diff --git a/examples/instruction_patching/Makefile b/examples/instruction_patching/Makefile new file mode 100644 index 0000000..c67a2b6 --- /dev/null +++ b/examples/instruction_patching/Makefile @@ -0,0 +1,27 @@ +all: build-ebpf build run + +build-ebpf: + mkdir -p ebpf/bin + clang -D__KERNEL__ -D__ASM_SYSREG_H \ + -Wno-unused-value \ + -Wno-pointer-sign \ + -Wno-compare-distinct-pointer-types \ + -Wunused \ + -Wall \ + -Werror \ + -I/lib/modules/$$(uname -r)/build/include \ + -I/lib/modules/$$(uname -r)/build/include/uapi \ + -I/lib/modules/$$(uname -r)/build/include/generated/uapi \ + -I/lib/modules/$$(uname -r)/build/arch/x86/include \ + -I/lib/modules/$$(uname -r)/build/arch/x86/include/uapi \ + -I/lib/modules/$$(uname -r)/build/arch/x86/include/generated \ + -O2 -emit-llvm \ + ebpf/main.c \ + -c -o - | llc -march=bpf -filetype=obj -o ebpf/bin/probe.o + go run github.com/shuLhan/go-bindata/cmd/go-bindata -pkg main -prefix "ebpf/bin" -o "probe.go" "ebpf/bin/probe.o" + +build: + go build -o bin/main . + +run: + sudo bin/main diff --git a/examples/instruction_patching/bin/.gitkeep b/examples/instruction_patching/bin/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/examples/instruction_patching/ebpf/include/bpf.h b/examples/instruction_patching/ebpf/include/bpf.h new file mode 100644 index 0000000..3a4d49a --- /dev/null +++ b/examples/instruction_patching/ebpf/include/bpf.h @@ -0,0 +1,1277 @@ +/* In Linux 5.4 asm_inline was introduced, but it's not supported by clang. + * Redefine it to just asm to enable successful compilation. + */ +#ifdef asm_inline +#undef asm_inline +#define asm_inline asm +#endif +/* Before bpf_helpers.h is included, uapi bpf.h has been + * included, which references linux/types.h. This may bring + * in asm_volatile_goto definition if permitted based on + * compiler setup and kernel configs. + * + * clang does not support "asm volatile goto" yet. + * So redefine asm_volatile_goto to some invalid asm code. + * If asm_volatile_goto is actually used by the bpf program, + * a compilation error will appear. + */ +#ifdef asm_volatile_goto +#undef asm_volatile_goto +#endif +#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto") + +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _UAPI__LINUX_BPF_H__ +#define _UAPI__LINUX_BPF_H__ + +#include +#include + +/* Extended instruction set based on top of classic BPF */ + +/* instruction classes */ +#define BPF_ALU64 0x07 /* alu mode in double word width */ + +/* ld/ldx fields */ +#define BPF_DW 0x18 /* double word (64-bit) */ +#define BPF_XADD 0xc0 /* exclusive add */ + +/* alu/jmp fields */ +#define BPF_MOV 0xb0 /* mov reg to reg */ +#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */ + +/* change endianness of a register */ +#define BPF_END 0xd0 /* flags for endianness conversion: */ +#define BPF_TO_LE 0x00 /* convert to little-endian */ +#define BPF_TO_BE 0x08 /* convert to big-endian */ +#define BPF_FROM_LE BPF_TO_LE +#define BPF_FROM_BE BPF_TO_BE + +/* jmp encodings */ +#define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ +#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ +#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ +#define BPF_CALL 0x80 /* function call */ +#define BPF_EXIT 0x90 /* function return */ + +/* Register numbers */ +enum +{ + BPF_REG_0 = 0, + BPF_REG_1, + BPF_REG_2, + BPF_REG_3, + BPF_REG_4, + BPF_REG_5, + BPF_REG_6, + BPF_REG_7, + BPF_REG_8, + BPF_REG_9, + BPF_REG_10, + __MAX_BPF_REG, +}; + +/* BPF has 10 general purpose 64-bit registers and stack frame. */ +#define MAX_BPF_REG __MAX_BPF_REG + +struct bpf_insn +{ + __u8 code; /* opcode */ + __u8 dst_reg : 4; /* dest register */ + __u8 src_reg : 4; /* source register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ +}; + +/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ +struct bpf_lpm_trie_key +{ + __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ + __u8 data[0]; /* Arbitrary size */ +}; + +/* BPF syscall commands, see bpf(2) man-page for details. */ +enum bpf_cmd +{ + BPF_MAP_CREATE, + BPF_MAP_LOOKUP_ELEM, + BPF_MAP_UPDATE_ELEM, + BPF_MAP_DELETE_ELEM, + BPF_MAP_GET_NEXT_KEY, + BPF_PROG_LOAD, + BPF_OBJ_PIN, + BPF_OBJ_GET, + BPF_PROG_ATTACH, + BPF_PROG_DETACH, + BPF_PROG_TEST_RUN, + BPF_PROG_GET_NEXT_ID, + BPF_MAP_GET_NEXT_ID, + BPF_PROG_GET_FD_BY_ID, + BPF_MAP_GET_FD_BY_ID, + BPF_OBJ_GET_INFO_BY_FD, + BPF_PROG_QUERY, + BPF_RAW_TRACEPOINT_OPEN, +}; + +enum bpf_map_type +{ + BPF_MAP_TYPE_UNSPEC, + BPF_MAP_TYPE_HASH, + BPF_MAP_TYPE_ARRAY, + BPF_MAP_TYPE_PROG_ARRAY, + BPF_MAP_TYPE_PERF_EVENT_ARRAY, + BPF_MAP_TYPE_PERCPU_HASH, + BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, + BPF_MAP_TYPE_LRU_HASH, + BPF_MAP_TYPE_LRU_PERCPU_HASH, + BPF_MAP_TYPE_LPM_TRIE, + BPF_MAP_TYPE_ARRAY_OF_MAPS, + BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, +}; + +enum bpf_prog_type +{ + BPF_PROG_TYPE_UNSPEC, + BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_KPROBE, + BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, + BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, + BPF_PROG_TYPE_PERF_EVENT, + BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_CGROUP_SOCK, + BPF_PROG_TYPE_LWT_IN, + BPF_PROG_TYPE_LWT_OUT, + BPF_PROG_TYPE_LWT_XMIT, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_CGROUP_DEVICE, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_RAW_TRACEPOINT, + BPF_PROG_TYPE_CGROUP_SOCK_ADDR, +}; + +enum bpf_attach_type +{ + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_SOCK_OPS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, + BPF_SK_MSG_VERDICT, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_POST_BIND, + BPF_CGROUP_INET6_POST_BIND, + __MAX_BPF_ATTACH_TYPE +}; + +#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE + +/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command + * + * NONE(default): No further bpf programs allowed in the subtree. + * + * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, + * the program in this cgroup yields to sub-cgroup program. + * + * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, + * that cgroup program gets run in addition to the program in this cgroup. + * + * Only one program is allowed to be attached to a cgroup with + * NONE or BPF_F_ALLOW_OVERRIDE flag. + * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will + * release old program and attach the new one. Attach flags has to match. + * + * Multiple programs are allowed to be attached to a cgroup with + * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order + * (those that were attached first, run first) + * The programs of sub-cgroup are executed first, then programs of + * this cgroup and then programs of parent cgroup. + * When children program makes decision (like picking TCP CA or sock bind) + * parent program has a chance to override it. + * + * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. + * A cgroup with NONE doesn't allow any programs in sub-cgroups. + * Ex1: + * cgrp1 (MULTI progs A, B) -> + * cgrp2 (OVERRIDE prog C) -> + * cgrp3 (MULTI prog D) -> + * cgrp4 (OVERRIDE prog E) -> + * cgrp5 (NONE prog F) + * the event in cgrp5 triggers execution of F,D,A,B in that order. + * if prog F is detached, the execution is E,D,A,B + * if prog F and D are detached, the execution is E,A,B + * if prog F, E and D are detached, the execution is C,A,B + * + * All eligible programs are executed regardless of return code from + * earlier programs. + */ +#define BPF_F_ALLOW_OVERRIDE (1U << 0) +#define BPF_F_ALLOW_MULTI (1U << 1) + +/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will perform strict alignment checking as if the kernel + * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, + * and NET_IP_ALIGN defined to 2. + */ +#define BPF_F_STRICT_ALIGNMENT (1U << 0) + +/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ +#define BPF_PSEUDO_MAP_FD 1 + +/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative + * offset to another bpf function + */ +#define BPF_PSEUDO_CALL 1 + +/* flags for BPF_MAP_UPDATE_ELEM command */ +#define BPF_ANY 0 /* create new element or update existing */ +#define BPF_NOEXIST 1 /* create new element if it didn't exist */ +#define BPF_EXIST 2 /* update existing element */ + +/* flags for BPF_MAP_CREATE command */ +#define BPF_F_NO_PREALLOC (1U << 0) +/* Instead of having one common LRU list in the + * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list + * which can scale and perform better. + * Note, the LRU nodes (including free nodes) cannot be moved + * across different LRU lists. + */ +#define BPF_F_NO_COMMON_LRU (1U << 1) +/* Specify numa node during map creation */ +#define BPF_F_NUMA_NODE (1U << 2) + +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + +#define BPF_OBJ_NAME_LEN 16U + +/* Flags for accessing BPF object */ +#define BPF_F_RDONLY (1U << 3) +#define BPF_F_WRONLY (1U << 4) + +/* Flag for stack_map, store build_id+offset instead of pointer */ +#define BPF_F_STACK_BUILD_ID (1U << 5) + +enum bpf_stack_build_id_status +{ + /* user space need an empty entry to identify end of a trace */ + BPF_STACK_BUILD_ID_EMPTY = 0, + /* with valid build_id and offset */ + BPF_STACK_BUILD_ID_VALID = 1, + /* couldn't get build_id, fallback to ip */ + BPF_STACK_BUILD_ID_IP = 2, +}; + +#define BPF_BUILD_ID_SIZE 20 +struct bpf_stack_build_id +{ + __s32 status; + unsigned char build_id[BPF_BUILD_ID_SIZE]; + union { + __u64 offset; + __u64 ip; + }; +}; + +union bpf_attr { + struct + { /* anonymous struct used by BPF_MAP_CREATE command */ + __u32 map_type; /* one of enum bpf_map_type */ + __u32 key_size; /* size of key in bytes */ + __u32 value_size; /* size of value in bytes */ + __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* BPF_MAP_CREATE related + * flags defined above. + */ + __u32 inner_map_fd; /* fd pointing to the inner map */ + __u32 numa_node; /* numa node (effective only if + * BPF_F_NUMA_NODE is set). + */ + char map_name[BPF_OBJ_NAME_LEN]; + __u32 map_ifindex; /* ifindex of netdev to create on */ + }; + + struct + { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + __u32 map_fd; + __aligned_u64 key; + union { + __aligned_u64 value; + __aligned_u64 next_key; + }; + __u64 flags; + }; + + struct + { /* anonymous struct used by BPF_PROG_LOAD command */ + __u32 prog_type; /* one of enum bpf_prog_type */ + __u32 insn_cnt; + __aligned_u64 insns; + __aligned_u64 license; + __u32 log_level; /* verbosity level of verifier */ + __u32 log_size; /* size of user buffer */ + __aligned_u64 log_buf; /* user supplied buffer */ + __u32 kern_version; /* checked when prog_type=kprobe */ + __u32 prog_flags; + char prog_name[BPF_OBJ_NAME_LEN]; + __u32 prog_ifindex; /* ifindex of netdev to prep for */ + /* For some prog types expected attach type must be known at + * load time to verify attach type specific parts of prog + * (context accesses, allowed helpers, etc). + */ + __u32 expected_attach_type; + }; + + struct + { /* anonymous struct used by BPF_OBJ_* commands */ + __aligned_u64 pathname; + __u32 bpf_fd; + __u32 file_flags; + }; + + struct + { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ + __u32 target_fd; /* container object to attach to */ + __u32 attach_bpf_fd; /* eBPF program to attach */ + __u32 attach_type; + __u32 attach_flags; + }; + + struct + { /* anonymous struct used by BPF_PROG_TEST_RUN command */ + __u32 prog_fd; + __u32 retval; + __u32 data_size_in; + __u32 data_size_out; + __aligned_u64 data_in; + __aligned_u64 data_out; + __u32 repeat; + __u32 duration; + } test; + + struct + { /* anonymous struct used by BPF_*_GET_*_ID */ + union { + __u32 start_id; + __u32 prog_id; + __u32 map_id; + }; + __u32 next_id; + __u32 open_flags; + }; + + struct + { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ + __u32 bpf_fd; + __u32 info_len; + __aligned_u64 info; + } info; + + struct + { /* anonymous struct used by BPF_PROG_QUERY command */ + __u32 target_fd; /* container object to query */ + __u32 attach_type; + __u32 query_flags; + __u32 attach_flags; + __aligned_u64 prog_ids; + __u32 prog_cnt; + } query; + + struct + { + __u64 name; + __u32 prog_fd; + } raw_tracepoint; +} __attribute__((aligned(8))); + +/* BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(&map, &key) + * Return: Map value or NULL + * + * int bpf_map_update_elem(&map, &key, &value, flags) + * Return: 0 on success or negative error + * + * int bpf_map_delete_elem(&map, &key) + * Return: 0 on success or negative error + * + * int bpf_probe_read(void *dst, int size, void *src) + * Return: 0 on success or negative error + * + * u64 bpf_ktime_get_ns(void) + * Return: current ktime + * + * int bpf_trace_printk(const char *fmt, int fmt_size, ...) + * Return: length of buffer written or negative error + * + * u32 bpf_prandom_u32(void) + * Return: random value + * + * u32 bpf_raw_smp_processor_id(void) + * Return: SMP processor ID + * + * int bpf_skb_store_bytes(skb, offset, from, len, flags) + * store bytes into packet + * @skb: pointer to skb + * @offset: offset within packet from skb->mac_header + * @from: pointer where to copy bytes from + * @len: number of bytes to store into packet + * @flags: bit 0 - if true, recompute skb->csum + * other bits - reserved + * Return: 0 on success or negative error + * + * int bpf_l3_csum_replace(skb, offset, from, to, flags) + * recompute IP checksum + * @skb: pointer to skb + * @offset: offset within packet where IP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * other bits - reserved + * Return: 0 on success or negative error + * + * int bpf_l4_csum_replace(skb, offset, from, to, flags) + * recompute TCP/UDP checksum + * @skb: pointer to skb + * @offset: offset within packet where TCP/UDP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * bit 4 - is pseudo header + * other bits - reserved + * Return: 0 on success or negative error + * + * int bpf_tail_call(ctx, prog_array_map, index) + * jump into another BPF program + * @ctx: context pointer passed to next program + * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY + * @index: 32-bit index inside array that selects specific program to run + * Return: 0 on success or negative error + * + * int bpf_clone_redirect(skb, ifindex, flags) + * redirect to another netdev + * @skb: pointer to skb + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: 0 on success or negative error + * + * u64 bpf_get_current_pid_tgid(void) + * Return: current->tgid << 32 | current->pid + * + * u64 bpf_get_current_uid_gid(void) + * Return: current_gid << 32 | current_uid + * + * int bpf_get_current_comm(char *buf, int size_of_buf) + * stores current->comm into buf + * Return: 0 on success or negative error + * + * u32 bpf_get_cgroup_classid(skb) + * retrieve a proc's classid + * @skb: pointer to skb + * Return: classid if != 0 + * + * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) + * Return: 0 on success or negative error + * + * int bpf_skb_vlan_pop(skb) + * Return: 0 on success or negative error + * + * int bpf_skb_get_tunnel_key(skb, key, size, flags) + * int bpf_skb_set_tunnel_key(skb, key, size, flags) + * retrieve or populate tunnel metadata + * @skb: pointer to skb + * @key: pointer to 'struct bpf_tunnel_key' + * @size: size of 'struct bpf_tunnel_key' + * @flags: room for future extensions + * Return: 0 on success or negative error + * + * u64 bpf_perf_event_read(map, flags) + * read perf event counter value + * @map: pointer to perf_event_array map + * @flags: index of event in the map or bitmask flags + * Return: value of perf event counter read or error code + * + * int bpf_redirect(ifindex, flags) + * redirect to another netdev + * @ifindex: ifindex of the net device + * @flags: + * cls_bpf: + * bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * xdp_bpf: + * all bits - reserved + * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error + * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error + * int bpf_redirect_map(map, key, flags) + * redirect to endpoint in map + * @map: pointer to dev map + * @key: index in map to lookup + * @flags: -- + * Return: XDP_REDIRECT on success or XDP_ABORT on error + * + * u32 bpf_get_route_realm(skb) + * retrieve a dst's tclassid + * @skb: pointer to skb + * Return: realm if != 0 + * + * int bpf_perf_event_output(ctx, map, flags, data, size) + * output perf raw sample + * @ctx: struct pt_regs* + * @map: pointer to perf_event_array map + * @flags: index of event in the map or bitmask flags + * @data: data on stack to be output as raw data + * @size: size of data + * Return: 0 on success or negative error + * + * int bpf_get_stackid(ctx, map, flags) + * walk user or kernel stack and return id + * @ctx: struct pt_regs* + * @map: pointer to stack_trace map + * @flags: bits 0-7 - numer of stack frames to skip + * bit 8 - collect user stack instead of kernel + * bit 9 - compare stacks by hash only + * bit 10 - if two different stacks hash into the same stackid + * discard old + * other bits - reserved + * Return: >= 0 stackid on success or negative error + * + * s64 bpf_csum_diff(from, from_size, to, to_size, seed) + * calculate csum diff + * @from: raw from buffer + * @from_size: length of from buffer + * @to: raw to buffer + * @to_size: length of to buffer + * @seed: optional seed + * Return: csum result or negative error code + * + * int bpf_skb_get_tunnel_opt(skb, opt, size) + * retrieve tunnel options metadata + * @skb: pointer to skb + * @opt: pointer to raw tunnel option data + * @size: size of @opt + * Return: option size + * + * int bpf_skb_set_tunnel_opt(skb, opt, size) + * populate tunnel options metadata + * @skb: pointer to skb + * @opt: pointer to raw tunnel option data + * @size: size of @opt + * Return: 0 on success or negative error + * + * int bpf_skb_change_proto(skb, proto, flags) + * Change protocol of the skb. Currently supported is v4 -> v6, + * v6 -> v4 transitions. The helper will also resize the skb. eBPF + * program is expected to fill the new headers via skb_store_bytes + * and lX_csum_replace. + * @skb: pointer to skb + * @proto: new skb->protocol type + * @flags: reserved + * Return: 0 on success or negative error + * + * int bpf_skb_change_type(skb, type) + * Change packet type of skb. + * @skb: pointer to skb + * @type: new skb->pkt_type type + * Return: 0 on success or negative error + * + * int bpf_skb_under_cgroup(skb, map, index) + * Check cgroup2 membership of skb + * @skb: pointer to skb + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 skb failed the cgroup2 descendant test + * == 1 skb succeeded the cgroup2 descendant test + * < 0 error + * + * u32 bpf_get_hash_recalc(skb) + * Retrieve and possibly recalculate skb->hash. + * @skb: pointer to skb + * Return: hash + * + * u64 bpf_get_current_task(void) + * Returns current task_struct + * Return: current + * + * int bpf_probe_write_user(void *dst, void *src, int len) + * safely attempt to write to a location + * @dst: destination address in userspace + * @src: source address on stack + * @len: number of bytes to copy + * Return: 0 on success or negative error + * + * int bpf_current_task_under_cgroup(map, index) + * Check cgroup2 membership of current task + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 current failed the cgroup2 descendant test + * == 1 current succeeded the cgroup2 descendant test + * < 0 error + * + * int bpf_skb_change_tail(skb, len, flags) + * The helper will resize the skb to the given new size, to be used f.e. + * with control messages. + * @skb: pointer to skb + * @len: new skb length + * @flags: reserved + * Return: 0 on success or negative error + * + * int bpf_skb_pull_data(skb, len) + * The helper will pull in non-linear data in case the skb is non-linear + * and not all of len are part of the linear section. Only needed for + * read/write with direct packet access. + * @skb: pointer to skb + * @len: len to make read/writeable + * Return: 0 on success or negative error + * + * s64 bpf_csum_update(skb, csum) + * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. + * @skb: pointer to skb + * @csum: csum to add + * Return: csum on success or negative error + * + * void bpf_set_hash_invalid(skb) + * Invalidate current skb->hash. + * @skb: pointer to skb + * + * int bpf_get_numa_node_id() + * Return: Id of current NUMA node. + * + * int bpf_skb_change_head() + * Grows headroom of skb and adjusts MAC header offset accordingly. + * Will extends/reallocae as required automatically. + * May change skb data pointer and will thus invalidate any check + * performed for direct packet access. + * @skb: pointer to skb + * @len: length of header to be pushed in front + * @flags: Flags (unused for now) + * Return: 0 on success or negative error + * + * int bpf_xdp_adjust_head(xdp_md, delta) + * Adjust the xdp_md.data by delta + * @xdp_md: pointer to xdp_md + * @delta: An positive/negative integer to be added to xdp_md.data + * Return: 0 on success or negative on error + * + * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) + * Copy a NUL terminated string from unsafe address. In case the string + * length is smaller than size, the target is not padded with further NUL + * bytes. In case the string length is larger than size, just count-1 + * bytes are copied and the last byte is set to NUL. + * @dst: destination address + * @size: maximum number of bytes to copy, including the trailing NUL + * @unsafe_ptr: unsafe address + * Return: + * > 0 length of the string including the trailing NUL on success + * < 0 error + * + * u64 bpf_get_socket_cookie(skb) + * Get the cookie for the socket stored inside sk_buff. + * @skb: pointer to skb + * Return: 8 Bytes non-decreasing number on success or 0 if the socket + * field is missing inside sk_buff + * + * u32 bpf_get_socket_uid(skb) + * Get the owner uid of the socket stored inside sk_buff. + * @skb: pointer to skb + * Return: uid of the socket owner on success or overflowuid if failed. + * + * u32 bpf_set_hash(skb, hash) + * Set full skb->hash. + * @skb: pointer to skb + * @hash: hash to set + * + * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen) + * Calls setsockopt. Not all opts are available, only those with + * integer optvals plus TCP_CONGESTION. + * Supported levels: SOL_SOCKET and IPPROTO_TCP + * @bpf_socket: pointer to bpf_socket + * @level: SOL_SOCKET or IPPROTO_TCP + * @optname: option name + * @optval: pointer to option value + * @optlen: length of optval in bytes + * Return: 0 or negative error + * + * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen) + * Calls getsockopt. Not all opts are available. + * Supported levels: IPPROTO_TCP + * @bpf_socket: pointer to bpf_socket + * @level: IPPROTO_TCP + * @optname: option name + * @optval: pointer to option value + * @optlen: length of optval in bytes + * Return: 0 or negative error + * + * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags) + * Set callback flags for sock_ops + * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct + * @flags: flags value + * Return: 0 for no error + * -EINVAL if there is no full tcp socket + * bits in flags that are not supported by current kernel + * + * int bpf_skb_adjust_room(skb, len_diff, mode, flags) + * Grow or shrink room in sk_buff. + * @skb: pointer to skb + * @len_diff: (signed) amount of room to grow/shrink + * @mode: operation mode (enum bpf_adj_room_mode) + * @flags: reserved for future use + * Return: 0 on success or negative error code + * + * int bpf_sk_redirect_map(map, key, flags) + * Redirect skb to a sock in map using key as a lookup key for the + * sock in map. + * @map: pointer to sockmap + * @key: key to lookup sock in map + * @flags: reserved for future use + * Return: SK_PASS + * + * int bpf_sock_map_update(skops, map, key, flags) + * @skops: pointer to bpf_sock_ops + * @map: pointer to sockmap to update + * @key: key to insert/update sock in map + * @flags: same flags as map update elem + * + * int bpf_xdp_adjust_meta(xdp_md, delta) + * Adjust the xdp_md.data_meta by delta + * @xdp_md: pointer to xdp_md + * @delta: An positive/negative integer to be added to xdp_md.data_meta + * Return: 0 on success or negative on error + * + * int bpf_perf_event_read_value(map, flags, buf, buf_size) + * read perf event counter value and perf event enabled/running time + * @map: pointer to perf_event_array map + * @flags: index of event in the map or bitmask flags + * @buf: buf to fill + * @buf_size: size of the buf + * Return: 0 on success or negative error code + * + * int bpf_perf_prog_read_value(ctx, buf, buf_size) + * read perf prog attached perf event counter and enabled/running time + * @ctx: pointer to ctx + * @buf: buf to fill + * @buf_size: size of the buf + * Return : 0 on success or negative error code + * + * int bpf_override_return(pt_regs, rc) + * @pt_regs: pointer to struct pt_regs + * @rc: the return value to set + * + * int bpf_msg_redirect_map(map, key, flags) + * Redirect msg to a sock in map using key as a lookup key for the + * sock in map. + * @map: pointer to sockmap + * @key: key to lookup sock in map + * @flags: reserved for future use + * Return: SK_PASS + * + * int bpf_bind(ctx, addr, addr_len) + * Bind socket to address. Only binding to IP is supported, no port can be + * set in addr. + * @ctx: pointer to context of type bpf_sock_addr + * @addr: pointer to struct sockaddr to bind socket to + * @addr_len: length of sockaddr structure + * Return: 0 on success or negative error code + */ +#define __BPF_FUNC_MAPPER(FN) \ + FN(unspec), \ + FN(map_lookup_elem), \ + FN(map_update_elem), \ + FN(map_delete_elem), \ + FN(probe_read), \ + FN(ktime_get_ns), \ + FN(trace_printk), \ + FN(get_prandom_u32), \ + FN(get_smp_processor_id), \ + FN(skb_store_bytes), \ + FN(l3_csum_replace), \ + FN(l4_csum_replace), \ + FN(tail_call), \ + FN(clone_redirect), \ + FN(get_current_pid_tgid), \ + FN(get_current_uid_gid), \ + FN(get_current_comm), \ + FN(get_cgroup_classid), \ + FN(skb_vlan_push), \ + FN(skb_vlan_pop), \ + FN(skb_get_tunnel_key), \ + FN(skb_set_tunnel_key), \ + FN(perf_event_read), \ + FN(redirect), \ + FN(get_route_realm), \ + FN(perf_event_output), \ + FN(skb_load_bytes), \ + FN(get_stackid), \ + FN(csum_diff), \ + FN(skb_get_tunnel_opt), \ + FN(skb_set_tunnel_opt), \ + FN(skb_change_proto), \ + FN(skb_change_type), \ + FN(skb_under_cgroup), \ + FN(get_hash_recalc), \ + FN(get_current_task), \ + FN(probe_write_user), \ + FN(current_task_under_cgroup), \ + FN(skb_change_tail), \ + FN(skb_pull_data), \ + FN(csum_update), \ + FN(set_hash_invalid), \ + FN(get_numa_node_id), \ + FN(skb_change_head), \ + FN(xdp_adjust_head), \ + FN(probe_read_str), \ + FN(get_socket_cookie), \ + FN(get_socket_uid), \ + FN(set_hash), \ + FN(setsockopt), \ + FN(skb_adjust_room), \ + FN(redirect_map), \ + FN(sk_redirect_map), \ + FN(sock_map_update), \ + FN(xdp_adjust_meta), \ + FN(perf_event_read_value), \ + FN(perf_prog_read_value), \ + FN(getsockopt), \ + FN(override_return), \ + FN(sock_ops_cb_flags_set), \ + FN(msg_redirect_map), \ + FN(msg_apply_bytes), \ + FN(msg_cork_bytes), \ + FN(msg_pull_data), \ + FN(bind), + +/* integer value in 'imm' field of BPF_CALL instruction selects which helper + * function eBPF program intends to call + */ +#define __BPF_ENUM_FN(x) BPF_FUNC_##x +enum bpf_func_id +{ + __BPF_FUNC_MAPPER(__BPF_ENUM_FN) + __BPF_FUNC_MAX_ID, +}; +#undef __BPF_ENUM_FN + +/* All flags used by eBPF helper functions, placed here. */ + +/* BPF_FUNC_skb_store_bytes flags. */ +#define BPF_F_RECOMPUTE_CSUM (1ULL << 0) +#define BPF_F_INVALIDATE_HASH (1ULL << 1) + +/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags. + * First 4 bits are for passing the header field size. + */ +#define BPF_F_HDR_FIELD_MASK 0xfULL + +/* BPF_FUNC_l4_csum_replace flags. */ +#define BPF_F_PSEUDO_HDR (1ULL << 4) +#define BPF_F_MARK_MANGLED_0 (1ULL << 5) +#define BPF_F_MARK_ENFORCE (1ULL << 6) + +/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ +#define BPF_F_INGRESS (1ULL << 0) + +/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ +#define BPF_F_TUNINFO_IPV6 (1ULL << 0) + +/* BPF_FUNC_get_stackid flags. */ +#define BPF_F_SKIP_FIELD_MASK 0xffULL +#define BPF_F_USER_STACK (1ULL << 8) +#define BPF_F_FAST_STACK_CMP (1ULL << 9) +#define BPF_F_REUSE_STACKID (1ULL << 10) + +/* BPF_FUNC_skb_set_tunnel_key flags. */ +#define BPF_F_ZERO_CSUM_TX (1ULL << 1) +#define BPF_F_DONT_FRAGMENT (1ULL << 2) +#define BPF_F_SEQ_NUMBER (1ULL << 3) + +/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and + * BPF_FUNC_perf_event_read_value flags. + */ +#define BPF_F_INDEX_MASK 0xffffffffULL +#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +/* BPF_FUNC_perf_event_output for sk_buff input context. */ +#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) + +/* Mode for BPF_FUNC_skb_adjust_room helper. */ +enum bpf_adj_room_mode +{ + BPF_ADJ_ROOM_NET, +}; + +/* user accessible mirror of in-kernel sk_buff. + * new fields can only be added to the end of this structure + */ +struct __sk_buff +{ + __u32 len; + __u32 pkt_type; + __u32 mark; + __u32 queue_mapping; + __u32 protocol; + __u32 vlan_present; + __u32 vlan_tci; + __u32 vlan_proto; + __u32 priority; + __u32 ingress_ifindex; + __u32 ifindex; + __u32 tc_index; + __u32 cb[5]; + __u32 hash; + __u32 tc_classid; + __u32 data; + __u32 data_end; + __u32 napi_id; + + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; +}; + +struct bpf_tunnel_key +{ + __u32 tunnel_id; + union { + __u32 remote_ipv4; + __u32 remote_ipv6[4]; + }; + __u8 tunnel_tos; + __u8 tunnel_ttl; + __u16 tunnel_ext; + __u32 tunnel_label; +}; + +/* Generic BPF return codes which all BPF program types may support. + * The values are binary compatible with their TC_ACT_* counter-part to + * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT + * programs. + * + * XDP is handled seprately, see XDP_*. + */ +enum bpf_ret_code +{ + BPF_OK = 0, + /* 1 reserved */ + BPF_DROP = 2, + /* 3-6 reserved */ + BPF_REDIRECT = 7, + /* >127 are reserved for prog type specific return codes */ +}; + +struct bpf_sock +{ + __u32 bound_dev_if; + __u32 family; + __u32 type; + __u32 protocol; + __u32 mark; + __u32 priority; + __u32 src_ip4; /* Allows 1,2,4-byte read. + * Stored in network byte order. + */ + __u32 src_ip6[4]; /* Allows 1,2,4-byte read. + * Stored in network byte order. + */ + __u32 src_port; /* Allows 4-byte read. + * Stored in host byte order + */ +}; + +#define XDP_PACKET_HEADROOM 256 + +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). + */ +enum xdp_action +{ + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, + XDP_REDIRECT, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md +{ + __u32 data; + __u32 data_end; + __u32 data_meta; + /* Below access go through struct xdp_rxq_info */ + __u32 ingress_ifindex; /* rxq->dev->ifindex */ + __u32 rx_queue_index; /* rxq->queue_index */ +}; + +enum sk_action +{ + SK_DROP = 0, + SK_PASS, +}; + +/* user accessible metadata for SK_MSG packet hook, new fields must + * be added to the end of this structure + */ +struct sk_msg_md +{ + void *data; + void *data_end; +}; + +#define BPF_TAG_SIZE 8 + +struct bpf_prog_info +{ + __u32 type; + __u32 id; + __u8 tag[BPF_TAG_SIZE]; + __u32 jited_prog_len; + __u32 xlated_prog_len; + __aligned_u64 jited_prog_insns; + __aligned_u64 xlated_prog_insns; + __u64 load_time; /* ns since boottime */ + __u32 created_by_uid; + __u32 nr_map_ids; + __aligned_u64 map_ids; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 : 32; + __u64 netns_dev; + __u64 netns_ino; +} __attribute__((aligned(8))); + +struct bpf_map_info +{ + __u32 type; + __u32 id; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 map_flags; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 : 32; + __u64 netns_dev; + __u64 netns_ino; +} __attribute__((aligned(8))); + +/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed + * by user and intended to be used by socket (e.g. to bind to, depends on + * attach attach type). + */ +struct bpf_sock_addr +{ + __u32 user_family; /* Allows 4-byte read, but no write. */ + __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. + * Stored in network byte order. + */ + __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 user_port; /* Allows 4-byte read and write. + * Stored in network byte order + */ + __u32 family; /* Allows 4-byte read, but no write */ + __u32 type; /* Allows 4-byte read, but no write */ + __u32 protocol; /* Allows 4-byte read, but no write */ +}; + +/* User bpf_sock_ops struct to access socket values and specify request ops + * and their replies. + * Some of this fields are in network (bigendian) byte order and may need + * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h). + * New fields can only be added at the end of this structure + */ +struct bpf_sock_ops +{ + __u32 op; + union { + __u32 args[4]; /* Optionally passed to bpf program */ + __u32 reply; /* Returned by bpf program */ + __u32 replylong[4]; /* Optionally returned by bpf prog */ + }; + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + __u32 is_fullsock; /* Some TCP fields are only valid if + * there is a full socket. If not, the + * fields read as zero. + */ + __u32 snd_cwnd; + __u32 srtt_us; /* Averaged RTT << 3 in usecs */ + __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */ + __u32 state; + __u32 rtt_min; + __u32 snd_ssthresh; + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u32 mss_cache; + __u32 ecn_flags; + __u32 rate_delivered; + __u32 rate_interval_us; + __u32 packets_out; + __u32 retrans_out; + __u32 total_retrans; + __u32 segs_in; + __u32 data_segs_in; + __u32 segs_out; + __u32 data_segs_out; + __u32 lost_out; + __u32 sacked_out; + __u32 sk_txhash; + __u64 bytes_received; + __u64 bytes_acked; +}; + +/* Definitions for bpf_sock_ops_cb_flags */ +#define BPF_SOCK_OPS_RTO_CB_FLAG (1 << 0) +#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1 << 1) +#define BPF_SOCK_OPS_STATE_CB_FLAG (1 << 2) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently \ + * supported cb flags \ + */ + +/* List of known BPF sock_ops operators. + * New entries can only be added at the end + */ +enum +{ + BPF_SOCK_OPS_VOID, + BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or + * -1 if default value should be used + */ + BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized + * window (in packets) or -1 if default + * value should be used + */ + BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an + * active connection is initialized + */ + BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an + * active connection is + * established + */ + BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a + * passive connection is + * established + */ + BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control + * needs ECN + */ + BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is + * based on the path and may be + * dependent on the congestion control + * algorithm. In general it indicates + * a congestion threshold. RTTs above + * this indicate congestion + */ + BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered. + * Arg1: value of icsk_retransmits + * Arg2: value of icsk_rto + * Arg3: whether RTO has expired + */ + BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted. + * Arg1: sequence number of 1st byte + * Arg2: # segments + * Arg3: return value of + * tcp_transmit_skb (0 => success) + */ + BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state. + * Arg1: old_state + * Arg2: new_state + */ +}; + +/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect + * changes between the TCP and BPF versions. Ideally this should never happen. + * If it does, we need to add code to convert them before calling + * the BPF sock_ops function. + */ +enum +{ + BPF_TCP_ESTABLISHED = 1, + BPF_TCP_SYN_SENT, + BPF_TCP_SYN_RECV, + BPF_TCP_FIN_WAIT1, + BPF_TCP_FIN_WAIT2, + BPF_TCP_TIME_WAIT, + BPF_TCP_CLOSE, + BPF_TCP_CLOSE_WAIT, + BPF_TCP_LAST_ACK, + BPF_TCP_LISTEN, + BPF_TCP_CLOSING, /* Now a valid state */ + BPF_TCP_NEW_SYN_RECV, + + BPF_TCP_MAX_STATES /* Leave at the end! */ +}; + +#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ +#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ + +struct bpf_perf_event_value +{ + __u64 counter; + __u64 enabled; + __u64 running; +}; + +#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) +#define BPF_DEVCG_ACC_READ (1ULL << 1) +#define BPF_DEVCG_ACC_WRITE (1ULL << 2) + +#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) +#define BPF_DEVCG_DEV_CHAR (1ULL << 1) + +struct bpf_cgroup_dev_ctx +{ + /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */ + __u32 access_type; + __u32 major; + __u32 minor; +}; + +struct bpf_raw_tracepoint_args +{ + __u64 args[0]; +}; + +#endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/examples/instruction_patching/ebpf/include/bpf_helpers.h b/examples/instruction_patching/ebpf/include/bpf_helpers.h new file mode 100644 index 0000000..bb4c86b --- /dev/null +++ b/examples/instruction_patching/ebpf/include/bpf_helpers.h @@ -0,0 +1,151 @@ +#ifndef __BPF_HELPERS_H +#define __BPF_HELPERS_H + +#define bpf_printk(fmt, ...) \ + ({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ + }) + +/* helper macro to place programs, maps, license in + * different sections in elf_bpf file. Section names + * are interpreted by elf_bpf loader + */ +#define SEC(NAME) __attribute__((section(NAME), used)) + +/* helper functions called from eBPF programs written in C */ +static void *(*bpf_map_lookup_elem)(void *map, void *key) = + (void *)BPF_FUNC_map_lookup_elem; +static int (*bpf_map_update_elem)(void *map, void *key, void *value, + unsigned long long flags) = + (void *)BPF_FUNC_map_update_elem; +static int (*bpf_map_delete_elem)(void *map, void *key) = + (void *)BPF_FUNC_map_delete_elem; +static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) = + (void *)BPF_FUNC_probe_read; +static unsigned long long (*bpf_ktime_get_ns)(void) = + (void *)BPF_FUNC_ktime_get_ns; +static int (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = + (void *)BPF_FUNC_trace_printk; +static unsigned long long (*bpf_get_smp_processor_id)(void) = + (void *)BPF_FUNC_get_smp_processor_id; +static unsigned long long (*bpf_get_current_pid_tgid)(void) = + (void *)BPF_FUNC_get_current_pid_tgid; +static unsigned long long (*bpf_get_current_uid_gid)(void) = + (void *)BPF_FUNC_get_current_uid_gid; +static int (*bpf_get_current_comm)(void *buf, int buf_size) = + (void *)BPF_FUNC_get_current_comm; +static int (*bpf_perf_event_read)(void *map, int index) = + (void *)BPF_FUNC_perf_event_read; +static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) = + (void *)BPF_FUNC_clone_redirect; +static int (*bpf_redirect)(int ifindex, int flags) = + (void *)BPF_FUNC_redirect; +static int (*bpf_perf_event_output)(void *ctx, void *map, + unsigned long long flags, void *data, + int size) = + (void *)BPF_FUNC_perf_event_output; +static int (*bpf_skb_get_tunnel_key)(void *ctx, void *key, int size, int flags) = + (void *)BPF_FUNC_skb_get_tunnel_key; +static int (*bpf_skb_set_tunnel_key)(void *ctx, void *key, int size, int flags) = + (void *)BPF_FUNC_skb_set_tunnel_key; +static unsigned long long (*bpf_get_prandom_u32)(void) = + (void *)BPF_FUNC_get_prandom_u32; + +/* llvm builtin functions that eBPF C program may use to + * emit BPF_LD_ABS and BPF_LD_IND instructions + */ +struct sk_buff; +unsigned long long load_byte(void *skb, + unsigned long long off) asm("llvm.bpf.load.byte"); +unsigned long long load_half(void *skb, + unsigned long long off) asm("llvm.bpf.load.half"); +unsigned long long load_word(void *skb, + unsigned long long off) asm("llvm.bpf.load.word"); + +/* a helper structure used by eBPF C program + * to describe map attributes to elf_bpf loader + */ +#define BUF_SIZE_MAP_NS 256 + +// struct bpf_map_def +// { +// unsigned int type; +// unsigned int key_size; +// unsigned int value_size; +// unsigned int max_entries; +// unsigned int map_flags; +// unsigned int pinning; +// char namespace[BUF_SIZE_MAP_NS]; +// }; + +static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) = + (void *)BPF_FUNC_skb_store_bytes; +static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) = + (void *)BPF_FUNC_l3_csum_replace; +static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) = + (void *)BPF_FUNC_l4_csum_replace; + +#if defined(__x86_64__) + +#define PT_REGS_PARM1(x) ((x)->di) +#define PT_REGS_PARM2(x) ((x)->si) +#define PT_REGS_PARM3(x) ((x)->dx) +#define PT_REGS_PARM4(x) ((x)->cx) +#define PT_REGS_PARM5(x) ((x)->r8) +#define PT_REGS_RET(x) ((x)->sp) +#define PT_REGS_FP(x) ((x)->bp) +#define PT_REGS_RC(x) ((x)->ax) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->ip) + +#elif defined(__s390x__) + +#define PT_REGS_PARM1(x) ((x)->gprs[2]) +#define PT_REGS_PARM2(x) ((x)->gprs[3]) +#define PT_REGS_PARM3(x) ((x)->gprs[4]) +#define PT_REGS_PARM4(x) ((x)->gprs[5]) +#define PT_REGS_PARM5(x) ((x)->gprs[6]) +#define PT_REGS_RET(x) ((x)->gprs[14]) +#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->gprs[2]) +#define PT_REGS_SP(x) ((x)->gprs[15]) +#define PT_REGS_IP(x) ((x)->ip) + +#elif defined(__aarch64__) + +#define PT_REGS_PARM1(x) ((x)->regs[0]) +#define PT_REGS_PARM2(x) ((x)->regs[1]) +#define PT_REGS_PARM3(x) ((x)->regs[2]) +#define PT_REGS_PARM4(x) ((x)->regs[3]) +#define PT_REGS_PARM5(x) ((x)->regs[4]) +#define PT_REGS_RET(x) ((x)->regs[30]) +#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->regs[0]) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->pc) + +#elif defined(__powerpc__) + +#define PT_REGS_PARM1(x) ((x)->gpr[3]) +#define PT_REGS_PARM2(x) ((x)->gpr[4]) +#define PT_REGS_PARM3(x) ((x)->gpr[5]) +#define PT_REGS_PARM4(x) ((x)->gpr[6]) +#define PT_REGS_PARM5(x) ((x)->gpr[7]) +#define PT_REGS_RC(x) ((x)->gpr[3]) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->nip) + +#endif + +#ifdef __powerpc__ +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP +#else +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ bpf_probe_read(&(ip), sizeof(ip), \ + (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) +#endif + +#endif diff --git a/examples/instruction_patching/ebpf/include/bpf_map.h b/examples/instruction_patching/ebpf/include/bpf_map.h new file mode 100644 index 0000000..71f1157 --- /dev/null +++ b/examples/instruction_patching/ebpf/include/bpf_map.h @@ -0,0 +1,19 @@ +#define BUF_SIZE_MAP_NS 256 + +typedef struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; + unsigned int inner_map_idx; + unsigned int pinning; + char namespace[BUF_SIZE_MAP_NS]; +} bpf_map_def; + +enum bpf_pin_type { + PIN_NONE = 0, + PIN_OBJECT_NS, + PIN_GLOBAL_NS, + PIN_CUSTOM_NS, +}; diff --git a/examples/instruction_patching/ebpf/main.c b/examples/instruction_patching/ebpf/main.c new file mode 100644 index 0000000..1be313e --- /dev/null +++ b/examples/instruction_patching/ebpf/main.c @@ -0,0 +1,15 @@ +#include "include/bpf.h" +#include "include/bpf_map.h" +#include "include/bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + + +static void *(*bpf_patch)(unsigned long,...) = (void *)-1; + +SEC("kprobe/security_socket_create") +int kprobe__security_socket_create(void *ctx) { + int ret = 0; + bpf_patch(ret); + return 1; +} \ No newline at end of file diff --git a/examples/instruction_patching/main.go b/examples/instruction_patching/main.go new file mode 100644 index 0000000..9a87af8 --- /dev/null +++ b/examples/instruction_patching/main.go @@ -0,0 +1,122 @@ +package main + +import ( + _ "embed" + "fmt" + "github.com/cilium/ebpf" + "github.com/cilium/ebpf/asm" + "github.com/sirupsen/logrus" + "log" + "time" + + manager "github.com/gojue/ebpfmanager" +) + +var Probe []byte + +const eBPFFuncName = "kprobe__security_socket_create" +const eBPFAsmValue = 255 + +var m1 = &manager.Manager{ + Probes: []*manager.Probe{ + { + UID: "MyFirstHook", + Section: "kprobe/vfs_mkdir", + AttachToFuncName: "vfs_mkdir", + EbpfFuncName: eBPFFuncName, + }, + }, + InstructionPatchers: []manager.InstructionPatcherFunc{patchBPFTelemetry}, +} + +const BPFTelemetryPatchCall = -1 + +func getAllProgramSpecs(m *manager.Manager) ([]*ebpf.ProgramSpec, error) { + var specs []*ebpf.ProgramSpec + for _, p := range m.Probes { + oldID := manager.ProbeIdentificationPair{p.UID, p.EbpfFuncName} + s, present, err := m.GetProgramSpec(oldID) + if err != nil { + return nil, err + } + if !present { + return nil, fmt.Errorf("could not find ProgramSpec for probe %v", oldID) + } + + specs = append(specs, s...) + } + + return specs, nil +} + +func patchBPFTelemetry(m *manager.Manager) error { + specs, err := getAllProgramSpecs(m) + if err != nil { + return err + } + for _, spec := range specs { + if spec == nil { + continue + } + iter := spec.Instructions.Iterate() + for iter.Next() { + ins := iter.Ins + + if !ins.IsBuiltinCall() { + continue + } + + if ins.Constant != BPFTelemetryPatchCall { + continue + } + *ins = asm.Mov.Imm(asm.R1, int32(eBPFAsmValue)).WithMetadata(ins.Metadata) + } + } + + return nil +} + +func main() { + if err := run(); err != nil { + log.Fatal(err) + } +} + +func run() error { + if err := m1.Init(recoverAssets()); err != nil { + return err + } + defer func() { + if err := m1.Stop(manager.CleanAll); err != nil { + log.Print(err) + } + }() + + if err := m1.Start(); err != nil { + return err + } + + log.Println("=> Use 'bpftool prog dump xlated id ' to verify that the instruction has been patched") + log.Println("=> Enter to exit") + // check output with `bpftool prog dump xlated id ` + /* + root@vm-ubuntu-arm64:/home/cfc4n# bpftool prog dump xlated id 664 + 0: (b7) r1 = 0 + 1: (b7) r1 = 255 + 2: (b7) r0 = 1 + 3: (95) exit + */ + // wait for eBPF program to be loaded + time.Sleep(time.Second * 3) + + err := check(eBPFFuncName) + + if err != nil { + logrus.Errorf("failed to check eBPF program: %v", err) + } + if err = m1.Stop(manager.CleanAll); err != nil { + logrus.Fatal(err) + } + log.Println("=> Stopped the manager") + return nil +} diff --git a/examples/instruction_patching/probe.go b/examples/instruction_patching/probe.go new file mode 100644 index 0000000..3675696 --- /dev/null +++ b/examples/instruction_patching/probe.go @@ -0,0 +1,276 @@ +// Code generated by go-bindata. DO NOT EDIT. +// sources: +// ebpf/bin/probe.o + +package main + + +import ( + "bytes" + "compress/gzip" + "fmt" + "io" + "io/ioutil" + "os" + "path/filepath" + "strings" + "time" +) + +func bindataRead(data []byte, name string) ([]byte, error) { + gz, err := gzip.NewReader(bytes.NewBuffer(data)) + if err != nil { + return nil, fmt.Errorf("Read %q: %v", name, err) + } + + var buf bytes.Buffer + _, err = io.Copy(&buf, gz) + clErr := gz.Close() + + if err != nil { + return nil, fmt.Errorf("Read %q: %v", name, err) + } + if clErr != nil { + return nil, err + } + + return buf.Bytes(), nil +} + + +type asset struct { + bytes []byte + info fileInfoEx +} + +type fileInfoEx interface { + os.FileInfo + MD5Checksum() string +} + +type bindataFileInfo struct { + name string + size int64 + mode os.FileMode + modTime time.Time + md5checksum string +} + +func (fi bindataFileInfo) Name() string { + return fi.name +} +func (fi bindataFileInfo) Size() int64 { + return fi.size +} +func (fi bindataFileInfo) Mode() os.FileMode { + return fi.mode +} +func (fi bindataFileInfo) ModTime() time.Time { + return fi.modTime +} +func (fi bindataFileInfo) MD5Checksum() string { + return fi.md5checksum +} +func (fi bindataFileInfo) IsDir() bool { + return false +} +func (fi bindataFileInfo) Sys() interface{} { + return nil +} + +var _bindataProbeO = []byte("\x1f\x8b\x08\x00\x00\x00\x00\x00\x00\xff\xac\x53\xb1\x4e\xc3\x30\x10\x7d\x6e\x02\x04\xc1\x50\x98\x18\x18\x3a\x31\x1a\x3e\xa1\x03\x85\xa5\x48\xc0\xca\x60\x92\xe8\x50\x43\x9b\x16\x39\x46\x6a\x11\x12\x13\x9f\x80\xd4\x3f\xe9\x77\x31\x31\x06\x25\x3a\x53\xcb\x4d\xd4\x85\x27\x5d\x5f\xef\x5d\xce\xcf\xce\x39\x1f\x83\xe1\x55\x47\x08\x58\x08\xfc\x60\x9d\xad\xb1\x74\xc4\x3e\xff\x46\x10\x58\xb1\xfe\x09\xa0\x2c\xcb\x72\x55\xaf\x01\x7c\xf1\xb3\xd7\xb7\xc3\x9a\xbb\x76\xfd\xb7\x7b\x44\xef\x07\xe2\x10\xc0\x09\x87\x45\xaf\xc1\xd7\xc7\x03\x80\x10\xdf\x65\x53\x2d\x40\xb0\xa1\xed\x01\x38\x76\x74\xeb\x71\x09\xe0\x08\xe1\x9f\x6e\xff\x9d\x32\x77\x38\x20\x0d\xcd\x0d\xc6\x2f\x7a\x96\x90\x52\x05\xa5\xaf\x3a\x33\x0b\x55\xcc\xd2\x31\x19\x95\x6a\x8a\x0d\x71\xf9\xbc\xa5\xaa\x26\x59\x4a\xd3\x82\x20\x35\x4d\x24\x8d\xd4\x93\x8e\x73\x42\x1e\x67\x53\x99\x42\x16\x46\x9b\x38\x81\x2c\x16\x79\xc5\xff\x83\xa4\x7e\x1f\x9b\xe8\xf1\xbc\xb4\xa7\xfb\x33\x17\x1c\xbb\x9e\xde\x6f\xf1\x0b\xbd\xfc\x6c\x4b\xbf\x3f\xeb\xc8\xcb\x07\xdc\xef\x9f\xe1\xb1\xc5\xcf\xdf\xff\x1d\x6b\x1d\x4f\x1f\x31\x5f\x6c\xf1\xbf\x01\xb0\xdf\x70\xde\x2e\x1b\xd9\xfb\x5c\xdd\xaf\x1d\xa7\xdf\xea\xcf\x0d\xde\x15\x96\xcc\x73\x67\xdf\x81\xd3\x6f\xbf\x87\xdf\x00\x00\x00\xff\xff\x20\xd9\x34\xf2\x98\x03\x00\x00") + +func bindataProbeOBytes() ([]byte, error) { + return bindataRead( + _bindataProbeO, + "/probe.o", + ) +} + + + +func bindataProbeO() (*asset, error) { + bytes, err := bindataProbeOBytes() + if err != nil { + return nil, err + } + + info := bindataFileInfo{ + name: "/probe.o", + size: 920, + md5checksum: "", + mode: os.FileMode(436), + modTime: time.Unix(1706883532, 0), + } + + a := &asset{bytes: bytes, info: info} + + return a, nil +} + + +// +// Asset loads and returns the asset for the given name. +// It returns an error if the asset could not be found or +// could not be loaded. +// +func Asset(name string) ([]byte, error) { + cannonicalName := strings.Replace(name, "\\", "/", -1) + if f, ok := _bindata[cannonicalName]; ok { + a, err := f() + if err != nil { + return nil, fmt.Errorf("Asset %s can't read by error: %v", name, err) + } + return a.bytes, nil + } + return nil, &os.PathError{Op: "open", Path: name, Err: os.ErrNotExist} +} + +// +// MustAsset is like Asset but panics when Asset would return an error. +// It simplifies safe initialization of global variables. +// nolint: deadcode +// +func MustAsset(name string) []byte { + a, err := Asset(name) + if err != nil { + panic("asset: Asset(" + name + "): " + err.Error()) + } + + return a +} + +// +// AssetInfo loads and returns the asset info for the given name. +// It returns an error if the asset could not be found or could not be loaded. +// +func AssetInfo(name string) (os.FileInfo, error) { + cannonicalName := strings.Replace(name, "\\", "/", -1) + if f, ok := _bindata[cannonicalName]; ok { + a, err := f() + if err != nil { + return nil, fmt.Errorf("AssetInfo %s can't read by error: %v", name, err) + } + return a.info, nil + } + return nil, &os.PathError{Op: "open", Path: name, Err: os.ErrNotExist} +} + +// +// AssetNames returns the names of the assets. +// nolint: deadcode +// +func AssetNames() []string { + names := make([]string, 0, len(_bindata)) + for name := range _bindata { + names = append(names, name) + } + return names +} + +// +// _bindata is a table, holding each asset generator, mapped to its name. +// +var _bindata = map[string]func() (*asset, error){ + "/probe.o": bindataProbeO, +} + +// +// AssetDir returns the file names below a certain +// directory embedded in the file by go-bindata. +// For example if you run go-bindata on data/... and data contains the +// following hierarchy: +// data/ +// foo.txt +// img/ +// a.png +// b.png +// then AssetDir("data") would return []string{"foo.txt", "img"} +// AssetDir("data/img") would return []string{"a.png", "b.png"} +// AssetDir("foo.txt") and AssetDir("notexist") would return an error +// AssetDir("") will return []string{"data"}. +// +func AssetDir(name string) ([]string, error) { + node := _bintree + if len(name) != 0 { + cannonicalName := strings.Replace(name, "\\", "/", -1) + pathList := strings.Split(cannonicalName, "/") + for _, p := range pathList { + node = node.Children[p] + if node == nil { + return nil, &os.PathError{ + Op: "open", + Path: name, + Err: os.ErrNotExist, + } + } + } + } + if node.Func != nil { + return nil, &os.PathError{ + Op: "open", + Path: name, + Err: os.ErrNotExist, + } + } + rv := make([]string, 0, len(node.Children)) + for childName := range node.Children { + rv = append(rv, childName) + } + return rv, nil +} + + +type bintree struct { + Func func() (*asset, error) + Children map[string]*bintree +} + +var _bintree = &bintree{Func: nil, Children: map[string]*bintree{ + "": {Func: nil, Children: map[string]*bintree{ + "probe.o": {Func: bindataProbeO, Children: map[string]*bintree{}}, + }}, +}} + +// RestoreAsset restores an asset under the given directory +func RestoreAsset(dir, name string) error { + data, err := Asset(name) + if err != nil { + return err + } + info, err := AssetInfo(name) + if err != nil { + return err + } + err = os.MkdirAll(_filePath(dir, filepath.Dir(name)), os.FileMode(0755)) + if err != nil { + return err + } + err = ioutil.WriteFile(_filePath(dir, name), data, info.Mode()) + if err != nil { + return err + } + return os.Chtimes(_filePath(dir, name), info.ModTime(), info.ModTime()) +} + +// RestoreAssets restores an asset under the given directory recursively +func RestoreAssets(dir, name string) error { + children, err := AssetDir(name) + // File + if err != nil { + return RestoreAsset(dir, name) + } + // Dir + for _, child := range children { + err = RestoreAssets(dir, filepath.Join(name, child)) + if err != nil { + return err + } + } + return nil +} + +func _filePath(dir, name string) string { + cannonicalName := strings.Replace(name, "\\", "/", -1) + return filepath.Join(append([]string{dir}, strings.Split(cannonicalName, "/")...)...) +} diff --git a/examples/instruction_patching/utils.go b/examples/instruction_patching/utils.go new file mode 100644 index 0000000..a3e7aa9 --- /dev/null +++ b/examples/instruction_patching/utils.go @@ -0,0 +1,95 @@ +package main + +import ( + "bytes" + "encoding/binary" + "fmt" + "io" + "os" + "os/exec" + "os/signal" + "strings" + "time" + "unsafe" + + "github.com/sirupsen/logrus" +) + +// ByteOrder - host byte order +var ByteOrder binary.ByteOrder + +const ( + //BpfProgShowProgramId = "bpftool prog show name %s |grep %s |awk -F ':' '{print $1}'" + BpfProgShowProgramId = "prog show name %s |grep %s |awk -F ':' '{print $1}'" + BpfProgDumpXlatedId = "prog dump xlated id %s" + BpfAsmCode = "r1 = %d" +) + +func init() { + ByteOrder = getHostByteOrder() +} + +// getHostByteOrder - Returns the host byte order +func getHostByteOrder() binary.ByteOrder { + var i int32 = 0x01020304 + u := unsafe.Pointer(&i) + pb := (*byte)(u) + b := *pb + if b == 0x04 { + return binary.LittleEndian + } + + return binary.BigEndian +} + +// recoverAssets - Recover ebpf asset +func recoverAssets() io.ReaderAt { + buf, err := Asset("/probe.o") + if err != nil { + logrus.Fatal(fmt.Errorf("error:%v, %s", err, "couldn't find asset")) + } + return bytes.NewReader(buf) +} + +func check(progName string) error { + if len(progName) >= 15 { + progName = progName[:15] + } + var c = exec.Command("bpftool", "prog", "show", "name", progName) + logrus.Println("executing command:", c.String()) + output, err := c.Output() + if err != nil { + return fmt.Errorf("executing command:%s, error:%v", c.String(), err) + } + outputStr := string(output) + var outArrs = strings.Split(outputStr, ":") + if len(outArrs) < 2 { + return fmt.Errorf("failed to find prog id in output:%s", outputStr) + } + var progId = outArrs[0] + logrus.Println("output:", progId) + c = exec.Command("bpftool", "prog", "dump", "xlated", "id", progId) + logrus.Println("executing command:", c.String()) + output, err = c.Output() + if err != nil { + return fmt.Errorf("executing command:%s, error:%v", c.String(), err) + } + outputStr = string(output) + logrus.Printf("output:%s", outputStr) + var asmCode = fmt.Sprintf(BpfAsmCode, eBPFAsmValue) + if !strings.Contains(outputStr, asmCode) { + logrus.Fatalf("failed to find asm code:%s in output:%s", asmCode, outputStr) + } + logrus.Println("found asm code:", asmCode) + return nil +} + +func wait() { + logrus.Println("run next testcase after 3 second") + time.Sleep(time.Second * 3) + //return + sig := make(chan os.Signal, 1) + signal.Notify(sig, os.Interrupt, os.Kill) + <-sig + fmt.Println() +} diff --git a/manager.go b/manager.go index 9361f52..a7e6683 100644 --- a/manager.go +++ b/manager.go @@ -237,6 +237,10 @@ type netlinkCacheValue struct { schedClsCount int } +// InstructionPatcherFunc - A function that patches the instructions of a program +// more info https://github.com/DataDog/ebpf-manager/blob/main/manager.go#L158 +type InstructionPatcherFunc func(m *Manager) error + // Manager - Helper structure that manages multiple eBPF programs and maps type Manager struct { wg *sync.WaitGroup @@ -258,6 +262,10 @@ type Manager struct { PerfMaps []*PerfMap RingbufMaps []*RingbufMap + + // InstructionPatchers - Callback functions called before loading probes, to + // provide user the ability to perform last minute instruction patching. + InstructionPatchers []InstructionPatcherFunc } // DumpMaps - Return a string containing human readable info about eBPF maps @@ -526,7 +534,11 @@ func (m *Manager) InitWithOptions(elf io.ReaderAt, options Options) error { m.activateProbes() m.state = initialized m.stateLock.Unlock() - + resetManager := func(m *Manager) { + m.stateLock.Lock() + m.state = reset + m.stateLock.Unlock() + } // Edit program constants if len(options.ConstantEditors) > 0 { if err := m.editConstants(); err != nil { @@ -548,6 +560,14 @@ func (m *Manager) InitWithOptions(elf io.ReaderAt, options Options) error { } } + // Patch instructions + for _, patcher := range m.InstructionPatchers { + if err := patcher(m); err != nil { + resetManager(m) + return err + } + } + // Load pinned maps and pinned programs to avoid loading them twice if err := m.loadPinnedObjects(); err != nil { return err