// autogenerated by syzkaller (http://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 #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include __attribute__((noreturn)) static void doexit(int status) { volatile unsigned i; syscall(__NR_exit_group, status); for (i = 0;; i++) { } } #include #include #include #include #include #include #include const int kFailStatus = 67; const int kRetryStatus = 69; static void fail(const char* msg, ...) { int e = errno; va_list args; va_start(args, msg); vfprintf(stderr, msg, args); va_end(args); fprintf(stderr, " (errno %d)\n", e); doexit((e == ENOMEM || e == EAGAIN) ? kRetryStatus : kFailStatus); } static void exitf(const char* msg, ...) { int e = errno; va_list args; va_start(args, msg); vfprintf(stderr, msg, args); va_end(args); fprintf(stderr, " (errno %d)\n", e); doexit(kRetryStatus); } static uint64_t current_time_ms() { struct timespec ts; if (clock_gettime(CLOCK_MONOTONIC, &ts)) fail("clock_gettime failed"); return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000; } static void use_temporary_dir() { char tmpdir_template[] = "./syzkaller.XXXXXX"; char* tmpdir = mkdtemp(tmpdir_template); if (!tmpdir) fail("failed to mkdtemp"); if (chmod(tmpdir, 0777)) fail("failed to chmod"); if (chdir(tmpdir)) fail("failed to chdir"); } static void vsnprintf_check(char* str, size_t size, const char* format, va_list args) { int rv; rv = vsnprintf(str, size, format, args); if (rv < 0) fail("tun: snprintf failed"); if ((size_t)rv >= size) fail("tun: string '%s...' doesn't fit into buffer", str); } static void snprintf_check(char* str, size_t size, const char* format, ...) { va_list args; va_start(args, format); vsnprintf_check(str, size, format, args); va_end(args); } #define COMMAND_MAX_LEN 128 #define PATH_PREFIX \ "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin " #define PATH_PREFIX_LEN (sizeof(PATH_PREFIX) - 1) static void execute_command(bool panic, const char* format, ...) { va_list args; char command[PATH_PREFIX_LEN + COMMAND_MAX_LEN]; int rv; va_start(args, format); memcpy(command, PATH_PREFIX, PATH_PREFIX_LEN); vsnprintf_check(command + PATH_PREFIX_LEN, COMMAND_MAX_LEN, format, args); rv = system(command); if (panic && rv != 0) fail("tun: command \"%s\" failed with code %d", &command[0], rv); va_end(args); } static int tunfd = -1; static int tun_frags_enabled; #define SYZ_TUN_MAX_PACKET_SIZE 1000 #define TUN_IFACE "syz_tun" #define LOCAL_MAC "aa:aa:aa:aa:aa:aa" #define REMOTE_MAC "aa:aa:aa:aa:aa:bb" #define LOCAL_IPV4 "172.20.20.170" #define REMOTE_IPV4 "172.20.20.187" #define LOCAL_IPV6 "fe80::aa" #define REMOTE_IPV6 "fe80::bb" #define IFF_NAPI 0x0010 #define IFF_NAPI_FRAGS 0x0020 static void initialize_tun(void) { tunfd = open("/dev/net/tun", O_RDWR | O_NONBLOCK); if (tunfd == -1) { printf("tun: can't open /dev/net/tun: please enable CONFIG_TUN=y\n"); printf("otherwise fuzzing or reproducing might not work as intended\n"); return; } const int kTunFd = 252; if (dup2(tunfd, kTunFd) < 0) fail("dup2(tunfd, kTunFd) failed"); close(tunfd); tunfd = kTunFd; struct ifreq ifr; memset(&ifr, 0, sizeof(ifr)); strncpy(ifr.ifr_name, TUN_IFACE, IFNAMSIZ); ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_NAPI | IFF_NAPI_FRAGS; if (ioctl(tunfd, TUNSETIFF, (void*)&ifr) < 0) { ifr.ifr_flags = IFF_TAP | IFF_NO_PI; if (ioctl(tunfd, TUNSETIFF, (void*)&ifr) < 0) fail("tun: ioctl(TUNSETIFF) failed"); } if (ioctl(tunfd, TUNGETIFF, (void*)&ifr) < 0) fail("tun: ioctl(TUNGETIFF) failed"); tun_frags_enabled = (ifr.ifr_flags & IFF_NAPI_FRAGS) != 0; execute_command(1, "sysctl -w net.ipv6.conf.%s.accept_dad=0", TUN_IFACE); execute_command(1, "sysctl -w net.ipv6.conf.%s.router_solicitations=0", TUN_IFACE); execute_command(1, "ip link set dev %s address %s", TUN_IFACE, LOCAL_MAC); execute_command(1, "ip addr add %s/24 dev %s", LOCAL_IPV4, TUN_IFACE); execute_command(1, "ip -6 addr add %s/120 dev %s", LOCAL_IPV6, TUN_IFACE); execute_command(1, "ip neigh add %s lladdr %s dev %s nud permanent", REMOTE_IPV4, REMOTE_MAC, TUN_IFACE); execute_command(1, "ip -6 neigh add %s lladdr %s dev %s nud permanent", REMOTE_IPV6, REMOTE_MAC, TUN_IFACE); execute_command(1, "ip link set dev %s up", TUN_IFACE); } #define DEV_IPV4 "172.20.20.%d" #define DEV_IPV6 "fe80::%02hx" #define DEV_MAC "aa:aa:aa:aa:aa:%02hx" static void initialize_netdevices(void) { unsigned i; const char* devtypes[] = {"ip6gretap", "bridge", "vcan", "bond", "veth"}; const char* devnames[] = {"lo", "sit0", "bridge0", "vcan0", "tunl0", "gre0", "gretap0", "ip_vti0", "ip6_vti0", "ip6tnl0", "ip6gre0", "ip6gretap0", "erspan0", "bond0", "veth0", "veth1"}; for (i = 0; i < sizeof(devtypes) / (sizeof(devtypes[0])); i++) execute_command(0, "ip link add dev %s0 type %s", devtypes[i], devtypes[i]); execute_command(0, "ip link add dev veth1 type veth"); for (i = 0; i < sizeof(devnames) / (sizeof(devnames[0])); i++) { char addr[32]; snprintf_check(addr, sizeof(addr), DEV_IPV4, i + 10); execute_command(0, "ip -4 addr add %s/24 dev %s", addr, devnames[i]); snprintf_check(addr, sizeof(addr), DEV_IPV6, i + 10); execute_command(0, "ip -6 addr add %s/120 dev %s", addr, devnames[i]); snprintf_check(addr, sizeof(addr), DEV_MAC, i + 10); execute_command(0, "ip link set dev %s address %s", devnames[i], addr); execute_command(0, "ip link set dev %s up", devnames[i]); } } static int read_tun(char* data, int size) { if (tunfd < 0) return -1; int rv = read(tunfd, data, size); if (rv < 0) { if (errno == EAGAIN) return -1; if (errno == EBADFD) return -1; fail("tun: read failed with %d", rv); } return rv; } static void flush_tun() { char data[SYZ_TUN_MAX_PACKET_SIZE]; while (read_tun(&data[0], sizeof(data)) != -1) ; } static void loop(); static void sandbox_common() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); setsid(); struct rlimit rlim; rlim.rlim_cur = rlim.rlim_max = 128 << 20; setrlimit(RLIMIT_AS, &rlim); rlim.rlim_cur = rlim.rlim_max = 8 << 20; setrlimit(RLIMIT_MEMLOCK, &rlim); rlim.rlim_cur = rlim.rlim_max = 1 << 20; setrlimit(RLIMIT_FSIZE, &rlim); rlim.rlim_cur = rlim.rlim_max = 1 << 20; setrlimit(RLIMIT_STACK, &rlim); rlim.rlim_cur = rlim.rlim_max = 0; setrlimit(RLIMIT_CORE, &rlim); #define CLONE_NEWCGROUP 0x02000000 if (unshare(CLONE_NEWNS)) { } if (unshare(CLONE_NEWIPC)) { } if (unshare(CLONE_NEWCGROUP)) { } if (unshare(CLONE_NEWUTS)) { } if (unshare(CLONE_SYSVSEM)) { } } 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) { close(fd); return false; } close(fd); return true; } static int real_uid; static int real_gid; __attribute__((aligned(64 << 10))) static char sandbox_stack[1 << 20]; static int namespace_sandbox_proc(void* arg) { sandbox_common(); write_file("/proc/self/setgroups", "deny"); if (!write_file("/proc/self/uid_map", "0 %d 1\n", real_uid)) fail("write of /proc/self/uid_map failed"); if (!write_file("/proc/self/gid_map", "0 %d 1\n", real_gid)) fail("write of /proc/self/gid_map failed"); if (unshare(CLONE_NEWNET)) fail("unshare(CLONE_NEWNET)"); initialize_tun(); initialize_netdevices(); if (mkdir("./syz-tmp", 0777)) fail("mkdir(syz-tmp) failed"); if (mount("", "./syz-tmp", "tmpfs", 0, NULL)) fail("mount(tmpfs) failed"); if (mkdir("./syz-tmp/newroot", 0777)) fail("mkdir failed"); if (mkdir("./syz-tmp/newroot/dev", 0700)) fail("mkdir failed"); unsigned mount_flags = MS_BIND | MS_REC | MS_PRIVATE; if (mount("/dev", "./syz-tmp/newroot/dev", NULL, mount_flags, NULL)) fail("mount(dev) failed"); if (mkdir("./syz-tmp/newroot/proc", 0700)) fail("mkdir failed"); if (mount(NULL, "./syz-tmp/newroot/proc", "proc", 0, NULL)) fail("mount(proc) failed"); if (mkdir("./syz-tmp/newroot/selinux", 0700)) fail("mkdir failed"); const char* selinux_path = "./syz-tmp/newroot/selinux"; if (mount("/selinux", selinux_path, NULL, mount_flags, NULL)) { if (errno != ENOENT) fail("mount(/selinux) failed"); if (mount("/sys/fs/selinux", selinux_path, NULL, mount_flags, NULL) && errno != ENOENT) fail("mount(/sys/fs/selinux) failed"); } if (mkdir("./syz-tmp/pivot", 0777)) fail("mkdir failed"); if (syscall(SYS_pivot_root, "./syz-tmp", "./syz-tmp/pivot")) { if (chdir("./syz-tmp")) fail("chdir failed"); } else { if (chdir("/")) fail("chdir failed"); if (umount2("./pivot", MNT_DETACH)) fail("umount failed"); } if (chroot("./newroot")) fail("chroot failed"); if (chdir("/")) fail("chdir failed"); 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)) fail("capget failed"); cap_data[0].effective &= ~(1 << CAP_SYS_PTRACE); cap_data[0].permitted &= ~(1 << CAP_SYS_PTRACE); cap_data[0].inheritable &= ~(1 << CAP_SYS_PTRACE); if (syscall(SYS_capset, &cap_hdr, &cap_data)) fail("capset failed"); loop(); doexit(1); } static int do_sandbox_namespace(void) { int pid; real_uid = getuid(); real_gid = getgid(); mprotect(sandbox_stack, 4096, PROT_NONE); pid = clone(namespace_sandbox_proc, &sandbox_stack[sizeof(sandbox_stack) - 64], CLONE_NEWUSER | CLONE_NEWPID, 0); if (pid < 0) fail("sandbox clone failed"); return pid; } #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; void* entrytable[XT_TABLE_SIZE / sizeof(void*)]; }; 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; char entrytable[XT_TABLE_SIZE]; }; 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; void* entrytable[XT_TABLE_SIZE / sizeof(void*)]; }; 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; char entrytable[XT_TABLE_SIZE]; }; 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) { struct ipt_get_entries entries; socklen_t optlen; int fd, i; fd = socket(family, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) fail("socket(%d, SOCK_STREAM, IPPROTO_TCP)", family); for (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); optlen = sizeof(table->info); if (getsockopt(fd, level, IPT_SO_GET_INFO, &table->info, &optlen)) { switch (errno) { case EPERM: case ENOENT: case ENOPROTOOPT: continue; } fail("getsockopt(IPT_SO_GET_INFO)"); } if (table->info.size > sizeof(table->replace.entrytable)) fail("table size is too large: %u", table->info.size); if (table->info.num_entries > XT_MAX_ENTRIES) fail("too many counters: %u", table->info.num_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)) fail("getsockopt(IPT_SO_GET_ENTRIES)"); 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) { struct xt_counters counters[XT_MAX_ENTRIES]; struct ipt_get_entries entries; struct ipt_getinfo info; socklen_t optlen; int fd, i; fd = socket(family, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) fail("socket(%d, SOCK_STREAM, IPPROTO_TCP)", family); for (i = 0; i < num_tables; i++) { struct ipt_table_desc* table = &tables[i]; if (table->info.valid_hooks == 0) continue; memset(&info, 0, sizeof(info)); strcpy(info.name, table->name); optlen = sizeof(info); if (getsockopt(fd, level, IPT_SO_GET_INFO, &info, &optlen)) fail("getsockopt(IPT_SO_GET_INFO)"); if (memcmp(&table->info, &info, sizeof(table->info)) == 0) { 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)) fail("getsockopt(IPT_SO_GET_ENTRIES)"); if (memcmp(table->replace.entrytable, entries.entrytable, table->info.size) == 0) continue; } 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)) fail("setsockopt(IPT_SO_SET_REPLACE)"); } close(fd); } static void checkpoint_arptables(void) { struct arpt_get_entries entries; socklen_t optlen; unsigned i; int fd; fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)"); for (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); 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; } fail("getsockopt(ARPT_SO_GET_INFO)"); } if (table->info.size > sizeof(table->replace.entrytable)) fail("table size is too large: %u", table->info.size); if (table->info.num_entries > XT_MAX_ENTRIES) fail("too many counters: %u", table->info.num_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)) fail("getsockopt(ARPT_SO_GET_ENTRIES)"); 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() { struct xt_counters counters[XT_MAX_ENTRIES]; struct arpt_get_entries entries; struct arpt_getinfo info; socklen_t optlen; unsigned i; int fd; fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)"); for (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; memset(&info, 0, sizeof(info)); strcpy(info.name, table->name); optlen = sizeof(info); if (getsockopt(fd, SOL_IP, ARPT_SO_GET_INFO, &info, &optlen)) fail("getsockopt(ARPT_SO_GET_INFO)"); if (memcmp(&table->info, &info, sizeof(table->info)) == 0) { 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)) fail("getsockopt(ARPT_SO_GET_ENTRIES)"); if (memcmp(table->replace.entrytable, entries.entrytable, table->info.size) == 0) continue; } 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)) fail("setsockopt(ARPT_SO_SET_REPLACE)"); } close(fd); } #include #include 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) { socklen_t optlen; unsigned i; int fd; fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)"); for (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); 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; } fail("getsockopt(EBT_SO_GET_INIT_INFO)"); } if (table->replace.entries_size > sizeof(table->entrytable)) fail("table size is too large: %u", table->replace.entries_size); 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)) fail("getsockopt(EBT_SO_GET_INIT_ENTRIES)"); } close(fd); } static void reset_ebtables() { struct ebt_replace replace; char entrytable[XT_TABLE_SIZE]; socklen_t optlen; unsigned i, j, h; int fd; fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)"); for (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; memset(&replace, 0, sizeof(replace)); strcpy(replace.name, table->name); optlen = sizeof(replace); if (getsockopt(fd, SOL_IP, EBT_SO_GET_INFO, &replace, &optlen)) fail("getsockopt(EBT_SO_GET_INFO)"); replace.num_counters = 0; for (h = 0; h < NF_BR_NUMHOOKS; h++) table->replace.hook_entry[h] = 0; if (memcmp(&table->replace, &replace, sizeof(table->replace)) == 0) { 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)) fail("getsockopt(EBT_SO_GET_ENTRIES)"); if (memcmp(table->entrytable, entrytable, replace.entries_size) == 0) continue; } for (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++; } } optlen = sizeof(table->replace) + table->replace.entries_size; if (setsockopt(fd, SOL_IP, EBT_SO_SET_ENTRIES, &table->replace, optlen)) fail("setsockopt(EBT_SO_SET_ENTRIES)"); } 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 remove_dir(const char* dir) { DIR* dp; struct dirent* ep; int iter = 0; retry: dp = opendir(dir); if (dp == NULL) { if (errno == EMFILE) { exitf("opendir(%s) failed due to NOFILE, exiting", dir); } exitf("opendir(%s) failed", dir); } 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); struct stat st; if (lstat(filename, &st)) exitf("lstat(%s) failed", filename); if (S_ISDIR(st.st_mode)) { remove_dir(filename); continue; } int i; for (i = 0;; i++) { if (unlink(filename) == 0) break; if (errno == EROFS) { break; } if (errno != EBUSY || i > 100) exitf("unlink(%s) failed", filename); if (umount2(filename, MNT_DETACH)) exitf("umount(%s) failed", filename); } } closedir(dp); int i; for (i = 0;; i++) { if (rmdir(dir) == 0) break; if (i < 100) { if (errno == EROFS) { break; } if (errno == EBUSY) { if (umount2(dir, MNT_DETACH)) exitf("umount(%s) failed", dir); continue; } if (errno == ENOTEMPTY) { if (iter < 100) { iter++; goto retry; } } } exitf("rmdir(%s) failed", dir); } } static void test(); void loop() { int iter; checkpoint_net_namespace(); for (iter = 0;; iter++) { char cwdbuf[256]; sprintf(cwdbuf, "./%d", iter); if (mkdir(cwdbuf, 0777)) fail("failed to mkdir"); int pid = fork(); if (pid < 0) fail("loop fork failed"); if (pid == 0) { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); if (chdir(cwdbuf)) fail("failed to chdir"); flush_tun(); test(); doexit(0); } int status = 0; uint64_t start = current_time_ms(); for (;;) { int res = waitpid(-1, &status, __WALL | WNOHANG); if (res == pid) break; usleep(1000); if (current_time_ms() - start > 5 * 1000) { kill(-pid, SIGKILL); kill(pid, SIGKILL); while (waitpid(-1, &status, __WALL) != pid) { } break; } } remove_dir(cwdbuf); reset_net_namespace(); } } struct thread_t { int created, running, call; pthread_t th; }; 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 (;;) { while (!__atomic_load_n(&th->running, __ATOMIC_ACQUIRE)) syscall(SYS_futex, &th->running, FUTEX_WAIT, 0, 0); execute_call(th->call); __atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED); __atomic_store_n(&th->running, 0, __ATOMIC_RELEASE); syscall(SYS_futex, &th->running, FUTEX_WAKE); } return 0; } static void execute(int num_calls) { int call, thread; running = 0; for (call = 0; call < num_calls; call++) { for (thread = 0; thread < sizeof(threads) / sizeof(threads[0]); thread++) { struct thread_t* th = &threads[thread]; if (!th->created) { th->created = 1; pthread_attr_t attr; pthread_attr_init(&attr); pthread_attr_setstacksize(&attr, 128 << 10); pthread_create(&th->th, &attr, thr, th); } if (!__atomic_load_n(&th->running, __ATOMIC_ACQUIRE)) { th->call = call; __atomic_fetch_add(&running, 1, __ATOMIC_RELAXED); __atomic_store_n(&th->running, 1, __ATOMIC_RELEASE); syscall(SYS_futex, &th->running, FUTEX_WAKE); struct timespec ts; ts.tv_sec = 0; ts.tv_nsec = 20 * 1000 * 1000; syscall(SYS_futex, &th->running, FUTEX_WAIT, 1, &ts); if (running) usleep((call == num_calls - 1) ? 10000 : 1000); break; } } } } uint64_t r[1] = {0xffffffffffffffff}; uint64_t procid; void execute_call(int call) { long res; switch (call) { case 0: memcpy((void*)0x20000180, "/dev/infiniband/rdma_cm", 24); res = syscall(__NR_openat, 0xffffffffffffff9c, 0x20000180, 2, 0); if (res != -1) r[0] = res; break; case 1: *(uint32_t*)0x20000000 = 0; *(uint16_t*)0x20000004 = 0x18; *(uint16_t*)0x20000006 = 0xfa00; *(uint64_t*)0x20000008 = 0; *(uint64_t*)0x20000010 = 0x20000f00; *(uint16_t*)0x20000018 = 0x106; *(uint8_t*)0x2000001a = 0; *(uint8_t*)0x2000001b = 0; *(uint8_t*)0x2000001c = 0; *(uint8_t*)0x2000001d = 0; *(uint8_t*)0x2000001e = 0; *(uint8_t*)0x2000001f = 0; syscall(__NR_write, r[0], 0x20000000, 0x20); break; case 2: memcpy((void*)0x200003c0, "\x09\x00\x00\x00\x00\x00\x00\xfa", 8); syscall(__NR_write, r[0], 0x200003c0, 8); break; } } void test() { execute(3); } int main() { syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0); char* cwd = get_current_dir_name(); for (procid = 0; procid < 8; procid++) { if (fork() == 0) { for (;;) { if (chdir(cwd)) fail("failed to chdir"); use_temporary_dir(); int pid = do_sandbox_namespace(); int status = 0; while (waitpid(pid, &status, __WALL) != pid) { } } } } sleep(1000000); return 0; }