File: bpf-direct.c

package info (click to toggle)
linux 4.19.20-1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, buster, sid
  • size: 954,852 kB
  • sloc: ansic: 16,749,828; asm: 271,286; makefile: 38,257; sh: 32,808; perl: 27,671; python: 21,022; cpp: 5,063; yacc: 4,648; lex: 2,585; awk: 1,385; ruby: 25; sed: 5
file content (191 lines) | stat: -rw-r--r-- 5,029 bytes parent folder | download | duplicates (9)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
// SPDX-License-Identifier: GPL-2.0
/*
 * Seccomp filter example for x86 (32-bit and 64-bit) with BPF macros
 *
 * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
 * Author: Will Drewry <wad@chromium.org>
 *
 * The code may be used by anyone for any purpose,
 * and can serve as a starting point for developing
 * applications using prctl(PR_SET_SECCOMP, 2, ...).
 */
#if defined(__i386__) || defined(__x86_64__)
#define SUPPORTED_ARCH 1
#endif

#if defined(SUPPORTED_ARCH)
#define __USE_GNU 1
#define _GNU_SOURCE 1

#include <linux/types.h>
#include <linux/filter.h>
#include <linux/seccomp.h>
#include <linux/unistd.h>
#include <signal.h>
#include <stdio.h>
#include <stddef.h>
#include <string.h>
#include <sys/prctl.h>
#include <unistd.h>

#define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]))
#define syscall_nr (offsetof(struct seccomp_data, nr))

#if defined(__i386__)
#define REG_RESULT	REG_EAX
#define REG_SYSCALL	REG_EAX
#define REG_ARG0	REG_EBX
#define REG_ARG1	REG_ECX
#define REG_ARG2	REG_EDX
#define REG_ARG3	REG_ESI
#define REG_ARG4	REG_EDI
#define REG_ARG5	REG_EBP
#elif defined(__x86_64__)
#define REG_RESULT	REG_RAX
#define REG_SYSCALL	REG_RAX
#define REG_ARG0	REG_RDI
#define REG_ARG1	REG_RSI
#define REG_ARG2	REG_RDX
#define REG_ARG3	REG_R10
#define REG_ARG4	REG_R8
#define REG_ARG5	REG_R9
#endif

#ifndef PR_SET_NO_NEW_PRIVS
#define PR_SET_NO_NEW_PRIVS 38
#endif

#ifndef SYS_SECCOMP
#define SYS_SECCOMP 1
#endif

static void emulator(int nr, siginfo_t *info, void *void_context)
{
	ucontext_t *ctx = (ucontext_t *)(void_context);
	int syscall;
	char *buf;
	ssize_t bytes;
	size_t len;
	if (info->si_code != SYS_SECCOMP)
		return;
	if (!ctx)
		return;
	syscall = ctx->uc_mcontext.gregs[REG_SYSCALL];
	buf = (char *) ctx->uc_mcontext.gregs[REG_ARG1];
	len = (size_t) ctx->uc_mcontext.gregs[REG_ARG2];

	if (syscall != __NR_write)
		return;
	if (ctx->uc_mcontext.gregs[REG_ARG0] != STDERR_FILENO)
		return;
	/* Redirect stderr messages to stdout. Doesn't handle EINTR, etc */
	ctx->uc_mcontext.gregs[REG_RESULT] = -1;
	if (write(STDOUT_FILENO, "[ERR] ", 6) > 0) {
		bytes = write(STDOUT_FILENO, buf, len);
		ctx->uc_mcontext.gregs[REG_RESULT] = bytes;
	}
	return;
}

static int install_emulator(void)
{
	struct sigaction act;
	sigset_t mask;
	memset(&act, 0, sizeof(act));
	sigemptyset(&mask);
	sigaddset(&mask, SIGSYS);

	act.sa_sigaction = &emulator;
	act.sa_flags = SA_SIGINFO;
	if (sigaction(SIGSYS, &act, NULL) < 0) {
		perror("sigaction");
		return -1;
	}
	if (sigprocmask(SIG_UNBLOCK, &mask, NULL)) {
		perror("sigprocmask");
		return -1;
	}
	return 0;
}

static int install_filter(void)
{
	struct sock_filter filter[] = {
		/* Grab the system call number */
		BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_nr),
		/* Jump table for the allowed syscalls */
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_rt_sigreturn, 0, 1),
		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
#ifdef __NR_sigreturn
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_sigreturn, 0, 1),
		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
#endif
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_exit_group, 0, 1),
		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_exit, 0, 1),
		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_read, 1, 0),
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_write, 3, 2),

		/* Check that read is only using stdin. */
		BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)),
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDIN_FILENO, 4, 0),
		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL),

		/* Check that write is only using stdout */
		BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)),
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDOUT_FILENO, 1, 0),
		/* Trap attempts to write to stderr */
		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDERR_FILENO, 1, 2),

		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_TRAP),
		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL),
	};
	struct sock_fprog prog = {
		.len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
		.filter = filter,
	};

	if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
		perror("prctl(NO_NEW_PRIVS)");
		return 1;
	}


	if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog)) {
		perror("prctl");
		return 1;
	}
	return 0;
}

#define payload(_c) (_c), sizeof((_c))
int main(int argc, char **argv)
{
	char buf[4096];
	ssize_t bytes = 0;
	if (install_emulator())
		return 1;
	if (install_filter())
		return 1;
	syscall(__NR_write, STDOUT_FILENO,
		payload("OHAI! WHAT IS YOUR NAME? "));
	bytes = syscall(__NR_read, STDIN_FILENO, buf, sizeof(buf));
	syscall(__NR_write, STDOUT_FILENO, payload("HELLO, "));
	syscall(__NR_write, STDOUT_FILENO, buf, bytes);
	syscall(__NR_write, STDERR_FILENO,
		payload("Error message going to STDERR\n"));
	return 0;
}
#else	/* SUPPORTED_ARCH */
/*
 * This sample is x86-only.  Since kernel samples are compiled with the
 * host toolchain, a non-x86 host will result in using only the main()
 * below.
 */
int main(void)
{
	return 1;
}
#endif	/* SUPPORTED_ARCH */