ - -static inline __u16 btf_kind(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info); -} - -static inline __u16 btf_vlen(const struct btf_type *t) -{ - return BTF_INFO_VLEN(t->info); -} - -static inline bool btf_kflag(const struct btf_type *t) -{ - return BTF_INFO_KFLAG(t->info); -} - -static inline bool btf_is_void(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_UNKN; -} - -static inline bool btf_is_int(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_INT; -} - -static inline bool btf_is_ptr(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_PTR; -} - -static inline bool btf_is_array(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_ARRAY; -} - -static inline bool btf_is_struct(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_STRUCT; -} - -static inline bool btf_is_union(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_UNION; -} - -static inline bool btf_is_composite(const struct btf_type *t) -{ - __u16 kind = btf_kind(t); - - return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; -} - -static inline bool btf_is_enum(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_ENUM; -} - -static inline bool btf_is_fwd(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_FWD; -} - -static inline bool btf_is_typedef(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_TYPEDEF; -} - -static inline bool btf_is_volatile(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_VOLATILE; -} - -static inline bool btf_is_const(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_CONST; -} - -static inline bool btf_is_restrict(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_RESTRICT; -} - -static inline bool btf_is_mod(const struct btf_type *t) -{ - __u16 kind = btf_kind(t); - - return kind == BTF_KIND_VOLATILE || - kind == BTF_KIND_CONST || - kind == BTF_KIND_RESTRICT || - kind == BTF_KIND_TYPE_TAG; -} - -static inline bool btf_is_func(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_FUNC; -} - -static inline bool btf_is_func_proto(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_FUNC_PROTO; -} - -static inline bool btf_is_var(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_VAR; -} - -static inline bool btf_is_datasec(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_DATASEC; -} - -static inline bool btf_is_float(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_FLOAT; -} - -static inline bool btf_is_decl_tag(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_DECL_TAG; -} - -static inline bool btf_is_type_tag(const struct btf_type *t) -{ - return btf_kind(t) == BTF_KIND_TYPE_TAG; -} - -static inline __u8 btf_int_encoding(const struct btf_type *t) -{ - return BTF_INT_ENCODING(*(__u32 *)(t + 1)); -} - -static inline __u8 btf_int_offset(const struct btf_type *t) -{ - return BTF_INT_OFFSET(*(__u32 *)(t + 1)); -} - -static inline __u8 btf_int_bits(const struct btf_type *t) -{ - return BTF_INT_BITS(*(__u32 *)(t + 1)); -} - -static inline struct btf_array *btf_array(const struct btf_type *t) -{ - return (struct btf_array *)(t + 1); -} - -static inline struct btf_enum *btf_enum(const struct btf_type *t) -{ - return (struct btf_enum *)(t + 1); -} - -static inline struct btf_member *btf_members(const struct btf_type *t) -{ - return (struct btf_member *)(t + 1); -} - -/* Get bit offset of a member with specified index. */ -static inline __u32 btf_member_bit_offset(const struct btf_type *t, - __u32 member_idx) -{ - const struct btf_member *m = btf_members(t) + member_idx; - bool kflag = btf_kflag(t); - - return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; -} -/* - * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or - * BTF_KIND_UNION. If member is not a bitfield, zero is returned. - */ -static inline __u32 btf_member_bitfield_size(const struct btf_type *t, - __u32 member_idx) -{ - const struct btf_member *m = btf_members(t) + member_idx; - bool kflag = btf_kflag(t); - - return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; -} - -static inline struct btf_param *btf_params(const struct btf_type *t) -{ - return (struct btf_param *)(t + 1); -} - -static inline struct btf_var *btf_var(const struct btf_type *t) -{ - return (struct btf_var *)(t + 1); -} - -static inline struct btf_var_secinfo * -btf_var_secinfos(const struct btf_type *t) -{ - return (struct btf_var_secinfo *)(t + 1); -} - -struct btf_decl_tag; -static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t) -{ - return (struct btf_decl_tag *)(t + 1); -} - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* __LIBBPF_BTF_H */ diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf.h deleted file mode 100644 index 9e9a3fd3edd820833831621f0e4bf337a8c2f4dc..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf.h +++ /dev/null @@ -1,1767 +0,0 @@ -/* 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 -#include // for size_t -#include - -#include "libbpf_common.h" -#include "libbpf_legacy.h" - -#ifdef __cplusplus -extern "C" { -#endif - -LIBBPF_API __u32 libbpf_major_version(void); -LIBBPF_API __u32 libbpf_minor_version(void); -LIBBPF_API const char *libbpf_version_string(void); - -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, -}; - -LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size); - -enum libbpf_print_level { - LIBBPF_WARN, - LIBBPF_INFO, - LIBBPF_DEBUG, -}; - -typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, - const char *, va_list ap); - -LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); - -/* Hide internal to user */ -struct bpf_object; - -struct bpf_object_open_attr { - const char *file; - enum bpf_prog_type prog_type; -}; - -struct bpf_object_open_opts { - /* size of this struct, for forward/backward compatiblity */ - size_t sz; - /* object name override, if provided: - * - for object open from file, this will override setting object - * name from file path's base name; - * - for object open from memory buffer, this will specify an object - * name and will override default "-" name; - */ - const char *object_name; - /* parse map definitions non-strictly, allowing extra attributes/data */ - bool relaxed_maps; - /* DEPRECATED: handle CO-RE relocations non-strictly, allowing failures. - * Value is ignored. Relocations always are processed non-strictly. - * Non-relocatable instructions are replaced with invalid ones to - * prevent accidental errors. - * */ - LIBBPF_DEPRECATED_SINCE(0, 6, "field has no effect") - bool relaxed_core_relocs; - /* maps that set the 'pinning' attribute in their definition will have - * their pin_path attribute set to a file in this directory, and be - * auto-pinned to that path on load; defaults to "/sys/fs/bpf". - */ - const char *pin_root_path; - - LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__set_attach_target() on each individual bpf_program") - __u32 attach_prog_fd; - /* Additional kernel config content that augments and overrides - * system Kconfig for CONFIG_xxx externs. - */ - const char *kconfig; - /* Path to the custom BTF to be used for BPF CO-RE relocations. - * This custom BTF completely replaces the use of vmlinux BTF - * for the purpose of CO-RE relocations. - * NOTE: any other BPF feature (e.g., fentry/fexit programs, - * struct_ops, etc) will need actual kernel BTF at /sys/kernel/btf/vmlinux. - */ - const char *btf_custom_path; - /* Pointer to a buffer for storing kernel logs for applicable BPF - * commands. Valid kernel_log_size has to be specified as well and are - * passed-through to bpf() syscall. Keep in mind that kernel might - * fail operation with -ENOSPC error if provided buffer is too small - * to contain entire log output. - * See the comment below for kernel_log_level for interaction between - * log_buf and log_level settings. - * - * If specified, this log buffer will be passed for: - * - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden - * with bpf_program__set_log() on per-program level, to get - * BPF verifier log output. - * - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get - * BTF sanity checking log. - * - * Each BPF command (BPF_BTF_LOAD or BPF_PROG_LOAD) will overwrite - * previous contents, so if you need more fine-grained control, set - * per-program buffer with bpf_program__set_log_buf() to preserve each - * individual program's verification log. Keep using kernel_log_buf - * for BTF verification log, if necessary. - */ - char *kernel_log_buf; - size_t kernel_log_size; - /* - * Log level can be set independently from log buffer. Log_level=0 - * means that libbpf will attempt loading BTF or program without any - * logging requested, but will retry with either its own or custom log - * buffer, if provided, and log_level=1 on any error. - * And vice versa, setting log_level>0 will request BTF or prog - * loading with verbose log from the first attempt (and as such also - * for successfully loaded BTF or program), and the actual log buffer - * could be either libbpf's own auto-allocated log buffer, if - * kernel_log_buffer is NULL, or user-provided custom kernel_log_buf. - * If user didn't provide custom log buffer, libbpf will emit captured - * logs through its print callback. - */ - __u32 kernel_log_level; - - size_t :0; -}; -#define bpf_object_open_opts__last_field kernel_log_level - -LIBBPF_API struct bpf_object *bpf_object__open(const char *path); - -/** - * @brief **bpf_object__open_file()** creates a bpf_object by opening - * the BPF ELF object file pointed to by the passed path and loading it - * into memory. - * @param path BPF object file path - * @param opts options for how to load the bpf object, this parameter is - * optional and can be set to NULL - * @return pointer to the new bpf_object; or NULL is returned on error, - * error code is stored in errno - */ -LIBBPF_API struct bpf_object * -bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts); - -/** - * @brief **bpf_object__open_mem()** creates a bpf_object by reading - * the BPF objects raw bytes from a memory buffer containing a valid - * BPF ELF object file. - * @param obj_buf pointer to the buffer containing ELF file bytes - * @param obj_buf_sz number of bytes in the buffer - * @param opts options for how to load the bpf object - * @return pointer to the new bpf_object; or NULL is returned on error, - * error code is stored in errno - */ -LIBBPF_API struct bpf_object * -bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, - const struct bpf_object_open_opts *opts); - -/* deprecated bpf_object__open variants */ -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open_mem() instead") -LIBBPF_API struct bpf_object * -bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, - const char *name); -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open_file() instead") -LIBBPF_API struct bpf_object * -bpf_object__open_xattr(struct bpf_object_open_attr *attr); - -enum libbpf_pin_type { - LIBBPF_PIN_NONE, - /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ - LIBBPF_PIN_BY_NAME, -}; - -/* pin_maps and unpin_maps can both be called with a NULL path, in which case - * they will use the pin_path attribute of each map (and ignore all maps that - * don't have a pin_path set). - */ -LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path); -LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj, - const char *path); -LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj, - const char *path); -LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj, - const char *path); -LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path); -LIBBPF_API void bpf_object__close(struct bpf_object *object); - -struct bpf_object_load_attr { - struct bpf_object *obj; - int log_level; - const char *target_btf_path; -}; - -/* Load/unload object into/from kernel */ -LIBBPF_API int bpf_object__load(struct bpf_object *obj); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__load() instead") -LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); -LIBBPF_DEPRECATED_SINCE(0, 6, "bpf_object__unload() is deprecated, use bpf_object__close() instead") -LIBBPF_API int bpf_object__unload(struct bpf_object *obj); - -LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); -LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); -LIBBPF_API int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version); - -struct btf; -LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); -LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); - -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__find_program_by_name() instead") -LIBBPF_API struct bpf_program * -bpf_object__find_program_by_title(const struct bpf_object *obj, - const char *title); -LIBBPF_API struct bpf_program * -bpf_object__find_program_by_name(const struct bpf_object *obj, - const char *name); - -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "track bpf_objects in application code instead") -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 *); -LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") -LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, - bpf_object_clear_priv_t clear_priv); -LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") -LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog); - -LIBBPF_API int -libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, - enum bpf_attach_type *expected_attach_type); -LIBBPF_API int libbpf_attach_type_by_name(const char *name, - enum bpf_attach_type *attach_type); -LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name, - enum bpf_attach_type attach_type); - -/* Accessors of bpf_program */ -struct bpf_program; -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_program() instead") -struct bpf_program *bpf_program__next(struct bpf_program *prog, - const struct bpf_object *obj); -LIBBPF_API struct bpf_program * -bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prog); - -#define bpf_object__for_each_program(pos, obj) \ - for ((pos) = bpf_object__next_program((obj), NULL); \ - (pos) != NULL; \ - (pos) = bpf_object__next_program((obj), (pos))) - -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_program() instead") -struct bpf_program *bpf_program__prev(struct bpf_program *prog, - const struct bpf_object *obj); -LIBBPF_API struct bpf_program * -bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog); - -typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); - -LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") -LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, - bpf_program_clear_priv_t clear_priv); -LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") -LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); -LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, - __u32 ifindex); - -LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog); -LIBBPF_API const char *bpf_program__section_name(const struct bpf_program *prog); -LIBBPF_API LIBBPF_DEPRECATED("BPF program title is confusing term; please use bpf_program__section_name() instead") -const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy); -LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog); -LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload); - -/* returns program size in bytes */ -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insn_cnt() instead") -LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog); - -struct bpf_insn; - -/** - * @brief **bpf_program__insns()** gives read-only access to BPF program's - * underlying BPF instructions. - * @param prog BPF program for which to return instructions - * @return a pointer to an array of BPF instructions that belong to the - * specified BPF program - * - * Returned pointer is always valid and not NULL. Number of `struct bpf_insn` - * pointed to can be fetched using **bpf_program__insn_cnt()** API. - * - * Keep in mind, libbpf can modify and append/delete BPF program's - * instructions as it processes BPF object file and prepares everything for - * uploading into the kernel. So depending on the point in BPF object - * lifetime, **bpf_program__insns()** can return different sets of - * instructions. As an example, during BPF object load phase BPF program - * instructions will be CO-RE-relocated, BPF subprograms instructions will be - * appended, ldimm64 instructions will have FDs embedded, etc. So instructions - * returned before **bpf_object__load()** and after it might be quite - * different. - */ -LIBBPF_API const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog); - -/** - * @brief **bpf_program__set_insns()** can set BPF program's underlying - * BPF instructions. - * - * WARNING: This is a very advanced libbpf API and users need to know - * what they are doing. This should be used from prog_prepare_load_fn - * callback only. - * - * @param prog BPF program for which to return instructions - * @param new_insns a pointer to an array of BPF instructions - * @param new_insn_cnt number of `struct bpf_insn`'s that form - * specified BPF program - * @return 0, on success; negative error code, otherwise - */ -LIBBPF_API int bpf_program__set_insns(struct bpf_program *prog, - struct bpf_insn *new_insns, size_t new_insn_cnt); - -/** - * @brief **bpf_program__insn_cnt()** returns number of `struct bpf_insn`'s - * that form specified BPF program. - * @param prog BPF program for which to return number of BPF instructions - * - * See **bpf_program__insns()** documentation for notes on how libbpf can - * change instructions and their count during different phases of - * **bpf_object** lifetime. - */ -LIBBPF_API size_t bpf_program__insn_cnt(const struct bpf_program *prog); - -LIBBPF_DEPRECATED_SINCE(0, 6, "use bpf_object__load() instead") -LIBBPF_API int bpf_program__load(struct bpf_program *prog, const char *license, __u32 kern_version); -LIBBPF_API int bpf_program__fd(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated") -LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog, - const char *path, - int instance); -LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated") -LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog, - const char *path, - int instance); - -/** - * @brief **bpf_program__pin()** pins the BPF program to a file - * in the BPF FS specified by a path. This increments the programs - * reference count, allowing it to stay loaded after the process - * which loaded it has exited. - * - * @param prog BPF program to pin, must already be loaded - * @param path file path in a BPF file system - * @return 0, on success; negative error code, otherwise - */ -LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); - -/** - * @brief **bpf_program__unpin()** unpins the BPF program from a file - * in the BPFFS specified by a path. This decrements the programs - * reference count. - * - * The file pinning the BPF program can also be unlinked by a different - * process in which case this function will return an error. - * - * @param prog BPF program to unpin - * @param path file path to the pin in a BPF file system - * @return 0, on success; negative error code, otherwise - */ -LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path); -LIBBPF_API void bpf_program__unload(struct bpf_program *prog); - -struct bpf_link; - -LIBBPF_API struct bpf_link *bpf_link__open(const char *path); -LIBBPF_API int bpf_link__fd(const struct bpf_link *link); -LIBBPF_API const char *bpf_link__pin_path(const struct bpf_link *link); -/** - * @brief **bpf_link__pin()** pins the BPF link to a file - * in the BPF FS specified by a path. This increments the links - * reference count, allowing it to stay loaded after the process - * which loaded it has exited. - * - * @param link BPF link to pin, must already be loaded - * @param path file path in a BPF file system - * @return 0, on success; negative error code, otherwise - */ - -LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path); - -/** - * @brief **bpf_link__unpin()** unpins the BPF link from a file - * in the BPFFS specified by a path. This decrements the links - * reference count. - * - * The file pinning the BPF link can also be unlinked by a different - * process in which case this function will return an error. - * - * @param prog BPF program to unpin - * @param path file path to the pin in a BPF file system - * @return 0, on success; negative error code, otherwise - */ -LIBBPF_API int bpf_link__unpin(struct bpf_link *link); -LIBBPF_API int bpf_link__update_program(struct bpf_link *link, - struct bpf_program *prog); -LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); -LIBBPF_API int bpf_link__detach(struct bpf_link *link); -LIBBPF_API int bpf_link__destroy(struct bpf_link *link); - -/** - * @brief **bpf_program__attach()** is a generic function for attaching - * a BPF program based on auto-detection of program type, attach type, - * and extra paremeters, where applicable. - * - * @param prog BPF program to attach - * @return Reference to the newly created BPF link; or NULL is returned on error, - * error code is stored in errno - * - * This is supported for: - * - kprobe/kretprobe (depends on SEC() definition) - * - uprobe/uretprobe (depends on SEC() definition) - * - tracepoint - * - raw tracepoint - * - tracing programs (typed raw TP/fentry/fexit/fmod_ret) - */ -LIBBPF_API struct bpf_link * -bpf_program__attach(const struct bpf_program *prog); - -struct bpf_perf_event_opts { - /* size of this struct, for forward/backward compatiblity */ - size_t sz; - /* custom user-provided value fetchable through bpf_get_attach_cookie() */ - __u64 bpf_cookie; -}; -#define bpf_perf_event_opts__last_field bpf_cookie - -LIBBPF_API struct bpf_link * -bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd); - -LIBBPF_API struct bpf_link * -bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, - const struct bpf_perf_event_opts *opts); - -struct bpf_kprobe_opts { - /* size of this struct, for forward/backward compatiblity */ - size_t sz; - /* custom user-provided value fetchable through bpf_get_attach_cookie() */ - __u64 bpf_cookie; - /* function's offset to install kprobe to */ - size_t offset; - /* kprobe is return probe */ - bool retprobe; - size_t :0; -}; -#define bpf_kprobe_opts__last_field retprobe - -LIBBPF_API struct bpf_link * -bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe, - const char *func_name); -LIBBPF_API struct bpf_link * -bpf_program__attach_kprobe_opts(const struct bpf_program *prog, - const char *func_name, - const struct bpf_kprobe_opts *opts); - -struct bpf_kprobe_multi_opts { - /* size of this struct, for forward/backward compatibility */ - size_t sz; - /* array of function symbols to attach */ - const char **syms; - /* array of function addresses to attach */ - const unsigned long *addrs; - /* array of user-provided values fetchable through bpf_get_attach_cookie */ - const __u64 *cookies; - /* number of elements in syms/addrs/cookies arrays */ - size_t cnt; - /* create return kprobes */ - bool retprobe; - size_t :0; -}; - -#define bpf_kprobe_multi_opts__last_field retprobe - -LIBBPF_API struct bpf_link * -bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, - const char *pattern, - const struct bpf_kprobe_multi_opts *opts); - -struct bpf_uprobe_opts { - /* size of this struct, for forward/backward compatiblity */ - size_t sz; - /* offset of kernel reference counted USDT semaphore, added in - * a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe") - */ - size_t ref_ctr_offset; - /* custom user-provided value fetchable through bpf_get_attach_cookie() */ - __u64 bpf_cookie; - /* uprobe is return probe, invoked at function return time */ - bool retprobe; - /* Function name to attach to. Could be an unqualified ("abc") or library-qualified - * "abc@LIBXYZ" name. To specify function entry, func_name should be set while - * func_offset argument to bpf_prog__attach_uprobe_opts() should be 0. To trace an - * offset within a function, specify func_name and use func_offset argument to specify - * offset within the function. Shared library functions must specify the shared library - * binary_path. - */ - const char *func_name; - size_t :0; -}; -#define bpf_uprobe_opts__last_field func_name - -/** - * @brief **bpf_program__attach_uprobe()** attaches a BPF program - * to the userspace function which is found by binary path and - * offset. You can optionally specify a particular proccess to attach - * to. You can also optionally attach the program to the function - * exit instead of entry. - * - * @param prog BPF program to attach - * @param retprobe Attach to function exit - * @param pid Process ID to attach the uprobe to, 0 for self (own process), - * -1 for all processes - * @param binary_path Path to binary that contains the function symbol - * @param func_offset Offset within the binary of the function symbol - * @return Reference to the newly created BPF link; or NULL is returned on error, - * error code is stored in errno - */ -LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, - pid_t pid, const char *binary_path, - size_t func_offset); - -/** - * @brief **bpf_program__attach_uprobe_opts()** is just like - * bpf_program__attach_uprobe() except with a options struct - * for various configurations. - * - * @param prog BPF program to attach - * @param pid Process ID to attach the uprobe to, 0 for self (own process), - * -1 for all processes - * @param binary_path Path to binary that contains the function symbol - * @param func_offset Offset within the binary of the function symbol - * @param opts Options for altering program attachment - * @return Reference to the newly created BPF link; or NULL is returned on error, - * error code is stored in errno - */ -LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, - const char *binary_path, size_t func_offset, - const struct bpf_uprobe_opts *opts); - -struct bpf_usdt_opts { - /* size of this struct, for forward/backward compatibility */ - size_t sz; - /* custom user-provided value accessible through usdt_cookie() */ - __u64 usdt_cookie; - size_t :0; -}; -#define bpf_usdt_opts__last_field usdt_cookie - -/** - * @brief **bpf_program__attach_usdt()** is just like - * bpf_program__attach_uprobe_opts() except it covers USDT (User-space - * Statically Defined Tracepoint) attachment, instead of attaching to - * user-space function entry or exit. - * - * @param prog BPF program to attach - * @param pid Process ID to attach the uprobe to, 0 for self (own process), - * -1 for all processes - * @param binary_path Path to binary that contains provided USDT probe - * @param usdt_provider USDT provider name - * @param usdt_name USDT probe name - * @param opts Options for altering program attachment - * @return Reference to the newly created BPF link; or NULL is returned on error, - * error code is stored in errno - */ -LIBBPF_API struct bpf_link * -bpf_program__attach_usdt(const struct bpf_program *prog, - pid_t pid, const char *binary_path, - const char *usdt_provider, const char *usdt_name, - const struct bpf_usdt_opts *opts); - -struct bpf_tracepoint_opts { - /* size of this struct, for forward/backward compatiblity */ - size_t sz; - /* custom user-provided value fetchable through bpf_get_attach_cookie() */ - __u64 bpf_cookie; -}; -#define bpf_tracepoint_opts__last_field bpf_cookie - -LIBBPF_API struct bpf_link * -bpf_program__attach_tracepoint(const struct bpf_program *prog, - const char *tp_category, - const char *tp_name); -LIBBPF_API struct bpf_link * -bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, - const char *tp_category, - const char *tp_name, - const struct bpf_tracepoint_opts *opts); - -LIBBPF_API struct bpf_link * -bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, - const char *tp_name); - -struct bpf_trace_opts { - /* size of this struct, for forward/backward compatibility */ - size_t sz; - /* custom user-provided value fetchable through bpf_get_attach_cookie() */ - __u64 cookie; -}; -#define bpf_trace_opts__last_field cookie - -LIBBPF_API struct bpf_link * -bpf_program__attach_trace(const struct bpf_program *prog); -LIBBPF_API struct bpf_link * -bpf_program__attach_trace_opts(const struct bpf_program *prog, const struct bpf_trace_opts *opts); - -LIBBPF_API struct bpf_link * -bpf_program__attach_lsm(const struct bpf_program *prog); -LIBBPF_API struct bpf_link * -bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd); -LIBBPF_API struct bpf_link * -bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd); -LIBBPF_API struct bpf_link * -bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex); -LIBBPF_API struct bpf_link * -bpf_program__attach_freplace(const struct bpf_program *prog, - int target_fd, const char *attach_func_name); - -struct bpf_map; - -LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); - -struct bpf_iter_attach_opts { - size_t sz; /* size of this struct for forward/backward compatibility */ - union bpf_iter_link_info *link_info; - __u32 link_info_len; -}; -#define bpf_iter_attach_opts__last_field link_info_len - -LIBBPF_API struct bpf_link * -bpf_program__attach_iter(const struct bpf_program *prog, - const struct bpf_iter_attach_opts *opts); - -/* - * 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); - -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insns() for getting bpf_program instructions") -LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, - bpf_program_prep_t prep); - -LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated") -LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); - -/* - * Adjust type of BPF program. Default is kprobe. - */ -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_lsm(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") -LIBBPF_API int bpf_program__set_sk_lookup(struct bpf_program *prog); - -LIBBPF_API enum bpf_prog_type bpf_program__type(const struct bpf_program *prog); - -/** - * @brief **bpf_program__set_type()** sets the program - * type of the passed BPF program. - * @param prog BPF program to set the program type for - * @param type program type to set the BPF map to have - * @return error code; or 0 if no error. An error occurs - * if the object is already loaded. - * - * This must be called before the BPF object is loaded, - * otherwise it has no effect and an error is returned. - */ -LIBBPF_API int bpf_program__set_type(struct bpf_program *prog, - enum bpf_prog_type type); - -LIBBPF_API enum bpf_attach_type -bpf_program__expected_attach_type(const struct bpf_program *prog); - -/** - * @brief **bpf_program__set_expected_attach_type()** sets the - * attach type of the passed BPF program. This is used for - * auto-detection of attachment when programs are loaded. - * @param prog BPF program to set the attach type for - * @param type attach type to set the BPF map to have - * @return error code; or 0 if no error. An error occurs - * if the object is already loaded. - * - * This must be called before the BPF object is loaded, - * otherwise it has no effect and an error is returned. - */ -LIBBPF_API int -bpf_program__set_expected_attach_type(struct bpf_program *prog, - enum bpf_attach_type type); - -LIBBPF_API __u32 bpf_program__flags(const struct bpf_program *prog); -LIBBPF_API int bpf_program__set_flags(struct bpf_program *prog, __u32 flags); - -/* Per-program log level and log buffer getters/setters. - * See bpf_object_open_opts comments regarding log_level and log_buf - * interactions. - */ -LIBBPF_API __u32 bpf_program__log_level(const struct bpf_program *prog); -LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level); -LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size); -LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size); - -/** - * @brief **bpf_program__set_attach_target()** sets BTF-based attach target - * for supported BPF program types: - * - BTF-aware raw tracepoints (tp_btf); - * - fentry/fexit/fmod_ret; - * - lsm; - * - freplace. - * @param prog BPF program to set the attach type for - * @param type attach type to set the BPF map to have - * @return error code; or 0 if no error occurred. - */ -LIBBPF_API int -bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, - const char *attach_func_name); - -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_lsm(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") -LIBBPF_API bool bpf_program__is_sk_lookup(const 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; -}; - -/** - * @brief **bpf_object__find_map_by_name()** returns BPF map of - * the given name, if it exists within the passed BPF object - * @param obj BPF object - * @param name name of the BPF map - * @return BPF map instance, if such map exists within the BPF object; - * or NULL otherwise. - */ -LIBBPF_API struct bpf_map * -bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); - -LIBBPF_API int -bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name); - -/* - * Get bpf_map through the offset of corresponding struct bpf_map_def - * in the BPF object file. - */ -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__find_map_by_name() instead") -struct bpf_map * -bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); - -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_map() instead") -struct bpf_map *bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); -LIBBPF_API struct bpf_map * -bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *map); - -#define bpf_object__for_each_map(pos, obj) \ - for ((pos) = bpf_object__next_map((obj), NULL); \ - (pos) != NULL; \ - (pos) = bpf_object__next_map((obj), (pos))) -#define bpf_map__for_each bpf_object__for_each_map - -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_map() instead") -struct bpf_map *bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); -LIBBPF_API struct bpf_map * -bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map); - -/** - * @brief **bpf_map__set_autocreate()** sets whether libbpf has to auto-create - * BPF map during BPF object load phase. - * @param map the BPF map instance - * @param autocreate whether to create BPF map during BPF object load - * @return 0 on success; -EBUSY if BPF object was already loaded - * - * **bpf_map__set_autocreate()** allows to opt-out from libbpf auto-creating - * BPF map. By default, libbpf will attempt to create every single BPF map - * defined in BPF object file using BPF_MAP_CREATE command of bpf() syscall - * and fill in map FD in BPF instructions. - * - * This API allows to opt-out of this process for specific map instance. This - * can be useful if host kernel doesn't support such BPF map type or used - * combination of flags and user application wants to avoid creating such - * a map in the first place. User is still responsible to make sure that their - * BPF-side code that expects to use such missing BPF map is recognized by BPF - * verifier as dead code, otherwise BPF verifier will reject such BPF program. - */ -LIBBPF_API int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate); -LIBBPF_API bool bpf_map__autocreate(const struct bpf_map *map); - -/** - * @brief **bpf_map__fd()** gets the file descriptor of the passed - * BPF map - * @param map the BPF map instance - * @return the file descriptor; or -EINVAL in case of an error - */ -LIBBPF_API int bpf_map__fd(const struct bpf_map *map); -LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); -/* get map definition */ -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use appropriate getters or setters instead") -const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); -/* get map name */ -LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); -/* get/set map type */ -LIBBPF_API enum bpf_map_type bpf_map__type(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type); -/* get/set map size (max_entries) */ -LIBBPF_API __u32 bpf_map__max_entries(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__set_max_entries() instead") -LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); -/* get/set map flags */ -LIBBPF_API __u32 bpf_map__map_flags(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags); -/* get/set map NUMA node */ -LIBBPF_API __u32 bpf_map__numa_node(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node); -/* get/set map key size */ -LIBBPF_API __u32 bpf_map__key_size(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_key_size(struct bpf_map *map, __u32 size); -/* get/set map value size */ -LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_value_size(struct bpf_map *map, __u32 size); -/* get map key/value BTF type IDs */ -LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); -LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); -/* get/set map if_index */ -LIBBPF_API __u32 bpf_map__ifindex(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); -/* get/set map map_extra flags */ -LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); - -typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); -LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") -LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, - bpf_map_clear_priv_t clear_priv); -LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") -LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, - const void *data, size_t size); -LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__type() instead") -LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); - -/** - * @brief **bpf_map__is_internal()** tells the caller whether or not the - * passed map is a special map created by libbpf automatically for things like - * global variables, __ksym externs, Kconfig values, etc - * @param map the bpf_map - * @return true, if the map is an internal map; false, otherwise - */ -LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); -LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); -LIBBPF_API const char *bpf_map__pin_path(const struct bpf_map *map); -LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map); -LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); -LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); - -LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); -LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); - -/** - * @brief **bpf_map__lookup_elem()** allows to lookup BPF map value - * corresponding to provided key. - * @param map BPF map to lookup element in - * @param key pointer to memory containing bytes of the key used for lookup - * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** - * @param value pointer to memory in which looked up value will be stored - * @param value_sz size in byte of value data memory; it has to match BPF map - * definition's **value_size**. For per-CPU BPF maps value size has to be - * a product of BPF map value size and number of possible CPUs in the system - * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for - * per-CPU values value size has to be aligned up to closest 8 bytes for - * alignment reasons, so expected size is: `round_up(value_size, 8) - * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation - * @return 0, on success; negative error, otherwise - * - * **bpf_map__lookup_elem()** is high-level equivalent of - * **bpf_map_lookup_elem()** API with added check for key and value size. - */ -LIBBPF_API int bpf_map__lookup_elem(const struct bpf_map *map, - const void *key, size_t key_sz, - void *value, size_t value_sz, __u64 flags); - -/** - * @brief **bpf_map__update_elem()** allows to insert or update value in BPF - * map that corresponds to provided key. - * @param map BPF map to insert to or update element in - * @param key pointer to memory containing bytes of the key - * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** - * @param value pointer to memory containing bytes of the value - * @param value_sz size in byte of value data memory; it has to match BPF map - * definition's **value_size**. For per-CPU BPF maps value size has to be - * a product of BPF map value size and number of possible CPUs in the system - * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for - * per-CPU values value size has to be aligned up to closest 8 bytes for - * alignment reasons, so expected size is: `round_up(value_size, 8) - * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation - * @return 0, on success; negative error, otherwise - * - * **bpf_map__update_elem()** is high-level equivalent of - * **bpf_map_update_elem()** API with added check for key and value size. - */ -LIBBPF_API int bpf_map__update_elem(const struct bpf_map *map, - const void *key, size_t key_sz, - const void *value, size_t value_sz, __u64 flags); - -/** - * @brief **bpf_map__delete_elem()** allows to delete element in BPF map that - * corresponds to provided key. - * @param map BPF map to delete element from - * @param key pointer to memory containing bytes of the key - * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** - * @flags extra flags passed to kernel for this operation - * @return 0, on success; negative error, otherwise - * - * **bpf_map__delete_elem()** is high-level equivalent of - * **bpf_map_delete_elem()** API with added check for key size. - */ -LIBBPF_API int bpf_map__delete_elem(const struct bpf_map *map, - const void *key, size_t key_sz, __u64 flags); - -/** - * @brief **bpf_map__lookup_and_delete_elem()** allows to lookup BPF map value - * corresponding to provided key and atomically delete it afterwards. - * @param map BPF map to lookup element in - * @param key pointer to memory containing bytes of the key used for lookup - * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** - * @param value pointer to memory in which looked up value will be stored - * @param value_sz size in byte of value data memory; it has to match BPF map - * definition's **value_size**. For per-CPU BPF maps value size has to be - * a product of BPF map value size and number of possible CPUs in the system - * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for - * per-CPU values value size has to be aligned up to closest 8 bytes for - * alignment reasons, so expected size is: `round_up(value_size, 8) - * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation - * @return 0, on success; negative error, otherwise - * - * **bpf_map__lookup_and_delete_elem()** is high-level equivalent of - * **bpf_map_lookup_and_delete_elem()** API with added check for key and value size. - */ -LIBBPF_API int bpf_map__lookup_and_delete_elem(const struct bpf_map *map, - const void *key, size_t key_sz, - void *value, size_t value_sz, __u64 flags); - -/** - * @brief **bpf_map__get_next_key()** allows to iterate BPF map keys by - * fetching next key that follows current key. - * @param map BPF map to fetch next key from - * @param cur_key pointer to memory containing bytes of current key or NULL to - * fetch the first key - * @param next_key pointer to memory to write next key into - * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** - * @return 0, on success; -ENOENT if **cur_key** is the last key in BPF map; - * negative error, otherwise - * - * **bpf_map__get_next_key()** is high-level equivalent of - * **bpf_map_get_next_key()** API with added check for key size. - */ -LIBBPF_API int bpf_map__get_next_key(const struct bpf_map *map, - const void *cur_key, void *next_key, size_t key_sz); - -/** - * @brief **libbpf_get_error()** extracts the error code from the passed - * pointer - * @param ptr pointer returned from libbpf API function - * @return error code; or 0 if no error occured - * - * Many libbpf API functions which return pointers have logic to encode error - * codes as pointers, and do not return NULL. Meaning **libbpf_get_error()** - * should be used on the return value from these functions immediately after - * calling the API function, with no intervening calls that could clobber the - * `errno` variable. Consult the individual functions documentation to verify - * if this logic applies should be used. - * - * For these API functions, if `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` - * is enabled, NULL is returned on error instead. - * - * If ptr is NULL, then errno should be already set by the failing - * API, because libbpf never returns NULL on success and it now always - * sets errno on error. - * - * Example usage: - * - * struct perf_buffer *pb; - * - * pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES, &opts); - * err = libbpf_get_error(pb); - * if (err) { - * pb = NULL; - * fprintf(stderr, "failed to open perf buffer: %d\n", err); - * goto cleanup; - * } - */ -LIBBPF_API 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 log_level; - int prog_flags; -}; - -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open() and bpf_object__load() instead") -LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, - struct bpf_object **pobj, int *prog_fd); -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open() and bpf_object__load() instead") -LIBBPF_API int bpf_prog_load_deprecated(const char *file, enum bpf_prog_type type, - struct bpf_object **pobj, int *prog_fd); - -/* XDP related API */ -struct xdp_link_info { - __u32 prog_id; - __u32 drv_prog_id; - __u32 hw_prog_id; - __u32 skb_prog_id; - __u8 attach_mode; -}; - -struct bpf_xdp_set_link_opts { - size_t sz; - int old_fd; - size_t :0; -}; -#define bpf_xdp_set_link_opts__last_field old_fd - -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") -LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") -LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, - const struct bpf_xdp_set_link_opts *opts); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query_id() instead") -LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); -LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query() instead") -LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, - size_t info_size, __u32 flags); - -struct bpf_xdp_attach_opts { - size_t sz; - int old_prog_fd; - size_t :0; -}; -#define bpf_xdp_attach_opts__last_field old_prog_fd - -struct bpf_xdp_query_opts { - size_t sz; - __u32 prog_id; /* output */ - __u32 drv_prog_id; /* output */ - __u32 hw_prog_id; /* output */ - __u32 skb_prog_id; /* output */ - __u8 attach_mode; /* output */ - size_t :0; -}; -#define bpf_xdp_query_opts__last_field attach_mode - -LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, - const struct bpf_xdp_attach_opts *opts); -LIBBPF_API int bpf_xdp_detach(int ifindex, __u32 flags, - const struct bpf_xdp_attach_opts *opts); -LIBBPF_API int bpf_xdp_query(int ifindex, int flags, struct bpf_xdp_query_opts *opts); -LIBBPF_API int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id); - -/* TC related API */ -enum bpf_tc_attach_point { - BPF_TC_INGRESS = 1 << 0, - BPF_TC_EGRESS = 1 << 1, - BPF_TC_CUSTOM = 1 << 2, -}; - -#define BPF_TC_PARENT(a, b) \ - ((((a) << 16) & 0xFFFF0000U) | ((b) & 0x0000FFFFU)) - -enum bpf_tc_flags { - BPF_TC_F_REPLACE = 1 << 0, -}; - -struct bpf_tc_hook { - size_t sz; - int ifindex; - enum bpf_tc_attach_point attach_point; - __u32 parent; - size_t :0; -}; -#define bpf_tc_hook__last_field parent - -struct bpf_tc_opts { - size_t sz; - int prog_fd; - __u32 flags; - __u32 prog_id; - __u32 handle; - __u32 priority; - size_t :0; -}; -#define bpf_tc_opts__last_field priority - -LIBBPF_API int bpf_tc_hook_create(struct bpf_tc_hook *hook); -LIBBPF_API int bpf_tc_hook_destroy(struct bpf_tc_hook *hook); -LIBBPF_API int bpf_tc_attach(const struct bpf_tc_hook *hook, - struct bpf_tc_opts *opts); -LIBBPF_API int bpf_tc_detach(const struct bpf_tc_hook *hook, - const struct bpf_tc_opts *opts); -LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook, - struct bpf_tc_opts *opts); - -/* Ring buffer APIs */ -struct ring_buffer; - -typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size); - -struct ring_buffer_opts { - size_t sz; /* size of this struct, for forward/backward compatiblity */ -}; - -#define ring_buffer_opts__last_field sz - -LIBBPF_API struct ring_buffer * -ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, - const struct ring_buffer_opts *opts); -LIBBPF_API void ring_buffer__free(struct ring_buffer *rb); -LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd, - ring_buffer_sample_fn sample_cb, void *ctx); -LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms); -LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb); -LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb); - -/* Perf buffer APIs */ -struct perf_buffer; - -typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu, - void *data, __u32 size); -typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); - -/* common use perf buffer options */ -struct perf_buffer_opts { - union { - size_t sz; - struct { /* DEPRECATED: will be removed in v1.0 */ - /* if specified, sample_cb is called for each sample */ - perf_buffer_sample_fn sample_cb; - /* if specified, lost_cb is called for each batch of lost samples */ - perf_buffer_lost_fn lost_cb; - /* ctx is provided to sample_cb and lost_cb */ - void *ctx; - }; - }; -}; -#define perf_buffer_opts__last_field sz - -/** - * @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified - * BPF_PERF_EVENT_ARRAY map - * @param map_fd FD of BPF_PERF_EVENT_ARRAY BPF map that will be used by BPF - * code to send data over to user-space - * @param page_cnt number of memory pages allocated for each per-CPU buffer - * @param sample_cb function called on each received data record - * @param lost_cb function called when record loss has occurred - * @param ctx user-provided extra context passed into *sample_cb* and *lost_cb* - * @return a new instance of struct perf_buffer on success, NULL on error with - * *errno* containing an error code - */ -LIBBPF_API struct perf_buffer * -perf_buffer__new(int map_fd, size_t page_cnt, - perf_buffer_sample_fn sample_cb, perf_buffer_lost_fn lost_cb, void *ctx, - const struct perf_buffer_opts *opts); - -LIBBPF_API struct perf_buffer * -perf_buffer__new_v0_6_0(int map_fd, size_t page_cnt, - perf_buffer_sample_fn sample_cb, perf_buffer_lost_fn lost_cb, void *ctx, - const struct perf_buffer_opts *opts); - -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use new variant of perf_buffer__new() instead") -struct perf_buffer *perf_buffer__new_deprecated(int map_fd, size_t page_cnt, - const struct perf_buffer_opts *opts); - -#define perf_buffer__new(...) ___libbpf_overload(___perf_buffer_new, __VA_ARGS__) -#define ___perf_buffer_new6(map_fd, page_cnt, sample_cb, lost_cb, ctx, opts) \ - perf_buffer__new(map_fd, page_cnt, sample_cb, lost_cb, ctx, opts) -#define ___perf_buffer_new3(map_fd, page_cnt, opts) \ - perf_buffer__new_deprecated(map_fd, page_cnt, opts) - -enum bpf_perf_event_ret { - LIBBPF_PERF_EVENT_DONE = 0, - LIBBPF_PERF_EVENT_ERROR = -1, - LIBBPF_PERF_EVENT_CONT = -2, -}; - -struct perf_event_header; - -typedef enum bpf_perf_event_ret -(*perf_buffer_event_fn)(void *ctx, int cpu, struct perf_event_header *event); - -/* raw perf buffer options, giving most power and control */ -struct perf_buffer_raw_opts { - union { - struct { - size_t sz; - long :0; - long :0; - }; - struct { /* DEPRECATED: will be removed in v1.0 */ - /* perf event attrs passed directly into perf_event_open() */ - struct perf_event_attr *attr; - /* raw event callback */ - perf_buffer_event_fn event_cb; - /* ctx is provided to event_cb */ - void *ctx; - }; - }; - /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of - * max_entries of given PERF_EVENT_ARRAY map) - */ - int cpu_cnt; - /* if cpu_cnt > 0, cpus is an array of CPUs to open ring buffers on */ - int *cpus; - /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */ - int *map_keys; -}; -#define perf_buffer_raw_opts__last_field map_keys - -LIBBPF_API struct perf_buffer * -perf_buffer__new_raw(int map_fd, size_t page_cnt, struct perf_event_attr *attr, - perf_buffer_event_fn event_cb, void *ctx, - const struct perf_buffer_raw_opts *opts); - -LIBBPF_API struct perf_buffer * -perf_buffer__new_raw_v0_6_0(int map_fd, size_t page_cnt, struct perf_event_attr *attr, - perf_buffer_event_fn event_cb, void *ctx, - const struct perf_buffer_raw_opts *opts); - -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use new variant of perf_buffer__new_raw() instead") -struct perf_buffer *perf_buffer__new_raw_deprecated(int map_fd, size_t page_cnt, - const struct perf_buffer_raw_opts *opts); - -#define perf_buffer__new_raw(...) ___libbpf_overload(___perf_buffer_new_raw, __VA_ARGS__) -#define ___perf_buffer_new_raw6(map_fd, page_cnt, attr, event_cb, ctx, opts) \ - perf_buffer__new_raw(map_fd, page_cnt, attr, event_cb, ctx, opts) -#define ___perf_buffer_new_raw3(map_fd, page_cnt, opts) \ - perf_buffer__new_raw_deprecated(map_fd, page_cnt, opts) - -LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); -LIBBPF_API int perf_buffer__epoll_fd(const struct perf_buffer *pb); -LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms); -LIBBPF_API int perf_buffer__consume(struct perf_buffer *pb); -LIBBPF_API int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx); -LIBBPF_API size_t perf_buffer__buffer_cnt(const struct perf_buffer *pb); -LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx); - -typedef enum bpf_perf_event_ret - (*bpf_perf_event_print_t)(struct perf_event_header *hdr, - void *private_data); -LIBBPF_DEPRECATED_SINCE(0, 8, "use perf_buffer__poll() or perf_buffer__consume() instead") -LIBBPF_API enum bpf_perf_event_ret -bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, - void **copy_mem, size_t *copy_size, - bpf_perf_event_print_t fn, void *private_data); - -struct bpf_prog_linfo; -struct bpf_prog_info; - -LIBBPF_API void bpf_prog_linfo__free(struct bpf_prog_linfo *prog_linfo); -LIBBPF_API struct bpf_prog_linfo * -bpf_prog_linfo__new(const struct bpf_prog_info *info); -LIBBPF_API const struct bpf_line_info * -bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo, - __u64 addr, __u32 func_idx, __u32 nr_skip); -LIBBPF_API const struct bpf_line_info * -bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo, - __u32 insn_off, __u32 nr_skip); - -/* - * Probe for supported system features - * - * Note that running many of these probes in a short amount of time can cause - * the kernel to reach the maximal size of lockable memory allowed for the - * user, causing subsequent probes to fail. In this case, the caller may want - * to adjust that limit with setrlimit(). - */ -LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_prog_type() instead") -LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex); -LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_map_type() instead") -LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex); -LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_helper() instead") -LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex); -LIBBPF_DEPRECATED_SINCE(0, 8, "implement your own or use bpftool for feature detection") -LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex); - -/** - * @brief **libbpf_probe_bpf_prog_type()** detects if host kernel supports - * BPF programs of a given type. - * @param prog_type BPF program type to detect kernel support for - * @param opts reserved for future extensibility, should be NULL - * @return 1, if given program type is supported; 0, if given program type is - * not supported; negative error code if feature detection failed or can't be - * performed - * - * Make sure the process has required set of CAP_* permissions (or runs as - * root) when performing feature checking. - */ -LIBBPF_API int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts); -/** - * @brief **libbpf_probe_bpf_map_type()** detects if host kernel supports - * BPF maps of a given type. - * @param map_type BPF map type to detect kernel support for - * @param opts reserved for future extensibility, should be NULL - * @return 1, if given map type is supported; 0, if given map type is - * not supported; negative error code if feature detection failed or can't be - * performed - * - * Make sure the process has required set of CAP_* permissions (or runs as - * root) when performing feature checking. - */ -LIBBPF_API int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts); -/** - * @brief **libbpf_probe_bpf_helper()** detects if host kernel supports the - * use of a given BPF helper from specified BPF program type. - * @param prog_type BPF program type used to check the support of BPF helper - * @param helper_id BPF helper ID (enum bpf_func_id) to check support for - * @param opts reserved for future extensibility, should be NULL - * @return 1, if given combination of program type and helper is supported; 0, - * if the combination is not supported; negative error code if feature - * detection for provided input arguments failed or can't be performed - * - * Make sure the process has required set of CAP_* permissions (or runs as - * root) when performing feature checking. - */ -LIBBPF_API int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, - enum bpf_func_id helper_id, const void *opts); - -/* - * Get bpf_prog_info in continuous memory - * - * struct bpf_prog_info has multiple arrays. The user has option to choose - * arrays to fetch from kernel. The following APIs provide an uniform way to - * fetch these data. All arrays in bpf_prog_info are stored in a single - * continuous memory region. This makes it easy to store the info in a - * file. - * - * Before writing bpf_prog_info_linear to files, it is necessary to - * translate pointers in bpf_prog_info to offsets. Helper functions - * bpf_program__bpil_addr_to_offs() and bpf_program__bpil_offs_to_addr() - * are introduced to switch between pointers and offsets. - * - * Examples: - * # To fetch map_ids and prog_tags: - * __u64 arrays = (1UL << BPF_PROG_INFO_MAP_IDS) | - * (1UL << BPF_PROG_INFO_PROG_TAGS); - * struct bpf_prog_info_linear *info_linear = - * bpf_program__get_prog_info_linear(fd, arrays); - * - * # To save data in file - * bpf_program__bpil_addr_to_offs(info_linear); - * write(f, info_linear, sizeof(*info_linear) + info_linear->data_len); - * - * # To read data from file - * read(f, info_linear, ); - * bpf_program__bpil_offs_to_addr(info_linear); - */ -enum bpf_prog_info_array { - BPF_PROG_INFO_FIRST_ARRAY = 0, - BPF_PROG_INFO_JITED_INSNS = 0, - BPF_PROG_INFO_XLATED_INSNS, - BPF_PROG_INFO_MAP_IDS, - BPF_PROG_INFO_JITED_KSYMS, - BPF_PROG_INFO_JITED_FUNC_LENS, - BPF_PROG_INFO_FUNC_INFO, - BPF_PROG_INFO_LINE_INFO, - BPF_PROG_INFO_JITED_LINE_INFO, - BPF_PROG_INFO_PROG_TAGS, - BPF_PROG_INFO_LAST_ARRAY, -}; - -struct bpf_prog_info_linear { - /* size of struct bpf_prog_info, when the tool is compiled */ - __u32 info_len; - /* total bytes allocated for data, round up to 8 bytes */ - __u32 data_len; - /* which arrays are included in data */ - __u64 arrays; - struct bpf_prog_info info; - __u8 data[]; -}; - -LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper") -LIBBPF_API struct bpf_prog_info_linear * -bpf_program__get_prog_info_linear(int fd, __u64 arrays); - -LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper") -LIBBPF_API void -bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); - -LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper") -LIBBPF_API void -bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); - -/** - * @brief **libbpf_num_possible_cpus()** is a helper function to get the - * number of possible CPUs that the host kernel supports and expects. - * @return number of possible CPUs; or error code on failure - * - * Example usage: - * - * int ncpus = libbpf_num_possible_cpus(); - * if (ncpus < 0) { - * // error handling - * } - * long values[ncpus]; - * bpf_map_lookup_elem(per_cpu_map_fd, key, values); - */ -LIBBPF_API int libbpf_num_possible_cpus(void); - -struct bpf_map_skeleton { - const char *name; - struct bpf_map **map; - void **mmaped; -}; - -struct bpf_prog_skeleton { - const char *name; - struct bpf_program **prog; - struct bpf_link **link; -}; - -struct bpf_object_skeleton { - size_t sz; /* size of this struct, for forward/backward compatibility */ - - const char *name; - const void *data; - size_t data_sz; - - struct bpf_object **obj; - - int map_cnt; - int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ - struct bpf_map_skeleton *maps; - - int prog_cnt; - int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ - struct bpf_prog_skeleton *progs; -}; - -LIBBPF_API int -bpf_object__open_skeleton(struct bpf_object_skeleton *s, - const struct bpf_object_open_opts *opts); -LIBBPF_API int bpf_object__load_skeleton(struct bpf_object_skeleton *s); -LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); -LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); -LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); - -struct bpf_var_skeleton { - const char *name; - struct bpf_map **map; - void **addr; -}; - -struct bpf_object_subskeleton { - size_t sz; /* size of this struct, for forward/backward compatibility */ - - const struct bpf_object *obj; - - int map_cnt; - int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ - struct bpf_map_skeleton *maps; - - int prog_cnt; - int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ - struct bpf_prog_skeleton *progs; - - int var_cnt; - int var_skel_sz; /* sizeof(struct bpf_var_skeleton) */ - struct bpf_var_skeleton *vars; -}; - -LIBBPF_API int -bpf_object__open_subskeleton(struct bpf_object_subskeleton *s); -LIBBPF_API void -bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s); - -struct gen_loader_opts { - size_t sz; /* size of this struct, for forward/backward compatiblity */ - const char *data; - const char *insns; - __u32 data_sz; - __u32 insns_sz; -}; - -#define gen_loader_opts__last_field insns_sz -LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj, - struct gen_loader_opts *opts); - -enum libbpf_tristate { - TRI_NO = 0, - TRI_YES = 1, - TRI_MODULE = 2, -}; - -struct bpf_linker_opts { - /* size of this struct, for forward/backward compatiblity */ - size_t sz; -}; -#define bpf_linker_opts__last_field sz - -struct bpf_linker_file_opts { - /* size of this struct, for forward/backward compatiblity */ - size_t sz; -}; -#define bpf_linker_file_opts__last_field sz - -struct bpf_linker; - -LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts); -LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, - const char *filename, - const struct bpf_linker_file_opts *opts); -LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); -LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); - -/* - * Custom handling of BPF program's SEC() definitions - */ - -struct bpf_prog_load_opts; /* defined in bpf.h */ - -/* Called during bpf_object__open() for each recognized BPF program. Callback - * can use various bpf_program__set_*() setters to adjust whatever properties - * are necessary. - */ -typedef int (*libbpf_prog_setup_fn_t)(struct bpf_program *prog, long cookie); - -/* Called right before libbpf performs bpf_prog_load() to load BPF program - * into the kernel. Callback can adjust opts as necessary. - */ -typedef int (*libbpf_prog_prepare_load_fn_t)(struct bpf_program *prog, - struct bpf_prog_load_opts *opts, long cookie); - -/* Called during skeleton attach or through bpf_program__attach(). If - * auto-attach is not supported, callback should return 0 and set link to - * NULL (it's not considered an error during skeleton attach, but it will be - * an error for bpf_program__attach() calls). On error, error should be - * returned directly and link set to NULL. On success, return 0 and set link - * to a valid struct bpf_link. - */ -typedef int (*libbpf_prog_attach_fn_t)(const struct bpf_program *prog, long cookie, - struct bpf_link **link); - -struct libbpf_prog_handler_opts { - /* size of this struct, for forward/backward compatiblity */ - size_t sz; - /* User-provided value that is passed to prog_setup_fn, - * prog_prepare_load_fn, and prog_attach_fn callbacks. Allows user to - * register one set of callbacks for multiple SEC() definitions and - * still be able to distinguish them, if necessary. For example, - * libbpf itself is using this to pass necessary flags (e.g., - * sleepable flag) to a common internal SEC() handler. - */ - long cookie; - /* BPF program initialization callback (see libbpf_prog_setup_fn_t). - * Callback is optional, pass NULL if it's not necessary. - */ - libbpf_prog_setup_fn_t prog_setup_fn; - /* BPF program loading callback (see libbpf_prog_prepare_load_fn_t). - * Callback is optional, pass NULL if it's not necessary. - */ - libbpf_prog_prepare_load_fn_t prog_prepare_load_fn; - /* BPF program attach callback (see libbpf_prog_attach_fn_t). - * Callback is optional, pass NULL if it's not necessary. - */ - libbpf_prog_attach_fn_t prog_attach_fn; -}; -#define libbpf_prog_handler_opts__last_field prog_attach_fn - -/** - * @brief **libbpf_register_prog_handler()** registers a custom BPF program - * SEC() handler. - * @param sec section prefix for which custom handler is registered - * @param prog_type BPF program type associated with specified section - * @param exp_attach_type Expected BPF attach type associated with specified section - * @param opts optional cookie, callbacks, and other extra options - * @return Non-negative handler ID is returned on success. This handler ID has - * to be passed to *libbpf_unregister_prog_handler()* to unregister such - * custom handler. Negative error code is returned on error. - * - * *sec* defines which SEC() definitions are handled by this custom handler - * registration. *sec* can have few different forms: - * - if *sec* is just a plain string (e.g., "abc"), it will match only - * SEC("abc"). If BPF program specifies SEC("abc/whatever") it will result - * in an error; - * - if *sec* is of the form "abc/", proper SEC() form is - * SEC("abc/something"), where acceptable "something" should be checked by - * *prog_init_fn* callback, if there are additional restrictions; - * - if *sec* is of the form "abc+", it will successfully match both - * SEC("abc") and SEC("abc/whatever") forms; - * - if *sec* is NULL, custom handler is registered for any BPF program that - * doesn't match any of the registered (custom or libbpf's own) SEC() - * handlers. There could be only one such generic custom handler registered - * at any given time. - * - * All custom handlers (except the one with *sec* == NULL) are processed - * before libbpf's own SEC() handlers. It is allowed to "override" libbpf's - * SEC() handlers by registering custom ones for the same section prefix - * (i.e., it's possible to have custom SEC("perf_event/LLC-load-misses") - * handler). - * - * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), - * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs - * to ensure synchronization if there is a risk of running this API from - * multiple threads simultaneously. - */ -LIBBPF_API int libbpf_register_prog_handler(const char *sec, - enum bpf_prog_type prog_type, - enum bpf_attach_type exp_attach_type, - const struct libbpf_prog_handler_opts *opts); -/** - * @brief *libbpf_unregister_prog_handler()* unregisters previously registered - * custom BPF program SEC() handler. - * @param handler_id handler ID returned by *libbpf_register_prog_handler()* - * after successful registration - * @return 0 on success, negative error code if handler isn't found - * - * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), - * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs - * to ensure synchronization if there is a risk of running this API from - * multiple threads simultaneously. - */ -LIBBPF_API int libbpf_unregister_prog_handler(int handler_id); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* __LIBBPF_LIBBPF_H */ diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf_common.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf_common.h deleted file mode 100644 index 000e37798ff2c4a299882b6f0cdbb857d9598892..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf_common.h +++ /dev/null @@ -1,83 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ - -/* - * Common user-facing libbpf helpers. - * - * Copyright (c) 2019 Facebook - */ - -#ifndef __LIBBPF_LIBBPF_COMMON_H -#define __LIBBPF_LIBBPF_COMMON_H - -#include -#include "libbpf_version.h" - -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - -#define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg))) - -/* Mark a symbol as deprecated when libbpf version is >= {major}.{minor} */ -#define LIBBPF_DEPRECATED_SINCE(major, minor, msg) \ - __LIBBPF_MARK_DEPRECATED_ ## major ## _ ## minor \ - (LIBBPF_DEPRECATED("libbpf v" # major "." # minor "+: " msg)) - -#define __LIBBPF_CURRENT_VERSION_GEQ(major, minor) \ - (LIBBPF_MAJOR_VERSION > (major) || \ - (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor))) - -/* Add checks for other versions below when planning deprecation of API symbols - * with the LIBBPF_DEPRECATED_SINCE macro. - */ -#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6) -#define __LIBBPF_MARK_DEPRECATED_0_6(X) X -#else -#define __LIBBPF_MARK_DEPRECATED_0_6(X) -#endif -#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7) -#define __LIBBPF_MARK_DEPRECATED_0_7(X) X -#else -#define __LIBBPF_MARK_DEPRECATED_0_7(X) -#endif -#if __LIBBPF_CURRENT_VERSION_GEQ(0, 8) -#define __LIBBPF_MARK_DEPRECATED_0_8(X) X -#else -#define __LIBBPF_MARK_DEPRECATED_0_8(X) -#endif - -/* This set of internal macros allows to do "function overloading" based on - * number of arguments provided by used in backwards-compatible way during the - * transition to libbpf 1.0 - * It's ugly but necessary evil that will be cleaned up when we get to 1.0. - * See bpf_prog_load() overload for example. - */ -#define ___libbpf_cat(A, B) A ## B -#define ___libbpf_select(NAME, NUM) ___libbpf_cat(NAME, NUM) -#define ___libbpf_nth(_1, _2, _3, _4, _5, _6, N, ...) N -#define ___libbpf_cnt(...) ___libbpf_nth(__VA_ARGS__, 6, 5, 4, 3, 2, 1) -#define ___libbpf_overload(NAME, ...) ___libbpf_select(NAME, ___libbpf_cnt(__VA_ARGS__))(__VA_ARGS__) - -/* Helper macro to declare and initialize libbpf options struct - * - * This dance with uninitialized declaration, followed by memset to zero, - * followed by assignment using compound literal syntax is done to preserve - * ability to use a nice struct field initialization syntax and **hopefully** - * have all the padding bytes initialized to zero. It's not guaranteed though, - * when copying literal, that compiler won't copy garbage in literal's padding - * bytes, but that's the best way I've found and it seems to work in practice. - * - * Macro declares opts struct of given type and name, zero-initializes, - * including any extra padding, it with memset() and then assigns initial - * values provided by users in struct initializer-syntax as varargs. - */ -#define LIBBPF_OPTS(TYPE, NAME, ...) \ - struct TYPE NAME = ({ \ - memset(&NAME, 0, sizeof(struct TYPE)); \ - (struct TYPE) { \ - .sz = sizeof(struct TYPE), \ - __VA_ARGS__ \ - }; \ - }) - -#endif /* __LIBBPF_LIBBPF_COMMON_H */ diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf_legacy.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf_legacy.h deleted file mode 100644 index d7bcbd01f66fae30f2236d411a183c32b7f18cf0..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf_legacy.h +++ /dev/null @@ -1,114 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ - -/* - * Libbpf legacy APIs (either discouraged or deprecated, as mentioned in [0]) - * - * [0] https://docs.google.com/document/d/1UyjTZuPFWiPFyKk1tV5an11_iaRuec6U-ZESZ54nNTY - * - * Copyright (C) 2021 Facebook - */ -#ifndef __LIBBPF_LEGACY_BPF_H -#define __LIBBPF_LEGACY_BPF_H - -#include -#include -#include -#include -#include "libbpf_common.h" - -#ifdef __cplusplus -extern "C" { -#endif - -enum libbpf_strict_mode { - /* Turn on all supported strict features of libbpf to simulate libbpf - * v1.0 behavior. - * This will be the default behavior in libbpf v1.0. - */ - LIBBPF_STRICT_ALL = 0xffffffff, - - /* - * Disable any libbpf 1.0 behaviors. This is the default before libbpf - * v1.0. It won't be supported anymore in v1.0, please update your - * code so that it handles LIBBPF_STRICT_ALL mode before libbpf v1.0. - */ - LIBBPF_STRICT_NONE = 0x00, - /* - * Return NULL pointers on error, not ERR_PTR(err). - * Additionally, libbpf also always sets errno to corresponding Exx - * (positive) error code. - */ - LIBBPF_STRICT_CLEAN_PTRS = 0x01, - /* - * Return actual error codes from low-level APIs directly, not just -1. - * Additionally, libbpf also always sets errno to corresponding Exx - * (positive) error code. - */ - LIBBPF_STRICT_DIRECT_ERRS = 0x02, - /* - * Enforce strict BPF program section (SEC()) names. - * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were - * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become - * unrecognized by libbpf and would have to be just SEC("xdp") and - * SEC("xdp") and SEC("perf_event"). - * - * Note, in this mode the program pin path will be based on the - * function name instead of section name. - * - * Additionally, routines in the .text section are always considered - * sub-programs. Legacy behavior allows for a single routine in .text - * to be a program. - */ - LIBBPF_STRICT_SEC_NAME = 0x04, - /* - * Disable the global 'bpf_objects_list'. Maintaining this list adds - * a race condition to bpf_object__open() and bpf_object__close(). - * Clients can maintain it on their own if it is valuable for them. - */ - LIBBPF_STRICT_NO_OBJECT_LIST = 0x08, - /* - * Automatically bump RLIMIT_MEMLOCK using setrlimit() before the - * first BPF program or map creation operation. This is done only if - * kernel is too old to support memcg-based memory accounting for BPF - * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY, - * but it can be overriden with libbpf_set_memlock_rlim_max() API. - * Note that libbpf_set_memlock_rlim_max() needs to be called before - * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load() - * operation. - */ - LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10, - /* - * Error out on any SEC("maps") map definition, which are deprecated - * in favor of BTF-defined map definitions in SEC(".maps"). - */ - LIBBPF_STRICT_MAP_DEFINITIONS = 0x20, - - __LIBBPF_STRICT_LAST, -}; - -LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); - -#define DECLARE_LIBBPF_OPTS LIBBPF_OPTS - -/* "Discouraged" APIs which don't follow consistent libbpf naming patterns. - * They are normally a trivial aliases or wrappers for proper APIs and are - * left to minimize unnecessary disruption for users of libbpf. But they - * shouldn't be used going forward. - */ - -struct bpf_program; -struct bpf_map; -struct btf; -struct btf_ext; - -LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); -LIBBPF_API enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); -LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); -LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); -LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* __LIBBPF_LEGACY_BPF_H */ diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf_version.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf_version.h deleted file mode 100644 index 61f2039404b6fce9bb89526505f7a9c57f5929a7..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/libbpf_version.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -/* Copyright (C) 2021 Facebook */ -#ifndef __LIBBPF_VERSION_H -#define __LIBBPF_VERSION_H - -#define LIBBPF_MAJOR_VERSION 0 -#define LIBBPF_MINOR_VERSION 8 - -#endif /* __LIBBPF_VERSION_H */ diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/skel_internal.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/skel_internal.h deleted file mode 100644 index bd6f4505e7b1e5adfa1bcdf992a8db9cf2286441..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/skel_internal.h +++ /dev/null @@ -1,349 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -/* Copyright (c) 2021 Facebook */ -#ifndef __SKEL_INTERNAL_H -#define __SKEL_INTERNAL_H - -#ifdef __KERNEL__ -#include -#include -#include -#include -#include -#else -#include -#include -#include -#include -#include "bpf.h" -#endif - -#ifndef __NR_bpf -# if defined(__mips__) && defined(_ABIO32) -# define __NR_bpf 4355 -# elif defined(__mips__) && defined(_ABIN32) -# define __NR_bpf 6319 -# elif defined(__mips__) && defined(_ABI64) -# define __NR_bpf 5315 -# endif -#endif - -/* This file is a base header for auto-generated *.lskel.h files. - * Its contents will change and may become part of auto-generation in the future. - * - * The layout of bpf_[map|prog]_desc and bpf_loader_ctx is feature dependent - * and will change from one version of libbpf to another and features - * requested during loader program generation. - */ -struct bpf_map_desc { - /* output of the loader prog */ - int map_fd; - /* input for the loader prog */ - __u32 max_entries; - __aligned_u64 initial_value; -}; -struct bpf_prog_desc { - int prog_fd; -}; - -enum { - BPF_SKEL_KERNEL = (1ULL << 0), -}; - -struct bpf_loader_ctx { - __u32 sz; - __u32 flags; - __u32 log_level; - __u32 log_size; - __u64 log_buf; -}; - -struct bpf_load_and_run_opts { - struct bpf_loader_ctx *ctx; - const void *data; - const void *insns; - __u32 data_sz; - __u32 insns_sz; - const char *errstr; -}; - -long bpf_sys_bpf(__u32 cmd, void *attr, __u32 attr_size); - -static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, - unsigned int size) -{ -#ifdef __KERNEL__ - return bpf_sys_bpf(cmd, attr, size); -#else - return syscall(__NR_bpf, cmd, attr, size); -#endif -} - -#ifdef __KERNEL__ -static inline int close(int fd) -{ - return close_fd(fd); -} - -static inline void *skel_alloc(size_t size) -{ - struct bpf_loader_ctx *ctx = kzalloc(size, GFP_KERNEL); - - if (!ctx) - return NULL; - ctx->flags |= BPF_SKEL_KERNEL; - return ctx; -} - -static inline void skel_free(const void *p) -{ - kfree(p); -} - -/* skel->bss/rodata maps are populated the following way: - * - * For kernel use: - * skel_prep_map_data() allocates kernel memory that kernel module can directly access. - * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value. - * The loader program will perform probe_read_kernel() from maps.rodata.initial_value. - * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and - * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree - * is not nessary. - * - * For user space: - * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly. - * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value. - * The loader program will perform copy_from_user() from maps.rodata.initial_value. - * skel_finalize_map_data() remaps bpf array map value from the kernel memory into - * skel->rodata address. - * - * The "bpftool gen skeleton -L" command generates lskel.h that is suitable for - * both kernel and user space. The generated loader program does - * either bpf_probe_read_kernel() or bpf_copy_from_user() from initial_value - * depending on bpf_loader_ctx->flags. - */ -static inline void skel_free_map_data(void *p, __u64 addr, size_t sz) -{ - if (addr != ~0ULL) - kvfree(p); - /* When addr == ~0ULL the 'p' points to - * ((struct bpf_array *)map)->value. See skel_finalize_map_data. - */ -} - -static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz) -{ - void *addr; - - addr = kvmalloc(val_sz, GFP_KERNEL); - if (!addr) - return NULL; - memcpy(addr, val, val_sz); - return addr; -} - -static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd) -{ - struct bpf_map *map; - void *addr = NULL; - - kvfree((void *) (long) *init_val); - *init_val = ~0ULL; - - /* At this point bpf_load_and_run() finished without error and - * 'fd' is a valid bpf map FD. All sanity checks below should succeed. - */ - map = bpf_map_get(fd); - if (IS_ERR(map)) - return NULL; - if (map->map_type != BPF_MAP_TYPE_ARRAY) - goto out; - addr = ((struct bpf_array *)map)->value; - /* the addr stays valid, since FD is not closed */ -out: - bpf_map_put(map); - return addr; -} - -#else - -static inline void *skel_alloc(size_t size) -{ - return calloc(1, size); -} - -static inline void skel_free(void *p) -{ - free(p); -} - -static inline void skel_free_map_data(void *p, __u64 addr, size_t sz) -{ - munmap(p, sz); -} - -static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz) -{ - void *addr; - - addr = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_ANONYMOUS, -1, 0); - if (addr == (void *) -1) - return NULL; - memcpy(addr, val, val_sz); - return addr; -} - -static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd) -{ - void *addr; - - addr = mmap((void *) (long) *init_val, mmap_sz, flags, MAP_SHARED | MAP_FIXED, fd, 0); - if (addr == (void *) -1) - return NULL; - return addr; -} -#endif - -static inline int skel_closenz(int fd) -{ - if (fd > 0) - return close(fd); - return -EINVAL; -} - -#ifndef offsetofend -#define offsetofend(TYPE, MEMBER) \ - (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) -#endif - -static inline int skel_map_create(enum bpf_map_type map_type, - const char *map_name, - __u32 key_size, - __u32 value_size, - __u32 max_entries) -{ - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); - union bpf_attr attr; - - memset(&attr, 0, attr_sz); - - attr.map_type = map_type; - strncpy(attr.map_name, map_name, sizeof(attr.map_name)); - attr.key_size = key_size; - attr.value_size = value_size; - attr.max_entries = max_entries; - - return skel_sys_bpf(BPF_MAP_CREATE, &attr, attr_sz); -} - -static inline int skel_map_update_elem(int fd, const void *key, - const void *value, __u64 flags) -{ - const size_t attr_sz = offsetofend(union bpf_attr, flags); - union bpf_attr attr; - - memset(&attr, 0, attr_sz); - attr.map_fd = fd; - attr.key = (long) key; - attr.value = (long) value; - attr.flags = flags; - - return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz); -} - -static inline int skel_raw_tracepoint_open(const char *name, int prog_fd) -{ - const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd); - union bpf_attr attr; - - memset(&attr, 0, attr_sz); - attr.raw_tracepoint.name = (long) name; - attr.raw_tracepoint.prog_fd = prog_fd; - - return skel_sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); -} - -static inline int skel_link_create(int prog_fd, int target_fd, - enum bpf_attach_type attach_type) -{ - const size_t attr_sz = offsetofend(union bpf_attr, link_create.iter_info_len); - union bpf_attr attr; - - memset(&attr, 0, attr_sz); - attr.link_create.prog_fd = prog_fd; - attr.link_create.target_fd = target_fd; - attr.link_create.attach_type = attach_type; - - return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz); -} - -#ifdef __KERNEL__ -#define set_err -#else -#define set_err err = -errno -#endif - -static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) -{ - int map_fd = -1, prog_fd = -1, key = 0, err; - union bpf_attr attr; - - err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1); - if (map_fd < 0) { - opts->errstr = "failed to create loader map"; - set_err; - goto out; - } - - err = skel_map_update_elem(map_fd, &key, opts->data, 0); - if (err < 0) { - opts->errstr = "failed to update loader map"; - set_err; - goto out; - } - - memset(&attr, 0, sizeof(attr)); - attr.prog_type = BPF_PROG_TYPE_SYSCALL; - attr.insns = (long) opts->insns; - attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); - attr.license = (long) "Dual BSD/GPL"; - memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog")); - attr.fd_array = (long) &map_fd; - attr.log_level = opts->ctx->log_level; - attr.log_size = opts->ctx->log_size; - attr.log_buf = opts->ctx->log_buf; - attr.prog_flags = BPF_F_SLEEPABLE; - err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); - if (prog_fd < 0) { - opts->errstr = "failed to load loader prog"; - set_err; - goto out; - } - - memset(&attr, 0, sizeof(attr)); - attr.test.prog_fd = prog_fd; - attr.test.ctx_in = (long) opts->ctx; - attr.test.ctx_size_in = opts->ctx->sz; - err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr)); - if (err < 0 || (int)attr.test.retval < 0) { - opts->errstr = "failed to execute loader prog"; - if (err < 0) { - set_err; - } else { - err = (int)attr.test.retval; -#ifndef __KERNEL__ - errno = -err; -#endif - } - goto out; - } - err = 0; -out: - if (map_fd >= 0) - close(map_fd); - if (prog_fd >= 0) - close(prog_fd); - return err; -} - -#endif diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/usdt.bpf.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/usdt.bpf.h deleted file mode 100644 index 4181fddb3687d774440c578eae9d5c5161dc7f6a..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/usdt.bpf.h +++ /dev/null @@ -1,259 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ -#ifndef __USDT_BPF_H__ -#define __USDT_BPF_H__ - -#include -#include -#include -#include - -/* Below types and maps are internal implementation details of libbpf's USDT - * support and are subjects to change. Also, bpf_usdt_xxx() API helpers should - * be considered an unstable API as well and might be adjusted based on user - * feedback from using libbpf's USDT support in production. - */ - -/* User can override BPF_USDT_MAX_SPEC_CNT to change default size of internal - * map that keeps track of USDT argument specifications. This might be - * necessary if there are a lot of USDT attachments. - */ -#ifndef BPF_USDT_MAX_SPEC_CNT -#define BPF_USDT_MAX_SPEC_CNT 256 -#endif -/* User can override BPF_USDT_MAX_IP_CNT to change default size of internal - * map that keeps track of IP (memory address) mapping to USDT argument - * specification. - * Note, if kernel supports BPF cookies, this map is not used and could be - * resized all the way to 1 to save a bit of memory. - */ -#ifndef BPF_USDT_MAX_IP_CNT -#define BPF_USDT_MAX_IP_CNT (4 * BPF_USDT_MAX_SPEC_CNT) -#endif -/* We use BPF CO-RE to detect support for BPF cookie from BPF side. This is - * the only dependency on CO-RE, so if it's undesirable, user can override - * BPF_USDT_HAS_BPF_COOKIE to specify whether to BPF cookie is supported or not. - */ -#ifndef BPF_USDT_HAS_BPF_COOKIE -#define BPF_USDT_HAS_BPF_COOKIE \ - bpf_core_enum_value_exists(enum bpf_func_id___usdt, BPF_FUNC_get_attach_cookie___usdt) -#endif - -enum __bpf_usdt_arg_type { - BPF_USDT_ARG_CONST, - BPF_USDT_ARG_REG, - BPF_USDT_ARG_REG_DEREF, -}; - -struct __bpf_usdt_arg_spec { - /* u64 scalar interpreted depending on arg_type, see below */ - __u64 val_off; - /* arg location case, see bpf_udst_arg() for details */ - enum __bpf_usdt_arg_type arg_type; - /* offset of referenced register within struct pt_regs */ - short reg_off; - /* whether arg should be interpreted as signed value */ - bool arg_signed; - /* number of bits that need to be cleared and, optionally, - * sign-extended to cast arguments that are 1, 2, or 4 bytes - * long into final 8-byte u64/s64 value returned to user - */ - char arg_bitshift; -}; - -/* should match USDT_MAX_ARG_CNT in usdt.c exactly */ -#define BPF_USDT_MAX_ARG_CNT 12 -struct __bpf_usdt_spec { - struct __bpf_usdt_arg_spec args[BPF_USDT_MAX_ARG_CNT]; - __u64 usdt_cookie; - short arg_cnt; -}; - -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, BPF_USDT_MAX_SPEC_CNT); - __type(key, int); - __type(value, struct __bpf_usdt_spec); -} __bpf_usdt_specs SEC(".maps") __weak; - -struct { - __uint(type, BPF_MAP_TYPE_HASH); - __uint(max_entries, BPF_USDT_MAX_IP_CNT); - __type(key, long); - __type(value, __u32); -} __bpf_usdt_ip_to_spec_id SEC(".maps") __weak; - -/* don't rely on user's BPF code to have latest definition of bpf_func_id */ -enum bpf_func_id___usdt { - BPF_FUNC_get_attach_cookie___usdt = 0xBAD, /* value doesn't matter */ -}; - -static __always_inline -int __bpf_usdt_spec_id(struct pt_regs *ctx) -{ - if (!BPF_USDT_HAS_BPF_COOKIE) { - long ip = PT_REGS_IP(ctx); - int *spec_id_ptr; - - spec_id_ptr = bpf_map_lookup_elem(&__bpf_usdt_ip_to_spec_id, &ip); - return spec_id_ptr ? *spec_id_ptr : -ESRCH; - } - - return bpf_get_attach_cookie(ctx); -} - -/* Return number of USDT arguments defined for currently traced USDT. */ -__weak __hidden -int bpf_usdt_arg_cnt(struct pt_regs *ctx) -{ - struct __bpf_usdt_spec *spec; - int spec_id; - - spec_id = __bpf_usdt_spec_id(ctx); - if (spec_id < 0) - return -ESRCH; - - spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); - if (!spec) - return -ESRCH; - - return spec->arg_cnt; -} - -/* Fetch USDT argument #*arg_num* (zero-indexed) and put its value into *res. - * Returns 0 on success; negative error, otherwise. - * On error *res is guaranteed to be set to zero. - */ -__weak __hidden -int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) -{ - struct __bpf_usdt_spec *spec; - struct __bpf_usdt_arg_spec *arg_spec; - unsigned long val; - int err, spec_id; - - *res = 0; - - spec_id = __bpf_usdt_spec_id(ctx); - if (spec_id < 0) - return -ESRCH; - - spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); - if (!spec) - return -ESRCH; - - if (arg_num >= BPF_USDT_MAX_ARG_CNT || arg_num >= spec->arg_cnt) - return -ENOENT; - - arg_spec = &spec->args[arg_num]; - switch (arg_spec->arg_type) { - case BPF_USDT_ARG_CONST: - /* Arg is just a constant ("-4@$-9" in USDT arg spec). - * value is recorded in arg_spec->val_off directly. - */ - val = arg_spec->val_off; - break; - case BPF_USDT_ARG_REG: - /* Arg is in a register (e.g, "8@%rax" in USDT arg spec), - * so we read the contents of that register directly from - * struct pt_regs. To keep things simple user-space parts - * record offsetof(struct pt_regs, ) in arg_spec->reg_off. - */ - err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off); - if (err) - return err; - break; - case BPF_USDT_ARG_REG_DEREF: - /* Arg is in memory addressed by register, plus some offset - * (e.g., "-4@-1204(%rbp)" in USDT arg spec). Register is - * identified like with BPF_USDT_ARG_REG case, and the offset - * is in arg_spec->val_off. We first fetch register contents - * from pt_regs, then do another user-space probe read to - * fetch argument value itself. - */ - err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off); - if (err) - return err; - err = bpf_probe_read_user(&val, sizeof(val), (void *)val + arg_spec->val_off); - if (err) - return err; -#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - val >>= arg_spec->arg_bitshift; -#endif - break; - default: - return -EINVAL; - } - - /* cast arg from 1, 2, or 4 bytes to final 8 byte size clearing - * necessary upper arg_bitshift bits, with sign extension if argument - * is signed - */ - val <<= arg_spec->arg_bitshift; - if (arg_spec->arg_signed) - val = ((long)val) >> arg_spec->arg_bitshift; - else - val = val >> arg_spec->arg_bitshift; - *res = val; - return 0; -} - -/* Retrieve user-specified cookie value provided during attach as - * bpf_usdt_opts.usdt_cookie. This serves the same purpose as BPF cookie - * returned by bpf_get_attach_cookie(). Libbpf's support for USDT is itself - * utilizing BPF cookies internally, so user can't use BPF cookie directly - * for USDT programs and has to use bpf_usdt_cookie() API instead. - */ -__weak __hidden -long bpf_usdt_cookie(struct pt_regs *ctx) -{ - struct __bpf_usdt_spec *spec; - int spec_id; - - spec_id = __bpf_usdt_spec_id(ctx); - if (spec_id < 0) - return 0; - - spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); - if (!spec) - return 0; - - return spec->usdt_cookie; -} - -/* we rely on ___bpf_apply() and ___bpf_narg() macros already defined in bpf_tracing.h */ -#define ___bpf_usdt_args0() ctx -#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); (void *)_x; }) -#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); (void *)_x; }) -#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); (void *)_x; }) -#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); (void *)_x; }) -#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); (void *)_x; }) -#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); (void *)_x; }) -#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); (void *)_x; }) -#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); (void *)_x; }) -#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); (void *)_x; }) -#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); (void *)_x; }) -#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); (void *)_x; }) -#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); (void *)_x; }) -#define ___bpf_usdt_args(args...) ___bpf_apply(___bpf_usdt_args, ___bpf_narg(args))(args) - -/* - * BPF_USDT serves the same purpose for USDT handlers as BPF_PROG for - * tp_btf/fentry/fexit BPF programs and BPF_KPROBE for kprobes. - * Original struct pt_regs * context is preserved as 'ctx' argument. - */ -#define BPF_USDT(name, args...) \ -name(struct pt_regs *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ -____##name(struct pt_regs *ctx, ##args); \ -typeof(name(0)) name(struct pt_regs *ctx) \ -{ \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - return ____##name(___bpf_usdt_args(args)); \ - _Pragma("GCC diagnostic pop") \ -} \ -static __attribute__((always_inline)) typeof(name(0)) \ -____##name(struct pt_regs *ctx, ##args) - -#endif /* __USDT_BPF_H__ */ diff --git a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/xsk.h b/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/xsk.h deleted file mode 100644 index 64e9c57fd792d44d7a3618b651bdecb61455f4d5..0000000000000000000000000000000000000000 --- a/source/tools/monitor/raptor/source/ebpf/src/lib/include/bpf/xsk.h +++ /dev/null @@ -1,336 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ - -/* - * AF_XDP user-space access library. - * - * Copyright (c) 2018 - 2019 Intel Corporation. - * Copyright (c) 2019 Facebook - * - * Author(s): Magnus Karlsson - */ - -#ifndef __LIBBPF_XSK_H -#define __LIBBPF_XSK_H - -#include -#include -#include -#include - -#include "libbpf.h" - -#ifdef __cplusplus -extern "C" { -#endif - -/* This whole API has been deprecated and moved to libxdp that can be found at - * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so - * it should just be linking with libxdp instead of libbpf for this set of - * functionality. If not, please submit a bug report on the aforementioned page. - */ - -/* Load-Acquire Store-Release barriers used by the XDP socket - * library. The following macros should *NOT* be considered part of - * the xsk.h API, and is subject to change anytime. - * - * LIBRARY INTERNAL - */ - -#define __XSK_READ_ONCE(x) (*(volatile typeof(x) *)&x) -#define __XSK_WRITE_ONCE(x, v) (*(volatile typeof(x) *)&x) = (v) - -#if defined(__i386__) || defined(__x86_64__) -# define libbpf_smp_store_release(p, v) \ - do { \ - asm volatile("" : : : "memory"); \ - __XSK_WRITE_ONCE(*p, v); \ - } while (0) -# define libbpf_smp_load_acquire(p) \ - ({ \ - typeof(*p) ___p1 = __XSK_READ_ONCE(*p); \ - asm volatile("" : : : "memory"); \ - ___p1; \ - }) -#elif defined(__aarch64__) -# define libbpf_smp_store_release(p, v) \ - asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory") -# define libbpf_smp_load_acquire(p) \ - ({ \ - typeof(*p) ___p1; \ - asm volatile ("ldar %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ - ___p1; \ - }) -#elif defined(__riscv) -# define libbpf_smp_store_release(p, v) \ - do { \ - asm volatile ("fence rw,w" : : : "memory"); \ - __XSK_WRITE_ONCE(*p, v); \ - } while (0) -# define libbpf_smp_load_acquire(p) \ - ({ \ - typeof(*p) ___p1 = __XSK_READ_ONCE(*p); \ - asm volatile ("fence r,rw" : : : "memory"); \ - ___p1; \ - }) -#endif - -#ifndef libbpf_smp_store_release -#define libbpf_smp_store_release(p, v) \ - do { \ - __sync_synchronize(); \ - __XSK_WRITE_ONCE(*p, v); \ - } while (0) -#endif - -#ifndef libbpf_smp_load_acquire -#define libbpf_smp_load_acquire(p) \ - ({ \ - typeof(*p) ___p1 = __XSK_READ_ONCE(*p); \ - __sync_synchronize(); \ - ___p1; \ - }) -#endif - -/* LIBRARY INTERNAL -- END */ - -/* Do not access these members directly. Use the functions below. */ -#define DEFINE_XSK_RING(name) \ -struct name { \ - __u32 cached_prod; \ - __u32 cached_cons; \ - __u32 mask; \ - __u32 size; \ - __u32 *producer; \ - __u32 *consumer; \ - void *ring; \ - __u32 *flags; \ -} - -DEFINE_XSK_RING(xsk_ring_prod); -DEFINE_XSK_RING(xsk_ring_cons); - -/* For a detailed explanation on the memory barriers associated with the - * ring, please take a look at net/xdp/xsk_queue.h. - */ - -struct xsk_umem; -struct xsk_socket; - -static inline __u64 *xsk_ring_prod__fill_addr(struct xsk_ring_prod *fill, - __u32 idx) -{ - __u64 *addrs = (__u64 *)fill->ring; - - return &addrs[idx & fill->mask]; -} - -static inline const __u64 * -xsk_ring_cons__comp_addr(const struct xsk_ring_cons *comp, __u32 idx) -{ - const __u64 *addrs = (const __u64 *)comp->ring; - - return &addrs[idx & comp->mask]; -} - -static inline struct xdp_desc *xsk_ring_prod__tx_desc(struct xsk_ring_prod *tx, - __u32 idx) -{ - struct xdp_desc *descs = (struct xdp_desc *)tx->ring; - - return &descs[idx & tx->mask]; -} - -static inline const struct xdp_desc * -xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx) -{ - const struct xdp_desc *descs = (const struct xdp_desc *)rx->ring; - - return &descs[idx & rx->mask]; -} - -static inline int xsk_ring_prod__needs_wakeup(const struct xsk_ring_prod *r) -{ - return *r->flags & XDP_RING_NEED_WAKEUP; -} - -static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb) -{ - __u32 free_entries = r->cached_cons - r->cached_prod; - - if (free_entries >= nb) - return free_entries; - - /* Refresh the local tail pointer. - * cached_cons is r->size bigger than the real consumer pointer so - * that this addition can be avoided in the more frequently - * executed code that computs free_entries in the beginning of - * this function. Without this optimization it whould have been - * free_entries = r->cached_prod - r->cached_cons + r->size. - */ - r->cached_cons = libbpf_smp_load_acquire(r->consumer); - r->cached_cons += r->size; - - return r->cached_cons - r->cached_prod; -} - -static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb) -{ - __u32 entries = r->cached_prod - r->cached_cons; - - if (entries == 0) { - r->cached_prod = libbpf_smp_load_acquire(r->producer); - entries = r->cached_prod - r->cached_cons; - } - - return (entries > nb) ? nb : entries; -} - -static inline __u32 xsk_ring_prod__reserve(struct xsk_ring_prod *prod, __u32 nb, __u32 *idx) -{ - if (xsk_prod_nb_free(prod, nb) < nb) - return 0; - - *idx = prod->cached_prod; - prod->cached_prod += nb; - - return nb; -} - -static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb) -{ - /* Make sure everything has been written to the ring before indicating - * this to the kernel by writing the producer pointer. - */ - libbpf_smp_store_release(prod->producer, *prod->producer + nb); -} - -static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx) -{ - __u32 entries = xsk_cons_nb_avail(cons, nb); - - if (entries > 0) { - *idx = cons->cached_cons; - cons->cached_cons += entries; - } - - return entries; -} - -static inline void xsk_ring_cons__cancel(struct xsk_ring_cons *cons, __u32 nb) -{ - cons->cached_cons -= nb; -} - -static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb) -{ - /* Make sure data has been read before indicating we are done - * with the entries by updating the consumer pointer. - */ - libbpf_smp_store_release(cons->consumer, *cons->consumer + nb); - -} - -static inline void *xsk_umem__get_data(void *umem_area, __u64 addr) -{ - return &((char *)umem_area)[addr]; -} - -static inline __u64 xsk_umem__extract_addr(__u64 addr) -{ - return addr & XSK_UNALIGNED_BUF_ADDR_MASK; -} - -static inline __u64 xsk_umem__extract_offset(__u64 addr) -{ - return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT; -} - -static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr) -{ - return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr); -} - -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_umem__fd(const struct xsk_umem *umem); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_socket__fd(const struct xsk_socket *xsk); - -#define XSK_RING_CONS__DEFAULT_NUM_DESCS 2048 -#define XSK_RING_PROD__DEFAULT_NUM_DESCS 2048 -#define XSK_UMEM__DEFAULT_FRAME_SHIFT 12 /* 4096 bytes */ -#define XSK_UMEM__DEFAULT_FRAME_SIZE (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT) -#define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0 -#define XSK_UMEM__DEFAULT_FLAGS 0 - -struct xsk_umem_config { - __u32 fill_size; - __u32 comp_size; - __u32 frame_size; - __u32 frame_headroom; - __u32 flags; -}; - -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd); - -/* Flags for the libbpf_flags field. */ -#define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0) - -struct xsk_socket_config { - __u32 rx_size; - __u32 tx_size; - __u32 libbpf_flags; - __u32 xdp_flags; - __u16 bind_flags; -}; - -/* Set config to NULL to get the default configuration. */ -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_umem__create(struct xsk_umem **umem, - void *umem_area, __u64 size, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *config); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_umem__create_v0_0_2(struct xsk_umem **umem, - void *umem_area, __u64 size, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *config); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_umem__create_v0_0_4(struct xsk_umem **umem, - void *umem_area, __u64 size, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *config); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_socket__create(struct xsk_socket **xsk, - const char *ifname, __u32 queue_id, - struct xsk_umem *umem, - struct xsk_ring_cons *rx, - struct xsk_ring_prod *tx, - const struct xsk_socket_config *config); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, - const char *ifname, - __u32 queue_id, struct xsk_umem *umem, - struct xsk_ring_cons *rx, - struct xsk_ring_prod *tx, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_socket_config *config); - -/* Returns 0 for success and -EBUSY if the umem is still in use. */ -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_umem__delete(struct xsk_umem *umem); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -void xsk_socket__delete(struct xsk_socket *xsk); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* __LIBBPF_XSK_H */