// https://syzkaller.appspot.com/bug?id=40b0c218e639f1d882b86abff2549cfe11c5101e // 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 #include #include #include #include #include #include #include #include #include #include unsigned long long procid; static __thread int skip_segv; static __thread jmp_buf segv_env; static void segv_handler(int sig, siginfo_t* info, void* ctx) { uintptr_t addr = (uintptr_t)info->si_addr; const uintptr_t prog_start = 1 << 20; const uintptr_t prog_end = 100 << 20; if (__atomic_load_n(&skip_segv, __ATOMIC_RELAXED) && (addr < prog_start || addr > prog_end)) { _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(...) \ { \ __atomic_fetch_add(&skip_segv, 1, __ATOMIC_SEQ_CST); \ if (_setjmp(segv_env) == 0) { \ __VA_ARGS__; \ } \ __atomic_fetch_sub(&skip_segv, 1, __ATOMIC_SEQ_CST); \ } 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 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; for (i = 0; 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); } #define BITMASK(bf_off, bf_len) (((1ull << (bf_len)) - 1) << (bf_off)) #define STORE_BY_BITMASK(type, htobe, addr, val, bf_off, bf_len) \ *(type*)(addr) = \ htobe((htobe(*(type*)(addr)) & ~BITMASK((bf_off), (bf_len))) | \ (((type)(val) << (bf_off)) & BITMASK((bf_off), (bf_len)))) 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); } 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_RELAXED)) 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; } static struct { char* pos; int nesting; struct nlattr* nested[8]; char buf[1024]; } nlmsg; static void netlink_init(int typ, int flags, const void* data, int size) { memset(&nlmsg, 0, sizeof(nlmsg)); struct nlmsghdr* hdr = (struct nlmsghdr*)nlmsg.buf; hdr->nlmsg_type = typ; hdr->nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags; memcpy(hdr + 1, data, size); nlmsg.pos = (char*)(hdr + 1) + NLMSG_ALIGN(size); } static void netlink_attr(int typ, const void* data, int size) { struct nlattr* attr = (struct nlattr*)nlmsg.pos; attr->nla_len = sizeof(*attr) + size; attr->nla_type = typ; memcpy(attr + 1, data, size); nlmsg.pos += NLMSG_ALIGN(attr->nla_len); } static void netlink_nest(int typ) { struct nlattr* attr = (struct nlattr*)nlmsg.pos; attr->nla_type = typ; nlmsg.pos += sizeof(*attr); nlmsg.nested[nlmsg.nesting++] = attr; } static void netlink_done(void) { struct nlattr* attr = nlmsg.nested[--nlmsg.nesting]; attr->nla_len = nlmsg.pos - (char*)attr; } static int netlink_send(int sock) { if (nlmsg.pos > nlmsg.buf + sizeof(nlmsg.buf) || nlmsg.nesting) exit(1); struct nlmsghdr* hdr = (struct nlmsghdr*)nlmsg.buf; hdr->nlmsg_len = nlmsg.pos - nlmsg.buf; struct sockaddr_nl addr; memset(&addr, 0, sizeof(addr)); addr.nl_family = AF_NETLINK; unsigned n = sendto(sock, nlmsg.buf, hdr->nlmsg_len, 0, (struct sockaddr*)&addr, sizeof(addr)); if (n != hdr->nlmsg_len) exit(1); n = recv(sock, nlmsg.buf, sizeof(nlmsg.buf), 0); if (n < sizeof(struct nlmsghdr) + sizeof(struct nlmsgerr)) exit(1); if (hdr->nlmsg_type != NLMSG_ERROR) exit(1); return -((struct nlmsgerr*)(hdr + 1))->error; } static void netlink_add_device_impl(const char* type, const char* name) { struct ifinfomsg hdr; memset(&hdr, 0, sizeof(hdr)); netlink_init(RTM_NEWLINK, NLM_F_EXCL | NLM_F_CREATE, &hdr, sizeof(hdr)); if (name) netlink_attr(IFLA_IFNAME, name, strlen(name)); netlink_nest(IFLA_LINKINFO); netlink_attr(IFLA_INFO_KIND, type, strlen(type)); } static void netlink_add_device(int sock, const char* type, const char* name) { netlink_add_device_impl(type, name); netlink_done(); int err = netlink_send(sock); (void)err; } static void netlink_add_veth(int sock, const char* name, const char* peer) { netlink_add_device_impl("veth", name); netlink_nest(IFLA_INFO_DATA); netlink_nest(VETH_INFO_PEER); nlmsg.pos += sizeof(struct ifinfomsg); netlink_attr(IFLA_IFNAME, peer, strlen(peer)); netlink_done(); netlink_done(); netlink_done(); int err = netlink_send(sock); (void)err; } static void netlink_add_hsr(int sock, const char* name, const char* slave1, const char* slave2) { netlink_add_device_impl("hsr", name); netlink_nest(IFLA_INFO_DATA); int ifindex1 = if_nametoindex(slave1); netlink_attr(IFLA_HSR_SLAVE1, &ifindex1, sizeof(ifindex1)); int ifindex2 = if_nametoindex(slave2); netlink_attr(IFLA_HSR_SLAVE2, &ifindex2, sizeof(ifindex2)); netlink_done(); netlink_done(); int err = netlink_send(sock); (void)err; } static void netlink_device_change(int sock, const char* name, bool up, const char* master, const void* mac, int macsize) { struct ifinfomsg hdr; memset(&hdr, 0, sizeof(hdr)); if (up) hdr.ifi_flags = hdr.ifi_change = IFF_UP; netlink_init(RTM_NEWLINK, 0, &hdr, sizeof(hdr)); netlink_attr(IFLA_IFNAME, name, strlen(name)); if (master) { int ifindex = if_nametoindex(master); netlink_attr(IFLA_MASTER, &ifindex, sizeof(ifindex)); } if (macsize) netlink_attr(IFLA_ADDRESS, mac, macsize); int err = netlink_send(sock); (void)err; } static int netlink_add_addr(int sock, const char* dev, const void* addr, int addrsize) { struct ifaddrmsg hdr; memset(&hdr, 0, sizeof(hdr)); hdr.ifa_family = addrsize == 4 ? AF_INET : AF_INET6; hdr.ifa_prefixlen = addrsize == 4 ? 24 : 120; hdr.ifa_scope = RT_SCOPE_UNIVERSE; hdr.ifa_index = if_nametoindex(dev); netlink_init(RTM_NEWADDR, NLM_F_CREATE | NLM_F_REPLACE, &hdr, sizeof(hdr)); netlink_attr(IFA_LOCAL, addr, addrsize); netlink_attr(IFA_ADDRESS, addr, addrsize); return netlink_send(sock); } static void netlink_add_addr4(int sock, const char* dev, const char* addr) { struct in_addr in_addr; inet_pton(AF_INET, addr, &in_addr); int err = netlink_add_addr(sock, dev, &in_addr, sizeof(in_addr)); (void)err; } static void netlink_add_addr6(int sock, const char* dev, const char* addr) { struct in6_addr in6_addr; inet_pton(AF_INET6, addr, &in6_addr); int err = netlink_add_addr(sock, dev, &in6_addr, sizeof(in6_addr)); (void)err; } static void netlink_add_neigh(int sock, const char* name, const void* addr, int addrsize, const void* mac, int macsize) { struct ndmsg hdr; memset(&hdr, 0, sizeof(hdr)); hdr.ndm_family = addrsize == 4 ? AF_INET : AF_INET6; hdr.ndm_ifindex = if_nametoindex(name); hdr.ndm_state = NUD_PERMANENT; netlink_init(RTM_NEWNEIGH, NLM_F_EXCL | NLM_F_CREATE, &hdr, sizeof(hdr)); netlink_attr(NDA_DST, addr, addrsize); netlink_attr(NDA_LLADDR, mac, macsize); int err = netlink_send(sock); (void)err; } static int tunfd = -1; static int tun_frags_enabled; #define SYZ_TUN_MAX_PACKET_SIZE 1000 #define TUN_IFACE "syz_tun" #define LOCAL_MAC 0xaaaaaaaaaaaa #define REMOTE_MAC 0xaaaaaaaaaabb #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 = 240; if (dup2(tunfd, kTunFd) < 0) exit(1); 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) exit(1); } if (ioctl(tunfd, TUNGETIFF, (void*)&ifr) < 0) exit(1); tun_frags_enabled = (ifr.ifr_flags & IFF_NAPI_FRAGS) != 0; char sysctl[64]; sprintf(sysctl, "/proc/sys/net/ipv6/conf/%s/accept_dad", TUN_IFACE); write_file(sysctl, "0"); sprintf(sysctl, "/proc/sys/net/ipv6/conf/%s/router_solicitations", TUN_IFACE); write_file(sysctl, "0"); int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); if (sock == -1) exit(1); netlink_add_addr4(sock, TUN_IFACE, LOCAL_IPV4); netlink_add_addr6(sock, TUN_IFACE, LOCAL_IPV6); uint64_t macaddr = REMOTE_MAC; struct in_addr in_addr; inet_pton(AF_INET, REMOTE_IPV4, &in_addr); netlink_add_neigh(sock, TUN_IFACE, &in_addr, sizeof(in_addr), &macaddr, ETH_ALEN); struct in6_addr in6_addr; inet_pton(AF_INET6, REMOTE_IPV6, &in6_addr); netlink_add_neigh(sock, TUN_IFACE, &in6_addr, sizeof(in6_addr), &macaddr, ETH_ALEN); macaddr = LOCAL_MAC; netlink_device_change(sock, TUN_IFACE, true, 0, &macaddr, ETH_ALEN); close(sock); } #define DEV_IPV4 "172.20.20.%d" #define DEV_IPV6 "fe80::%02x" #define DEV_MAC 0x00aaaaaaaaaa static void initialize_netdevices(void) { char netdevsim[16]; sprintf(netdevsim, "netdevsim%d", (int)procid); struct { const char* type; const char* dev; } devtypes[] = { {"ip6gretap", "ip6gretap0"}, {"bridge", "bridge0"}, {"vcan", "vcan0"}, {"bond", "bond0"}, {"team", "team0"}, {"dummy", "dummy0"}, {"nlmon", "nlmon0"}, {"caif", "caif0"}, {"batadv", "batadv0"}, {"vxcan", "vxcan1"}, {"netdevsim", netdevsim}, {"veth", 0}, }; const char* devmasters[] = {"bridge", "bond", "team"}; struct { const char* name; int macsize; bool noipv6; } devices[] = { {"lo", ETH_ALEN}, {"sit0", 0}, {"bridge0", ETH_ALEN}, {"vcan0", 0, true}, {"tunl0", 0}, {"gre0", 0}, {"gretap0", ETH_ALEN}, {"ip_vti0", 0}, {"ip6_vti0", 0}, {"ip6tnl0", 0}, {"ip6gre0", 0}, {"ip6gretap0", ETH_ALEN}, {"erspan0", ETH_ALEN}, {"bond0", ETH_ALEN}, {"veth0", ETH_ALEN}, {"veth1", ETH_ALEN}, {"team0", ETH_ALEN}, {"veth0_to_bridge", ETH_ALEN}, {"veth1_to_bridge", ETH_ALEN}, {"veth0_to_bond", ETH_ALEN}, {"veth1_to_bond", ETH_ALEN}, {"veth0_to_team", ETH_ALEN}, {"veth1_to_team", ETH_ALEN}, {"veth0_to_hsr", ETH_ALEN}, {"veth1_to_hsr", ETH_ALEN}, {"hsr0", 0}, {"dummy0", ETH_ALEN}, {"nlmon0", 0}, {"vxcan1", 0, true}, {"caif0", ETH_ALEN}, {"batadv0", ETH_ALEN}, {netdevsim, ETH_ALEN}, }; int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); if (sock == -1) exit(1); unsigned i; for (i = 0; i < sizeof(devtypes) / sizeof(devtypes[0]); i++) netlink_add_device(sock, devtypes[i].type, devtypes[i].dev); for (i = 0; i < sizeof(devmasters) / (sizeof(devmasters[0])); i++) { char master[32], slave0[32], veth0[32], slave1[32], veth1[32]; sprintf(slave0, "%s_slave_0", devmasters[i]); sprintf(veth0, "veth0_to_%s", devmasters[i]); netlink_add_veth(sock, slave0, veth0); sprintf(slave1, "%s_slave_1", devmasters[i]); sprintf(veth1, "veth1_to_%s", devmasters[i]); netlink_add_veth(sock, slave1, veth1); sprintf(master, "%s0", devmasters[i]); netlink_device_change(sock, slave0, false, master, 0, 0); netlink_device_change(sock, slave1, false, master, 0, 0); } netlink_device_change(sock, "bridge_slave_0", true, 0, 0, 0); netlink_device_change(sock, "bridge_slave_1", true, 0, 0, 0); netlink_add_veth(sock, "hsr_slave_0", "veth0_to_hsr"); netlink_add_veth(sock, "hsr_slave_1", "veth1_to_hsr"); netlink_add_hsr(sock, "hsr0", "hsr_slave_0", "hsr_slave_1"); netlink_device_change(sock, "hsr_slave_0", true, 0, 0, 0); netlink_device_change(sock, "hsr_slave_1", true, 0, 0, 0); for (i = 0; i < sizeof(devices) / (sizeof(devices[0])); i++) { char addr[32]; sprintf(addr, DEV_IPV4, i + 10); netlink_add_addr4(sock, devices[i].name, addr); if (!devices[i].noipv6) { sprintf(addr, DEV_IPV6, i + 10); netlink_add_addr6(sock, devices[i].name, addr); } uint64_t macaddr = DEV_MAC + ((i + 10ull) << 40); netlink_device_change(sock, devices[i].name, true, 0, &macaddr, devices[i].macsize); } close(sock); } static void initialize_netdevices_init(void) { int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); if (sock == -1) exit(1); struct { const char* type; int macsize; bool noipv6; bool noup; } devtypes[] = { {"nr", 7, true}, {"rose", 5, true, true}, }; unsigned i; for (i = 0; i < sizeof(devtypes) / sizeof(devtypes[0]); i++) { char dev[32], addr[32]; sprintf(dev, "%s%d", devtypes[i].type, (int)procid); sprintf(addr, "172.30.%d.%d", i, (int)procid + 1); netlink_add_addr4(sock, dev, addr); if (!devtypes[i].noipv6) { sprintf(addr, "fe88::%02x:%02x", i, (int)procid + 1); netlink_add_addr6(sock, dev, addr); } int macsize = devtypes[i].macsize; uint64_t macaddr = 0xbbbbbb + ((unsigned long long)i << (8 * (macsize - 2))) + (procid << (8 * (macsize - 1))); netlink_device_change(sock, dev, !devtypes[i].noup, 0, &macaddr, macsize); } close(sock); } 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; exit(1); } return rv; } static void flush_tun() { char data[SYZ_TUN_MAX_PACKET_SIZE]; while (read_tun(&data[0], sizeof(data)) != -1) { } } #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) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } 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; } exit(1); } if (table->info.size > sizeof(table->replace.entrytable)) exit(1); if (table->info.num_entries > XT_MAX_ENTRIES) exit(1); 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) { 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) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } 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)) exit(1); 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)) exit(1); 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)) exit(1); } 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) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } 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; } exit(1); } if (table->info.size > sizeof(table->replace.entrytable)) exit(1); if (table->info.num_entries > XT_MAX_ENTRIES) exit(1); 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() { 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) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } 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)) exit(1); 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)) exit(1); if (memcmp(table->replace.entrytable, entries.entrytable, table->info.size) == 0) continue; } else { } 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) { socklen_t optlen; unsigned i; int fd; fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); if (fd == -1) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } 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; } 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() { 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) { switch (errno) { case EAFNOSUPPORT: case ENOPROTOOPT: return; } exit(1); } 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)) exit(1); replace.num_counters = 0; table->replace.entries = 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)) exit(1); 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++; } } 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 setup_common() { if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) { } } 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 = (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 = 0; setrlimit(RLIMIT_CORE, &rlim); rlim.rlim_cur = rlim.rlim_max = 256; setrlimit(RLIMIT_NOFILE, &rlim); if (unshare(CLONE_NEWNS)) { } 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); } int wait_for_loop(int pid) { if (pid < 0) exit(1); int status = 0; while (waitpid(-1, &status, __WALL) != pid) { } return WEXITSTATUS(status); } 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(); initialize_netdevices_init(); if (unshare(CLONE_NEWNET)) { } initialize_tun(); initialize_netdevices(); loop(); exit(1); } static void kill_and_wait(int pid, int* status) { kill(-pid, SIGKILL); kill(pid, SIGKILL); int i; for (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() { checkpoint_net_namespace(); } static void reset_loop() { reset_net_namespace(); } static void setup_test() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); write_file("/proc/self/oom_score_adj", "1000"); flush_tun(); } static void close_fds() { int fd; for (fd = 3; fd < 30; fd++) close(fd); } 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; int collide = 0; again: for (call = 0; call < 7; 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 (collide && (call % 2) == 0) break; event_timedwait(&th->done, 45); break; } } for (i = 0; i < 100 && __atomic_load_n(&running, __ATOMIC_RELAXED); i++) sleep_ms(1); close_fds(); if (!collide) { collide = 1; goto again; } } static void execute_one(void); #define WAIT_FLAGS __WALL static void loop(void) { setup_loop(); int iter; for (iter = 0;; iter++) { reset_loop(); int pid = fork(); if (pid < 0) exit(1); if (pid == 0) { 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 < 5 * 1000) continue; kill_and_wait(pid, &status); break; } } } #ifndef __NR_bpf #define __NR_bpf 321 #endif void execute_call(int call) { switch (call) { case 0: syscall(__NR_mkdir, 0, 0); break; case 1: syscall(__NR_mount, 0x20000000, 0, 0, 0x2001001, 0); break; case 2: NONFAILING(*(uint32_t*)0x2001d000 = 1); NONFAILING(*(uint32_t*)0x2001d004 = 0x70); NONFAILING(*(uint8_t*)0x2001d008 = 0); NONFAILING(*(uint8_t*)0x2001d009 = 0); NONFAILING(*(uint8_t*)0x2001d00a = 0); NONFAILING(*(uint8_t*)0x2001d00b = 0); NONFAILING(*(uint32_t*)0x2001d00c = 0); NONFAILING(*(uint64_t*)0x2001d010 = 0x7f); NONFAILING(*(uint64_t*)0x2001d018 = 0); NONFAILING(*(uint64_t*)0x2001d020 = 0); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 0, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 1, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 2, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 3, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 4, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 3, 5, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 6, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 7, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 8, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 9, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 10, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 11, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 12, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 13, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 14, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 15, 2)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 17, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 18, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 19, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 20, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 21, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 22, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 23, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 24, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 25, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 26, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 27, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 28, 1)); NONFAILING(STORE_BY_BITMASK(uint64_t, , 0x2001d028, 0, 29, 35)); NONFAILING(*(uint32_t*)0x2001d030 = 0); NONFAILING(*(uint32_t*)0x2001d034 = 0); NONFAILING(*(uint64_t*)0x2001d038 = 0); NONFAILING(*(uint64_t*)0x2001d040 = 0); NONFAILING(*(uint64_t*)0x2001d048 = 0); NONFAILING(*(uint64_t*)0x2001d050 = 0); NONFAILING(*(uint32_t*)0x2001d058 = 0); NONFAILING(*(uint32_t*)0x2001d05c = 0); NONFAILING(*(uint64_t*)0x2001d060 = 0); NONFAILING(*(uint32_t*)0x2001d068 = 0); NONFAILING(*(uint16_t*)0x2001d06c = 0); NONFAILING(*(uint16_t*)0x2001d06e = 0); syscall(__NR_perf_event_open, 0x2001d000, 0, -1, -1, 0); break; case 3: syscall(__NR_prctl, 0x23, 0xf, 0, 0); break; case 4: syscall(__NR_readlink, 0, 0, 0); break; case 5: syscall(__NR_bpf, 0xc, 0, 0); break; case 6: NONFAILING(*(uint32_t*)0x20000080 = 5); NONFAILING(*(uint32_t*)0x20000084 = 3); NONFAILING(*(uint64_t*)0x20000088 = 0x20001fd8); NONFAILING(*(uint8_t*)0x20001fd8 = 0x85); NONFAILING(STORE_BY_BITMASK(uint8_t, , 0x20001fd9, 0, 0, 4)); NONFAILING(STORE_BY_BITMASK(uint8_t, , 0x20001fd9, 0, 4, 4)); NONFAILING(*(uint16_t*)0x20001fda = 0); NONFAILING(*(uint32_t*)0x20001fdc = 7); NONFAILING(*(uint8_t*)0x20001fe0 = 0x25); NONFAILING(*(uint8_t*)0x20001fe1 = 0); NONFAILING(*(uint16_t*)0x20001fe2 = 0); NONFAILING(*(uint32_t*)0x20001fe4 = 0); NONFAILING(*(uint8_t*)0x20001fe8 = 0x95); NONFAILING(*(uint8_t*)0x20001fe9 = 0); NONFAILING(*(uint16_t*)0x20001fea = 0); NONFAILING(*(uint32_t*)0x20001fec = 0); NONFAILING(*(uint64_t*)0x20000090 = 0x20000000); NONFAILING(memcpy( (void*)0x20000000, "PL " "\000L\367\321*\361\034\351%7\265\343\031\036f\336]N\301\216L-" "\360\024\204\250mw\204/" "bIF\352\343\020yL\214\226\377\024f#.%\225\0219\275\245\322\231\016R?" "\216\303\b\017\374\022$\330\334L\204\251\310\350\2531Wh\006qU#" "\372t\236\206\025\306\020I\270\261\276j\247t\a\002\314Z\335", 100)); NONFAILING(*(uint32_t*)0x20000098 = 5); NONFAILING(*(uint32_t*)0x2000009c = 0x252); NONFAILING(*(uint64_t*)0x200000a0 = 0x2000cf3d); NONFAILING(*(uint32_t*)0x200000a8 = 0); NONFAILING(*(uint32_t*)0x200000ac = 0); NONFAILING(*(uint8_t*)0x200000b0 = 0); NONFAILING(*(uint8_t*)0x200000b1 = 0); NONFAILING(*(uint8_t*)0x200000b2 = 0); NONFAILING(*(uint8_t*)0x200000b3 = 0); NONFAILING(*(uint8_t*)0x200000b4 = 0); NONFAILING(*(uint8_t*)0x200000b5 = 0); NONFAILING(*(uint8_t*)0x200000b6 = 0); NONFAILING(*(uint8_t*)0x200000b7 = 0); NONFAILING(*(uint8_t*)0x200000b8 = 0); NONFAILING(*(uint8_t*)0x200000b9 = 0); NONFAILING(*(uint8_t*)0x200000ba = 0); NONFAILING(*(uint8_t*)0x200000bb = 0); NONFAILING(*(uint8_t*)0x200000bc = 0); NONFAILING(*(uint8_t*)0x200000bd = 0); NONFAILING(*(uint8_t*)0x200000be = 0); NONFAILING(*(uint8_t*)0x200000bf = 0); NONFAILING(*(uint32_t*)0x200000c0 = 0); NONFAILING(*(uint32_t*)0x200000c4 = 0); NONFAILING(*(uint32_t*)0x200000c8 = -1); NONFAILING(*(uint32_t*)0x200000cc = 8); NONFAILING(*(uint64_t*)0x200000d0 = 0x20000000); NONFAILING(*(uint32_t*)0x20000000 = 0); NONFAILING(*(uint32_t*)0x20000004 = 0); NONFAILING(*(uint32_t*)0x200000d8 = 0); NONFAILING(*(uint32_t*)0x200000dc = 0x10); NONFAILING(*(uint64_t*)0x200000e0 = 0x20000000); NONFAILING(*(uint32_t*)0x20000000 = 0); NONFAILING(*(uint32_t*)0x20000004 = 0); NONFAILING(*(uint32_t*)0x20000008 = 0); NONFAILING(*(uint32_t*)0x2000000c = 0); NONFAILING(*(uint32_t*)0x200000e8 = 0); syscall(__NR_bpf, 5, 0x20000080, 0x48); break; } } int main(void) { syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0); install_segv_handler(); for (procid = 0; procid < 6; procid++) { if (fork() == 0) { do_sandbox_none(); } } sleep(1000000); return 0; }