// https://syzkaller.appspot.com/bug?id=c8bf60517e72e9d86942fe6666ea7fb94f76d492 // autogenerated by syzkaller (https://github.com/google/syzkaller) #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #ifndef __NR_memfd_create #define __NR_memfd_create 279 #endif #ifndef __NR_mmap #define __NR_mmap 222 #endif #ifndef __NR_mount #define __NR_mount 40 #endif #ifndef __NR_pivot_root #define __NR_pivot_root 41 #endif static unsigned long long procid; static __thread int clone_ongoing; static __thread int skip_segv; static __thread jmp_buf segv_env; static void segv_handler(int sig, siginfo_t* info, void* ctx) { if (__atomic_load_n(&clone_ongoing, __ATOMIC_RELAXED) != 0) { exit(sig); } uintptr_t addr = (uintptr_t)info->si_addr; const uintptr_t prog_start = 1 << 20; const uintptr_t prog_end = 100 << 20; int skip = __atomic_load_n(&skip_segv, __ATOMIC_RELAXED) != 0; int valid = addr < prog_start || addr > prog_end; if (skip && valid) { _longjmp(segv_env, 1); } exit(sig); } static void install_segv_handler(void) { struct sigaction sa; memset(&sa, 0, sizeof(sa)); sa.sa_handler = SIG_IGN; syscall(SYS_rt_sigaction, 0x20, &sa, NULL, 8); syscall(SYS_rt_sigaction, 0x21, &sa, NULL, 8); memset(&sa, 0, sizeof(sa)); sa.sa_sigaction = segv_handler; sa.sa_flags = SA_NODEFER | SA_SIGINFO; sigaction(SIGSEGV, &sa, NULL); sigaction(SIGBUS, &sa, NULL); } #define NONFAILING(...) \ ({ \ int ok = 1; \ __atomic_fetch_add(&skip_segv, 1, __ATOMIC_SEQ_CST); \ if (_setjmp(segv_env) == 0) { \ __VA_ARGS__; \ } else \ ok = 0; \ __atomic_fetch_sub(&skip_segv, 1, __ATOMIC_SEQ_CST); \ ok; \ }) static void sleep_ms(uint64_t ms) { usleep(ms * 1000); } static uint64_t current_time_ms(void) { struct timespec ts; if (clock_gettime(CLOCK_MONOTONIC, &ts)) exit(1); return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000; } static void use_temporary_dir(void) { char tmpdir_template[] = "./syzkaller.XXXXXX"; char* tmpdir = mkdtemp(tmpdir_template); if (!tmpdir) exit(1); if (chmod(tmpdir, 0777)) exit(1); if (chdir(tmpdir)) exit(1); } static void thread_start(void* (*fn)(void*), void* arg) { pthread_t th; pthread_attr_t attr; pthread_attr_init(&attr); pthread_attr_setstacksize(&attr, 128 << 10); int i = 0; for (; i < 100; i++) { if (pthread_create(&th, &attr, fn, arg) == 0) { pthread_attr_destroy(&attr); return; } if (errno == EAGAIN) { usleep(50); continue; } break; } exit(1); } typedef struct { int state; } event_t; static void event_init(event_t* ev) { ev->state = 0; } static void event_reset(event_t* ev) { ev->state = 0; } static void event_set(event_t* ev) { if (ev->state) exit(1); __atomic_store_n(&ev->state, 1, __ATOMIC_RELEASE); syscall(SYS_futex, &ev->state, FUTEX_WAKE | FUTEX_PRIVATE_FLAG, 1000000); } static void event_wait(event_t* ev) { while (!__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE)) syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, 0); } static int event_isset(event_t* ev) { return __atomic_load_n(&ev->state, __ATOMIC_ACQUIRE); } static int event_timedwait(event_t* ev, uint64_t timeout) { uint64_t start = current_time_ms(); uint64_t now = start; for (;;) { uint64_t remain = timeout - (now - start); struct timespec ts; ts.tv_sec = remain / 1000; ts.tv_nsec = (remain % 1000) * 1000 * 1000; syscall(SYS_futex, &ev->state, FUTEX_WAIT | FUTEX_PRIVATE_FLAG, 0, &ts); if (__atomic_load_n(&ev->state, __ATOMIC_ACQUIRE)) return 1; now = current_time_ms(); if (now - start > timeout) return 0; } } static bool write_file(const char* file, const char* what, ...) { char buf[1024]; va_list args; va_start(args, what); vsnprintf(buf, sizeof(buf), what, args); va_end(args); buf[sizeof(buf) - 1] = 0; int len = strlen(buf); int fd = open(file, O_WRONLY | O_CLOEXEC); if (fd == -1) return false; if (write(fd, buf, len) != len) { int err = errno; close(fd); errno = err; return false; } close(fd); return true; } #define MAX_FDS 30 //% This code is derived from puff.{c,h}, found in the zlib development. The //% original files come with the following copyright notice: //% Copyright (C) 2002-2013 Mark Adler, all rights reserved //% version 2.3, 21 Jan 2013 //% This software is provided 'as-is', without any express or implied //% warranty. In no event will the author be held liable for any damages //% arising from the use of this software. //% Permission is granted to anyone to use this software for any purpose, //% including commercial applications, and to alter it and redistribute it //% freely, subject to the following restrictions: //% 1. The origin of this software must not be misrepresented; you must not //% claim that you wrote the original software. If you use this software //% in a product, an acknowledgment in the product documentation would be //% appreciated but is not required. //% 2. Altered source versions must be plainly marked as such, and must not be //% misrepresented as being the original software. //% 3. This notice may not be removed or altered from any source distribution. //% Mark Adler madler@alumni.caltech.edu //% BEGIN CODE DERIVED FROM puff.{c,h} #define MAXBITS 15 #define MAXLCODES 286 #define MAXDCODES 30 #define MAXCODES (MAXLCODES + MAXDCODES) #define FIXLCODES 288 struct puff_state { unsigned char* out; unsigned long outlen; unsigned long outcnt; const unsigned char* in; unsigned long inlen; unsigned long incnt; int bitbuf; int bitcnt; jmp_buf env; }; static int puff_bits(struct puff_state* s, int need) { long val = s->bitbuf; while (s->bitcnt < need) { if (s->incnt == s->inlen) longjmp(s->env, 1); val |= (long)(s->in[s->incnt++]) << s->bitcnt; s->bitcnt += 8; } s->bitbuf = (int)(val >> need); s->bitcnt -= need; return (int)(val & ((1L << need) - 1)); } static int puff_stored(struct puff_state* s) { s->bitbuf = 0; s->bitcnt = 0; if (s->incnt + 4 > s->inlen) return 2; unsigned len = s->in[s->incnt++]; len |= s->in[s->incnt++] << 8; if (s->in[s->incnt++] != (~len & 0xff) || s->in[s->incnt++] != ((~len >> 8) & 0xff)) return -2; if (s->incnt + len > s->inlen) return 2; if (s->outcnt + len > s->outlen) return 1; for (; len--; s->outcnt++, s->incnt++) { if (s->in[s->incnt]) s->out[s->outcnt] = s->in[s->incnt]; } return 0; } struct puff_huffman { short* count; short* symbol; }; static int puff_decode(struct puff_state* s, const struct puff_huffman* h) { int first = 0; int index = 0; int bitbuf = s->bitbuf; int left = s->bitcnt; int code = first = index = 0; int len = 1; short* next = h->count + 1; while (1) { while (left--) { code |= bitbuf & 1; bitbuf >>= 1; int count = *next++; if (code - count < first) { s->bitbuf = bitbuf; s->bitcnt = (s->bitcnt - len) & 7; return h->symbol[index + (code - first)]; } index += count; first += count; first <<= 1; code <<= 1; len++; } left = (MAXBITS + 1) - len; if (left == 0) break; if (s->incnt == s->inlen) longjmp(s->env, 1); bitbuf = s->in[s->incnt++]; if (left > 8) left = 8; } return -10; } static int puff_construct(struct puff_huffman* h, const short* length, int n) { int len; for (len = 0; len <= MAXBITS; len++) h->count[len] = 0; int symbol; for (symbol = 0; symbol < n; symbol++) (h->count[length[symbol]])++; if (h->count[0] == n) return 0; int left = 1; for (len = 1; len <= MAXBITS; len++) { left <<= 1; left -= h->count[len]; if (left < 0) return left; } short offs[MAXBITS + 1]; offs[1] = 0; for (len = 1; len < MAXBITS; len++) offs[len + 1] = offs[len] + h->count[len]; for (symbol = 0; symbol < n; symbol++) if (length[symbol] != 0) h->symbol[offs[length[symbol]]++] = symbol; return left; } static int puff_codes(struct puff_state* s, const struct puff_huffman* lencode, const struct puff_huffman* distcode) { static const short lens[29] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258}; static const short lext[29] = {0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0}; static const short dists[30] = { 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, 8193, 12289, 16385, 24577}; static const short dext[30] = {0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13}; int symbol; do { symbol = puff_decode(s, lencode); if (symbol < 0) return symbol; if (symbol < 256) { if (s->outcnt == s->outlen) return 1; if (symbol) s->out[s->outcnt] = symbol; s->outcnt++; } else if (symbol > 256) { symbol -= 257; if (symbol >= 29) return -10; int len = lens[symbol] + puff_bits(s, lext[symbol]); symbol = puff_decode(s, distcode); if (symbol < 0) return symbol; unsigned dist = dists[symbol] + puff_bits(s, dext[symbol]); if (dist > s->outcnt) return -11; if (s->outcnt + len > s->outlen) return 1; while (len--) { if (dist <= s->outcnt && s->out[s->outcnt - dist]) s->out[s->outcnt] = s->out[s->outcnt - dist]; s->outcnt++; } } } while (symbol != 256); return 0; } static int puff_fixed(struct puff_state* s) { static int virgin = 1; static short lencnt[MAXBITS + 1], lensym[FIXLCODES]; static short distcnt[MAXBITS + 1], distsym[MAXDCODES]; static struct puff_huffman lencode, distcode; if (virgin) { lencode.count = lencnt; lencode.symbol = lensym; distcode.count = distcnt; distcode.symbol = distsym; short lengths[FIXLCODES]; int symbol; for (symbol = 0; symbol < 144; symbol++) lengths[symbol] = 8; for (; symbol < 256; symbol++) lengths[symbol] = 9; for (; symbol < 280; symbol++) lengths[symbol] = 7; for (; symbol < FIXLCODES; symbol++) lengths[symbol] = 8; puff_construct(&lencode, lengths, FIXLCODES); for (symbol = 0; symbol < MAXDCODES; symbol++) lengths[symbol] = 5; puff_construct(&distcode, lengths, MAXDCODES); virgin = 0; } return puff_codes(s, &lencode, &distcode); } static int puff_dynamic(struct puff_state* s) { static const short order[19] = {16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; int nlen = puff_bits(s, 5) + 257; int ndist = puff_bits(s, 5) + 1; int ncode = puff_bits(s, 4) + 4; if (nlen > MAXLCODES || ndist > MAXDCODES) return -3; short lengths[MAXCODES]; int index; for (index = 0; index < ncode; index++) lengths[order[index]] = puff_bits(s, 3); for (; index < 19; index++) lengths[order[index]] = 0; short lencnt[MAXBITS + 1], lensym[MAXLCODES]; struct puff_huffman lencode = {lencnt, lensym}; int err = puff_construct(&lencode, lengths, 19); if (err != 0) return -4; index = 0; while (index < nlen + ndist) { int symbol; int len; symbol = puff_decode(s, &lencode); if (symbol < 0) return symbol; if (symbol < 16) lengths[index++] = symbol; else { len = 0; if (symbol == 16) { if (index == 0) return -5; len = lengths[index - 1]; symbol = 3 + puff_bits(s, 2); } else if (symbol == 17) symbol = 3 + puff_bits(s, 3); else symbol = 11 + puff_bits(s, 7); if (index + symbol > nlen + ndist) return -6; while (symbol--) lengths[index++] = len; } } if (lengths[256] == 0) return -9; err = puff_construct(&lencode, lengths, nlen); if (err && (err < 0 || nlen != lencode.count[0] + lencode.count[1])) return -7; short distcnt[MAXBITS + 1], distsym[MAXDCODES]; struct puff_huffman distcode = {distcnt, distsym}; err = puff_construct(&distcode, lengths + nlen, ndist); if (err && (err < 0 || ndist != distcode.count[0] + distcode.count[1])) return -8; return puff_codes(s, &lencode, &distcode); } static int puff(unsigned char* dest, unsigned long* destlen, const unsigned char* source, unsigned long sourcelen) { struct puff_state s = { .out = dest, .outlen = *destlen, .outcnt = 0, .in = source, .inlen = sourcelen, .incnt = 0, .bitbuf = 0, .bitcnt = 0, }; int err; if (setjmp(s.env) != 0) err = 2; else { int last; do { last = puff_bits(&s, 1); int type = puff_bits(&s, 2); err = type == 0 ? puff_stored(&s) : (type == 1 ? puff_fixed(&s) : (type == 2 ? puff_dynamic(&s) : -1)); if (err != 0) break; } while (!last); } *destlen = s.outcnt; return err; } //% END CODE DERIVED FROM puff.{c,h} #define ZLIB_HEADER_WIDTH 2 static int puff_zlib_to_file(const unsigned char* source, unsigned long sourcelen, int dest_fd) { if (sourcelen < ZLIB_HEADER_WIDTH) return 0; source += ZLIB_HEADER_WIDTH; sourcelen -= ZLIB_HEADER_WIDTH; const unsigned long max_destlen = 132 << 20; void* ret = mmap(0, max_destlen, PROT_WRITE | PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); if (ret == MAP_FAILED) return -1; unsigned char* dest = (unsigned char*)ret; unsigned long destlen = max_destlen; int err = puff(dest, &destlen, source, sourcelen); if (err) { munmap(dest, max_destlen); errno = -err; return -1; } if (write(dest_fd, dest, destlen) != (ssize_t)destlen) { munmap(dest, max_destlen); return -1; } return munmap(dest, max_destlen); } static int setup_loop_device(unsigned char* data, unsigned long size, const char* loopname, int* loopfd_p) { int err = 0, loopfd = -1; int memfd = syscall(__NR_memfd_create, "syzkaller", 0); if (memfd == -1) { err = errno; goto error; } if (puff_zlib_to_file(data, size, memfd)) { err = errno; goto error_close_memfd; } loopfd = open(loopname, O_RDWR); if (loopfd == -1) { err = errno; goto error_close_memfd; } if (ioctl(loopfd, LOOP_SET_FD, memfd)) { if (errno != EBUSY) { err = errno; goto error_close_loop; } ioctl(loopfd, LOOP_CLR_FD, 0); usleep(1000); if (ioctl(loopfd, LOOP_SET_FD, memfd)) { err = errno; goto error_close_loop; } } close(memfd); *loopfd_p = loopfd; return 0; error_close_loop: close(loopfd); error_close_memfd: close(memfd); error: errno = err; return -1; } static long syz_mount_image(volatile long fsarg, volatile long dir, volatile long flags, volatile long optsarg, volatile long change_dir, volatile unsigned long size, volatile long image) { unsigned char* data = (unsigned char*)image; int res = -1, err = 0, loopfd = -1, need_loop_device = !!size; char* mount_opts = (char*)optsarg; char* target = (char*)dir; char* fs = (char*)fsarg; char* source = NULL; char loopname[64]; if (need_loop_device) { memset(loopname, 0, sizeof(loopname)); snprintf(loopname, sizeof(loopname), "/dev/loop%llu", procid); if (setup_loop_device(data, size, loopname, &loopfd) == -1) return -1; source = loopname; } mkdir(target, 0777); char opts[256]; memset(opts, 0, sizeof(opts)); if (strlen(mount_opts) > (sizeof(opts) - 32)) { } strncpy(opts, mount_opts, sizeof(opts) - 32); if (strcmp(fs, "iso9660") == 0) { flags |= MS_RDONLY; } else if (strncmp(fs, "ext", 3) == 0) { bool has_remount_ro = false; char* remount_ro_start = strstr(opts, "errors=remount-ro"); if (remount_ro_start != NULL) { char after = *(remount_ro_start + strlen("errors=remount-ro")); char before = remount_ro_start == opts ? '\0' : *(remount_ro_start - 1); has_remount_ro = ((before == '\0' || before == ',') && (after == '\0' || after == ',')); } if (strstr(opts, "errors=panic") || !has_remount_ro) strcat(opts, ",errors=continue"); } else if (strcmp(fs, "xfs") == 0) { strcat(opts, ",nouuid"); } res = mount(source, target, fs, flags, opts); if (res == -1) { err = errno; goto error_clear_loop; } res = open(target, O_RDONLY | O_DIRECTORY); if (res == -1) { err = errno; goto error_clear_loop; } if (change_dir) { res = chdir(target); if (res == -1) { err = errno; } } error_clear_loop: if (need_loop_device) { ioctl(loopfd, LOOP_CLR_FD, 0); close(loopfd); } errno = err; return res; } #define XT_TABLE_SIZE 1536 #define XT_MAX_ENTRIES 10 struct xt_counters { uint64_t pcnt, bcnt; }; struct ipt_getinfo { char name[32]; unsigned int valid_hooks; unsigned int hook_entry[5]; unsigned int underflow[5]; unsigned int num_entries; unsigned int size; }; struct ipt_get_entries { char name[32]; unsigned int size; uint64_t entrytable[XT_TABLE_SIZE / sizeof(uint64_t)]; }; struct ipt_replace { char name[32]; unsigned int valid_hooks; unsigned int num_entries; unsigned int size; unsigned int hook_entry[5]; unsigned int underflow[5]; unsigned int num_counters; struct xt_counters* counters; uint64_t entrytable[XT_TABLE_SIZE / sizeof(uint64_t)]; }; struct ipt_table_desc { const char* name; struct ipt_getinfo info; struct ipt_replace replace; }; static struct ipt_table_desc ipv4_tables[] = { {.name = "filter"}, {.name = "nat"}, {.name = "mangle"}, {.name = "raw"}, {.name = "security"}, }; static struct ipt_table_desc ipv6_tables[] = { {.name = "filter"}, {.name = "nat"}, {.name = "mangle"}, {.name = "raw"}, {.name = "security"}, }; #define IPT_BASE_CTL 64 #define IPT_SO_SET_REPLACE (IPT_BASE_CTL) #define IPT_SO_GET_INFO (IPT_BASE_CTL) #define IPT_SO_GET_ENTRIES (IPT_BASE_CTL + 1) struct arpt_getinfo { char name[32]; unsigned int valid_hooks; unsigned int hook_entry[3]; unsigned int underflow[3]; unsigned int num_entries; unsigned int size; }; struct arpt_get_entries { char name[32]; unsigned int size; uint64_t entrytable[XT_TABLE_SIZE / sizeof(uint64_t)]; }; struct arpt_replace { char name[32]; unsigned int valid_hooks; unsigned int num_entries; unsigned int size; unsigned int hook_entry[3]; unsigned int underflow[3]; unsigned int num_counters; struct xt_counters* counters; uint64_t entrytable[XT_TABLE_SIZE / sizeof(uint64_t)]; }; struct arpt_table_desc { const char* name; struct arpt_getinfo info; struct arpt_replace replace; }; static struct arpt_table_desc arpt_tables[] = { {.name = "filter"}, }; #define ARPT_BASE_CTL 96 #define ARPT_SO_SET_REPLACE (ARPT_BASE_CTL) #define ARPT_SO_GET_INFO (ARPT_BASE_CTL) #define ARPT_SO_GET_ENTRIES (ARPT_BASE_CTL + 1) static void checkpoint_iptables(struct ipt_table_desc* tables, int num_tables, int family, int level) { int fd = socket(family, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } for (int i = 0; i < num_tables; i++) { struct ipt_table_desc* table = &tables[i]; strcpy(table->info.name, table->name); strcpy(table->replace.name, table->name); socklen_t optlen = sizeof(table->info); if (getsockopt(fd, level, IPT_SO_GET_INFO, &table->info, &optlen)) { switch (errno) { case EPERM: case ENOENT: case ENOPROTOOPT: continue; } exit(1); } if (table->info.size > sizeof(table->replace.entrytable)) exit(1); if (table->info.num_entries > XT_MAX_ENTRIES) exit(1); struct ipt_get_entries entries; memset(&entries, 0, sizeof(entries)); strcpy(entries.name, table->name); entries.size = table->info.size; optlen = sizeof(entries) - sizeof(entries.entrytable) + table->info.size; if (getsockopt(fd, level, IPT_SO_GET_ENTRIES, &entries, &optlen)) exit(1); table->replace.valid_hooks = table->info.valid_hooks; table->replace.num_entries = table->info.num_entries; table->replace.size = table->info.size; memcpy(table->replace.hook_entry, table->info.hook_entry, sizeof(table->replace.hook_entry)); memcpy(table->replace.underflow, table->info.underflow, sizeof(table->replace.underflow)); memcpy(table->replace.entrytable, entries.entrytable, table->info.size); } close(fd); } static void reset_iptables(struct ipt_table_desc* tables, int num_tables, int family, int level) { int fd = socket(family, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } for (int i = 0; i < num_tables; i++) { struct ipt_table_desc* table = &tables[i]; if (table->info.valid_hooks == 0) continue; struct ipt_getinfo info; memset(&info, 0, sizeof(info)); strcpy(info.name, table->name); socklen_t optlen = sizeof(info); if (getsockopt(fd, level, IPT_SO_GET_INFO, &info, &optlen)) exit(1); if (memcmp(&table->info, &info, sizeof(table->info)) == 0) { struct ipt_get_entries entries; memset(&entries, 0, sizeof(entries)); strcpy(entries.name, table->name); entries.size = table->info.size; optlen = sizeof(entries) - sizeof(entries.entrytable) + entries.size; if (getsockopt(fd, level, IPT_SO_GET_ENTRIES, &entries, &optlen)) exit(1); if (memcmp(table->replace.entrytable, entries.entrytable, table->info.size) == 0) continue; } struct xt_counters counters[XT_MAX_ENTRIES]; table->replace.num_counters = info.num_entries; table->replace.counters = counters; optlen = sizeof(table->replace) - sizeof(table->replace.entrytable) + table->replace.size; if (setsockopt(fd, level, IPT_SO_SET_REPLACE, &table->replace, optlen)) exit(1); } close(fd); } static void checkpoint_arptables(void) { int fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } for (unsigned i = 0; i < sizeof(arpt_tables) / sizeof(arpt_tables[0]); i++) { struct arpt_table_desc* table = &arpt_tables[i]; strcpy(table->info.name, table->name); strcpy(table->replace.name, table->name); socklen_t optlen = sizeof(table->info); if (getsockopt(fd, SOL_IP, ARPT_SO_GET_INFO, &table->info, &optlen)) { switch (errno) { case EPERM: case ENOENT: case ENOPROTOOPT: continue; } exit(1); } if (table->info.size > sizeof(table->replace.entrytable)) exit(1); if (table->info.num_entries > XT_MAX_ENTRIES) exit(1); struct arpt_get_entries entries; memset(&entries, 0, sizeof(entries)); strcpy(entries.name, table->name); entries.size = table->info.size; optlen = sizeof(entries) - sizeof(entries.entrytable) + table->info.size; if (getsockopt(fd, SOL_IP, ARPT_SO_GET_ENTRIES, &entries, &optlen)) exit(1); table->replace.valid_hooks = table->info.valid_hooks; table->replace.num_entries = table->info.num_entries; table->replace.size = table->info.size; memcpy(table->replace.hook_entry, table->info.hook_entry, sizeof(table->replace.hook_entry)); memcpy(table->replace.underflow, table->info.underflow, sizeof(table->replace.underflow)); memcpy(table->replace.entrytable, entries.entrytable, table->info.size); } close(fd); } static void reset_arptables() { int fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } for (unsigned i = 0; i < sizeof(arpt_tables) / sizeof(arpt_tables[0]); i++) { struct arpt_table_desc* table = &arpt_tables[i]; if (table->info.valid_hooks == 0) continue; struct arpt_getinfo info; memset(&info, 0, sizeof(info)); strcpy(info.name, table->name); socklen_t optlen = sizeof(info); if (getsockopt(fd, SOL_IP, ARPT_SO_GET_INFO, &info, &optlen)) exit(1); if (memcmp(&table->info, &info, sizeof(table->info)) == 0) { struct arpt_get_entries entries; memset(&entries, 0, sizeof(entries)); strcpy(entries.name, table->name); entries.size = table->info.size; optlen = sizeof(entries) - sizeof(entries.entrytable) + entries.size; if (getsockopt(fd, SOL_IP, ARPT_SO_GET_ENTRIES, &entries, &optlen)) exit(1); if (memcmp(table->replace.entrytable, entries.entrytable, table->info.size) == 0) continue; } else { } struct xt_counters counters[XT_MAX_ENTRIES]; table->replace.num_counters = info.num_entries; table->replace.counters = counters; optlen = sizeof(table->replace) - sizeof(table->replace.entrytable) + table->replace.size; if (setsockopt(fd, SOL_IP, ARPT_SO_SET_REPLACE, &table->replace, optlen)) exit(1); } close(fd); } #define NF_BR_NUMHOOKS 6 #define EBT_TABLE_MAXNAMELEN 32 #define EBT_CHAIN_MAXNAMELEN 32 #define EBT_BASE_CTL 128 #define EBT_SO_SET_ENTRIES (EBT_BASE_CTL) #define EBT_SO_GET_INFO (EBT_BASE_CTL) #define EBT_SO_GET_ENTRIES (EBT_SO_GET_INFO + 1) #define EBT_SO_GET_INIT_INFO (EBT_SO_GET_ENTRIES + 1) #define EBT_SO_GET_INIT_ENTRIES (EBT_SO_GET_INIT_INFO + 1) struct ebt_replace { char name[EBT_TABLE_MAXNAMELEN]; unsigned int valid_hooks; unsigned int nentries; unsigned int entries_size; struct ebt_entries* hook_entry[NF_BR_NUMHOOKS]; unsigned int num_counters; struct ebt_counter* counters; char* entries; }; struct ebt_entries { unsigned int distinguisher; char name[EBT_CHAIN_MAXNAMELEN]; unsigned int counter_offset; int policy; unsigned int nentries; char data[0] __attribute__((aligned(__alignof__(struct ebt_replace)))); }; struct ebt_table_desc { const char* name; struct ebt_replace replace; char entrytable[XT_TABLE_SIZE]; }; static struct ebt_table_desc ebt_tables[] = { {.name = "filter"}, {.name = "nat"}, {.name = "broute"}, }; static void checkpoint_ebtables(void) { int fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } for (size_t i = 0; i < sizeof(ebt_tables) / sizeof(ebt_tables[0]); i++) { struct ebt_table_desc* table = &ebt_tables[i]; strcpy(table->replace.name, table->name); socklen_t optlen = sizeof(table->replace); if (getsockopt(fd, SOL_IP, EBT_SO_GET_INIT_INFO, &table->replace, &optlen)) { switch (errno) { case EPERM: case ENOENT: case ENOPROTOOPT: continue; } exit(1); } if (table->replace.entries_size > sizeof(table->entrytable)) exit(1); table->replace.num_counters = 0; table->replace.entries = table->entrytable; optlen = sizeof(table->replace) + table->replace.entries_size; if (getsockopt(fd, SOL_IP, EBT_SO_GET_INIT_ENTRIES, &table->replace, &optlen)) exit(1); } close(fd); } static void reset_ebtables() { int fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } for (unsigned i = 0; i < sizeof(ebt_tables) / sizeof(ebt_tables[0]); i++) { struct ebt_table_desc* table = &ebt_tables[i]; if (table->replace.valid_hooks == 0) continue; struct ebt_replace replace; memset(&replace, 0, sizeof(replace)); strcpy(replace.name, table->name); socklen_t optlen = sizeof(replace); if (getsockopt(fd, SOL_IP, EBT_SO_GET_INFO, &replace, &optlen)) exit(1); replace.num_counters = 0; table->replace.entries = 0; for (unsigned h = 0; h < NF_BR_NUMHOOKS; h++) table->replace.hook_entry[h] = 0; if (memcmp(&table->replace, &replace, sizeof(table->replace)) == 0) { char entrytable[XT_TABLE_SIZE]; memset(&entrytable, 0, sizeof(entrytable)); replace.entries = entrytable; optlen = sizeof(replace) + replace.entries_size; if (getsockopt(fd, SOL_IP, EBT_SO_GET_ENTRIES, &replace, &optlen)) exit(1); if (memcmp(table->entrytable, entrytable, replace.entries_size) == 0) continue; } for (unsigned j = 0, h = 0; h < NF_BR_NUMHOOKS; h++) { if (table->replace.valid_hooks & (1 << h)) { table->replace.hook_entry[h] = (struct ebt_entries*)table->entrytable + j; j++; } } table->replace.entries = table->entrytable; optlen = sizeof(table->replace) + table->replace.entries_size; if (setsockopt(fd, SOL_IP, EBT_SO_SET_ENTRIES, &table->replace, optlen)) exit(1); } close(fd); } static void checkpoint_net_namespace(void) { checkpoint_ebtables(); checkpoint_arptables(); checkpoint_iptables(ipv4_tables, sizeof(ipv4_tables) / sizeof(ipv4_tables[0]), AF_INET, SOL_IP); checkpoint_iptables(ipv6_tables, sizeof(ipv6_tables) / sizeof(ipv6_tables[0]), AF_INET6, SOL_IPV6); } static void reset_net_namespace(void) { reset_ebtables(); reset_arptables(); reset_iptables(ipv4_tables, sizeof(ipv4_tables) / sizeof(ipv4_tables[0]), AF_INET, SOL_IP); reset_iptables(ipv6_tables, sizeof(ipv6_tables) / sizeof(ipv6_tables[0]), AF_INET6, SOL_IPV6); } static void mount_cgroups(const char* dir, const char** controllers, int count) { if (mkdir(dir, 0777)) { return; } char enabled[128] = {0}; int i = 0; for (; i < count; i++) { if (mount("none", dir, "cgroup", 0, controllers[i])) { continue; } umount(dir); strcat(enabled, ","); strcat(enabled, controllers[i]); } if (enabled[0] == 0) { if (rmdir(dir) && errno != EBUSY) exit(1); return; } if (mount("none", dir, "cgroup", 0, enabled + 1)) { if (rmdir(dir) && errno != EBUSY) exit(1); } if (chmod(dir, 0777)) { } } static void mount_cgroups2(const char** controllers, int count) { if (mkdir("/syzcgroup/unified", 0777)) { return; } if (mount("none", "/syzcgroup/unified", "cgroup2", 0, NULL)) { if (rmdir("/syzcgroup/unified") && errno != EBUSY) exit(1); return; } if (chmod("/syzcgroup/unified", 0777)) { } int control = open("/syzcgroup/unified/cgroup.subtree_control", O_WRONLY); if (control == -1) return; int i; for (i = 0; i < count; i++) if (write(control, controllers[i], strlen(controllers[i])) < 0) { } close(control); } static void setup_cgroups() { const char* unified_controllers[] = {"+cpu", "+io", "+pids"}; const char* net_controllers[] = {"net", "net_prio", "devices", "blkio", "freezer"}; const char* cpu_controllers[] = {"cpuset", "cpuacct", "hugetlb", "rlimit", "memory"}; if (mkdir("/syzcgroup", 0777)) { return; } mount_cgroups2(unified_controllers, sizeof(unified_controllers) / sizeof(unified_controllers[0])); mount_cgroups("/syzcgroup/net", net_controllers, sizeof(net_controllers) / sizeof(net_controllers[0])); mount_cgroups("/syzcgroup/cpu", cpu_controllers, sizeof(cpu_controllers) / sizeof(cpu_controllers[0])); write_file("/syzcgroup/cpu/cgroup.clone_children", "1"); write_file("/syzcgroup/cpu/cpuset.memory_pressure_enabled", "1"); } static void setup_cgroups_loop() { int pid = getpid(); char file[128]; char cgroupdir[64]; snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid); if (mkdir(cgroupdir, 0777)) { } snprintf(file, sizeof(file), "%s/pids.max", cgroupdir); write_file(file, "32"); snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir); write_file(file, "%d", pid); snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid); if (mkdir(cgroupdir, 0777)) { } snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir); write_file(file, "%d", pid); snprintf(file, sizeof(file), "%s/memory.soft_limit_in_bytes", cgroupdir); write_file(file, "%d", 299 << 20); snprintf(file, sizeof(file), "%s/memory.limit_in_bytes", cgroupdir); write_file(file, "%d", 300 << 20); snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid); if (mkdir(cgroupdir, 0777)) { } snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir); write_file(file, "%d", pid); } static void setup_cgroups_test() { char cgroupdir[64]; snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid); if (symlink(cgroupdir, "./cgroup")) { } snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid); if (symlink(cgroupdir, "./cgroup.cpu")) { } snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid); if (symlink(cgroupdir, "./cgroup.net")) { } } static void setup_common() { if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) { } } static void setup_binderfs() { if (mkdir("/dev/binderfs", 0777)) { } if (mount("binder", "/dev/binderfs", "binder", 0, NULL)) { } } static void loop(); static void sandbox_common() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setsid(); struct rlimit rlim; rlim.rlim_cur = rlim.rlim_max = (200 << 20); setrlimit(RLIMIT_AS, &rlim); rlim.rlim_cur = rlim.rlim_max = 32 << 20; setrlimit(RLIMIT_MEMLOCK, &rlim); rlim.rlim_cur = rlim.rlim_max = 136 << 20; setrlimit(RLIMIT_FSIZE, &rlim); rlim.rlim_cur = rlim.rlim_max = 1 << 20; setrlimit(RLIMIT_STACK, &rlim); rlim.rlim_cur = rlim.rlim_max = 128 << 20; setrlimit(RLIMIT_CORE, &rlim); rlim.rlim_cur = rlim.rlim_max = 256; setrlimit(RLIMIT_NOFILE, &rlim); if (unshare(CLONE_NEWNS)) { } if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) { } if (unshare(CLONE_NEWIPC)) { } if (unshare(0x02000000)) { } if (unshare(CLONE_NEWUTS)) { } if (unshare(CLONE_SYSVSEM)) { } typedef struct { const char* name; const char* value; } sysctl_t; static const sysctl_t sysctls[] = { {"/proc/sys/kernel/shmmax", "16777216"}, {"/proc/sys/kernel/shmall", "536870912"}, {"/proc/sys/kernel/shmmni", "1024"}, {"/proc/sys/kernel/msgmax", "8192"}, {"/proc/sys/kernel/msgmni", "1024"}, {"/proc/sys/kernel/msgmnb", "1024"}, {"/proc/sys/kernel/sem", "1024 1048576 500 1024"}, }; unsigned i; for (i = 0; i < sizeof(sysctls) / sizeof(sysctls[0]); i++) write_file(sysctls[i].name, sysctls[i].value); } static int wait_for_loop(int pid) { if (pid < 0) exit(1); int status = 0; while (waitpid(-1, &status, __WALL) != pid) { } return WEXITSTATUS(status); } static void drop_caps(void) { struct __user_cap_header_struct cap_hdr = {}; struct __user_cap_data_struct cap_data[2] = {}; cap_hdr.version = _LINUX_CAPABILITY_VERSION_3; cap_hdr.pid = getpid(); if (syscall(SYS_capget, &cap_hdr, &cap_data)) exit(1); const int drop = (1 << CAP_SYS_PTRACE) | (1 << CAP_SYS_NICE); cap_data[0].effective &= ~drop; cap_data[0].permitted &= ~drop; cap_data[0].inheritable &= ~drop; if (syscall(SYS_capset, &cap_hdr, &cap_data)) exit(1); } static int do_sandbox_none(void) { if (unshare(CLONE_NEWPID)) { } int pid = fork(); if (pid != 0) return wait_for_loop(pid); setup_common(); sandbox_common(); drop_caps(); if (unshare(CLONE_NEWNET)) { } write_file("/proc/sys/net/ipv4/ping_group_range", "0 65535"); setup_binderfs(); loop(); exit(1); } #define FS_IOC_SETFLAGS _IOW('f', 2, long) static void remove_dir(const char* dir) { int iter = 0; DIR* dp = 0; retry: while (umount2(dir, MNT_DETACH | UMOUNT_NOFOLLOW) == 0) { } dp = opendir(dir); if (dp == NULL) { if (errno == EMFILE) { exit(1); } exit(1); } struct dirent* ep = 0; while ((ep = readdir(dp))) { if (strcmp(ep->d_name, ".") == 0 || strcmp(ep->d_name, "..") == 0) continue; char filename[FILENAME_MAX]; snprintf(filename, sizeof(filename), "%s/%s", dir, ep->d_name); while (umount2(filename, MNT_DETACH | UMOUNT_NOFOLLOW) == 0) { } struct stat st; if (lstat(filename, &st)) exit(1); if (S_ISDIR(st.st_mode)) { remove_dir(filename); continue; } int i; for (i = 0;; i++) { if (unlink(filename) == 0) break; if (errno == EPERM) { int fd = open(filename, O_RDONLY); if (fd != -1) { long flags = 0; if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0) { } close(fd); continue; } } if (errno == EROFS) { break; } if (errno != EBUSY || i > 100) exit(1); if (umount2(filename, MNT_DETACH | UMOUNT_NOFOLLOW)) exit(1); } } closedir(dp); for (int i = 0;; i++) { if (rmdir(dir) == 0) break; if (i < 100) { if (errno == EPERM) { int fd = open(dir, O_RDONLY); if (fd != -1) { long flags = 0; if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0) { } close(fd); continue; } } if (errno == EROFS) { break; } if (errno == EBUSY) { if (umount2(dir, MNT_DETACH | UMOUNT_NOFOLLOW)) exit(1); continue; } if (errno == ENOTEMPTY) { if (iter < 100) { iter++; goto retry; } } } exit(1); } } static void kill_and_wait(int pid, int* status) { kill(-pid, SIGKILL); kill(pid, SIGKILL); for (int i = 0; i < 100; i++) { if (waitpid(-1, status, WNOHANG | __WALL) == pid) return; usleep(1000); } DIR* dir = opendir("/sys/fs/fuse/connections"); if (dir) { for (;;) { struct dirent* ent = readdir(dir); if (!ent) break; if (strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0) continue; char abort[300]; snprintf(abort, sizeof(abort), "/sys/fs/fuse/connections/%s/abort", ent->d_name); int fd = open(abort, O_WRONLY); if (fd == -1) { continue; } if (write(fd, abort, 1) < 0) { } close(fd); } closedir(dir); } else { } while (waitpid(-1, status, __WALL) != pid) { } } static void setup_loop() { setup_cgroups_loop(); checkpoint_net_namespace(); } static void reset_loop() { char buf[64]; snprintf(buf, sizeof(buf), "/dev/loop%llu", procid); int loopfd = open(buf, O_RDWR); if (loopfd != -1) { ioctl(loopfd, LOOP_CLR_FD, 0); close(loopfd); } reset_net_namespace(); } static void setup_test() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); setup_cgroups_test(); write_file("/proc/self/oom_score_adj", "1000"); if (symlink("/dev/binderfs", "./binderfs")) { } } static void close_fds() { for (int fd = 3; fd < MAX_FDS; fd++) close(fd); } static void setup_binfmt_misc() { if (mount(0, "/proc/sys/fs/binfmt_misc", "binfmt_misc", 0, 0)) { } write_file("/proc/sys/fs/binfmt_misc/register", ":syz0:M:0:\x01::./file0:"); write_file("/proc/sys/fs/binfmt_misc/register", ":syz1:M:1:\x02::./file0:POC"); } static void setup_sysctl() { char mypid[32]; snprintf(mypid, sizeof(mypid), "%d", getpid()); struct { const char* name; const char* data; } files[] = { {"/proc/sys/kernel/hung_task_check_interval_secs", "20"}, {"/proc/sys/net/core/bpf_jit_kallsyms", "1"}, {"/proc/sys/net/core/bpf_jit_harden", "0"}, {"/proc/sys/kernel/kptr_restrict", "0"}, {"/proc/sys/kernel/softlockup_all_cpu_backtrace", "1"}, {"/proc/sys/fs/mount-max", "100"}, {"/proc/sys/vm/oom_dump_tasks", "0"}, {"/proc/sys/debug/exception-trace", "0"}, {"/proc/sys/kernel/printk", "7 4 1 3"}, {"/proc/sys/kernel/keys/gc_delay", "1"}, {"/proc/sys/vm/oom_kill_allocating_task", "1"}, {"/proc/sys/kernel/ctrl-alt-del", "0"}, {"/proc/sys/kernel/cad_pid", mypid}, }; for (size_t i = 0; i < sizeof(files) / sizeof(files[0]); i++) { if (!write_file(files[i].name, files[i].data)) printf("write to %s failed: %s\n", files[i].name, strerror(errno)); } } struct thread_t { int created, call; event_t ready, done; }; static struct thread_t threads[16]; static void execute_call(int call); static int running; static void* thr(void* arg) { struct thread_t* th = (struct thread_t*)arg; for (;;) { event_wait(&th->ready); event_reset(&th->ready); execute_call(th->call); __atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED); event_set(&th->done); } return 0; } static void execute_one(void) { int i, call, thread; for (call = 0; call < 4; call++) { for (thread = 0; thread < (int)(sizeof(threads) / sizeof(threads[0])); thread++) { struct thread_t* th = &threads[thread]; if (!th->created) { th->created = 1; event_init(&th->ready); event_init(&th->done); event_set(&th->done); thread_start(thr, th); } if (!event_isset(&th->done)) continue; event_reset(&th->done); th->call = call; __atomic_fetch_add(&running, 1, __ATOMIC_RELAXED); event_set(&th->ready); if (call == 2) break; event_timedwait(&th->done, 50); break; } } for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++) sleep_ms(1); close_fds(); } static void execute_one(void); #define WAIT_FLAGS __WALL static void loop(void) { setup_loop(); int iter = 0; for (;; iter++) { char cwdbuf[32]; sprintf(cwdbuf, "./%d", iter); if (mkdir(cwdbuf, 0777)) exit(1); reset_loop(); int pid = fork(); if (pid < 0) exit(1); if (pid == 0) { if (chdir(cwdbuf)) exit(1); setup_test(); execute_one(); exit(0); } int status = 0; uint64_t start = current_time_ms(); for (;;) { if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid) break; sleep_ms(1); if (current_time_ms() - start < 5000) continue; kill_and_wait(pid, &status); break; } remove_dir(cwdbuf); } } void execute_call(int call) { switch (call) { case 0: NONFAILING(memcpy((void*)0x200000c0, "./file0\000", 8)); NONFAILING(syz_mount_image(/*fs=*/0, /*dir=*/0x200000c0, /*flags=*/0, /*opts=*/0, /*chdir=*/0, /*size=*/0, /*img=*/0)); break; case 1: NONFAILING(*(uint8_t*)0x20000080 = -1); NONFAILING(*(uint8_t*)0x20000081 = -1); NONFAILING(memcpy((void*)0x200001c0, "./file0\000", 8)); NONFAILING(memcpy((void*)0x20000200, "mqueue\000", 7)); syscall(__NR_mount, /*src=*/0x20000080ul, /*dst=*/0x200001c0ul, /*type=*/0x20000200ul, /*flags=*/0ul, /*data=*/0ul); break; case 2: NONFAILING(memcpy((void*)0x20000480, "./file0\000", 8)); NONFAILING(memcpy((void*)0x200004c0, "./file0\000", 8)); syscall(__NR_pivot_root, /*new_root=*/0x20000480ul, /*put_old=*/0x200004c0ul); break; case 3: NONFAILING(memcpy((void*)0x20000480, "./file0\000", 8)); NONFAILING(memcpy((void*)0x200004c0, "./file0\000", 8)); syscall(__NR_pivot_root, /*new_root=*/0x20000480ul, /*put_old=*/0x200004c0ul); break; } } int main(void) { syscall(__NR_mmap, /*addr=*/0x1ffff000ul, /*len=*/0x1000ul, /*prot=*/0ul, /*flags=*/0x32ul, /*fd=*/-1, /*offset=*/0ul); syscall(__NR_mmap, /*addr=*/0x20000000ul, /*len=*/0x1000000ul, /*prot=*/7ul, /*flags=*/0x32ul, /*fd=*/-1, /*offset=*/0ul); syscall(__NR_mmap, /*addr=*/0x21000000ul, /*len=*/0x1000ul, /*prot=*/0ul, /*flags=*/0x32ul, /*fd=*/-1, /*offset=*/0ul); setup_sysctl(); setup_cgroups(); setup_binfmt_misc(); install_segv_handler(); use_temporary_dir(); do_sandbox_none(); return 0; }