// https://syzkaller.appspot.com/bug?id=d24737e004c679ad45678f20e9aec57c98f9b478 // 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 #include #include #include #include static 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; 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 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; } struct nlmsg { char* pos; int nesting; struct nlattr* nested[8]; char buf[4096]; }; static void netlink_init(struct nlmsg* nlmsg, 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(struct nlmsg* nlmsg, int typ, const void* data, int size) { struct nlattr* attr = (struct nlattr*)nlmsg->pos; attr->nla_len = sizeof(*attr) + size; attr->nla_type = typ; if (size > 0) memcpy(attr + 1, data, size); nlmsg->pos += NLMSG_ALIGN(attr->nla_len); } static void netlink_nest(struct nlmsg* nlmsg, 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(struct nlmsg* nlmsg) { struct nlattr* attr = nlmsg->nested[--nlmsg->nesting]; attr->nla_len = nlmsg->pos - (char*)attr; } static int netlink_send_ext(struct nlmsg* nlmsg, int sock, uint16_t reply_type, int* reply_len) { 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 (reply_len) *reply_len = 0; if (hdr->nlmsg_type == NLMSG_DONE) return 0; if (n < sizeof(struct nlmsghdr)) exit(1); if (reply_len && hdr->nlmsg_type == reply_type) { *reply_len = n; return 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 int netlink_send(struct nlmsg* nlmsg, int sock) { return netlink_send_ext(nlmsg, sock, 0, NULL); } static int netlink_query_family_id(struct nlmsg* nlmsg, int sock, const char* family_name) { struct genlmsghdr genlhdr; memset(&genlhdr, 0, sizeof(genlhdr)); genlhdr.cmd = CTRL_CMD_GETFAMILY; netlink_init(nlmsg, GENL_ID_CTRL, 0, &genlhdr, sizeof(genlhdr)); netlink_attr(nlmsg, CTRL_ATTR_FAMILY_NAME, family_name, strnlen(family_name, GENL_NAMSIZ - 1) + 1); int n = 0; int err = netlink_send_ext(nlmsg, sock, GENL_ID_CTRL, &n); if (err < 0) { return -1; } uint16_t id = 0; struct nlattr* attr = (struct nlattr*)(nlmsg->buf + NLMSG_HDRLEN + NLMSG_ALIGN(sizeof(genlhdr))); for (; (char*)attr < nlmsg->buf + n; attr = (struct nlattr*)((char*)attr + NLMSG_ALIGN(attr->nla_len))) { if (attr->nla_type == CTRL_ATTR_FAMILY_ID) { id = *(uint16_t*)(attr + 1); break; } } if (!id) { return -1; } recv(sock, nlmsg->buf, sizeof(nlmsg->buf), 0); return id; } static int netlink_next_msg(struct nlmsg* nlmsg, unsigned int offset, unsigned int total_len) { struct nlmsghdr* hdr = (struct nlmsghdr*)(nlmsg->buf + offset); if (offset == total_len || offset + hdr->nlmsg_len > total_len) return -1; return hdr->nlmsg_len; } static void netlink_add_device_impl(struct nlmsg* nlmsg, const char* type, const char* name) { struct ifinfomsg hdr; memset(&hdr, 0, sizeof(hdr)); netlink_init(nlmsg, RTM_NEWLINK, NLM_F_EXCL | NLM_F_CREATE, &hdr, sizeof(hdr)); if (name) netlink_attr(nlmsg, IFLA_IFNAME, name, strlen(name)); netlink_nest(nlmsg, IFLA_LINKINFO); netlink_attr(nlmsg, IFLA_INFO_KIND, type, strlen(type)); } static void netlink_add_device(struct nlmsg* nlmsg, int sock, const char* type, const char* name) { netlink_add_device_impl(nlmsg, type, name); netlink_done(nlmsg); int err = netlink_send(nlmsg, sock); (void)err; } static void netlink_add_veth(struct nlmsg* nlmsg, int sock, const char* name, const char* peer) { netlink_add_device_impl(nlmsg, "veth", name); netlink_nest(nlmsg, IFLA_INFO_DATA); netlink_nest(nlmsg, VETH_INFO_PEER); nlmsg->pos += sizeof(struct ifinfomsg); netlink_attr(nlmsg, IFLA_IFNAME, peer, strlen(peer)); netlink_done(nlmsg); netlink_done(nlmsg); netlink_done(nlmsg); int err = netlink_send(nlmsg, sock); (void)err; } static void netlink_add_hsr(struct nlmsg* nlmsg, int sock, const char* name, const char* slave1, const char* slave2) { netlink_add_device_impl(nlmsg, "hsr", name); netlink_nest(nlmsg, IFLA_INFO_DATA); int ifindex1 = if_nametoindex(slave1); netlink_attr(nlmsg, IFLA_HSR_SLAVE1, &ifindex1, sizeof(ifindex1)); int ifindex2 = if_nametoindex(slave2); netlink_attr(nlmsg, IFLA_HSR_SLAVE2, &ifindex2, sizeof(ifindex2)); netlink_done(nlmsg); netlink_done(nlmsg); int err = netlink_send(nlmsg, sock); (void)err; } static void netlink_add_linked(struct nlmsg* nlmsg, int sock, const char* type, const char* name, const char* link) { netlink_add_device_impl(nlmsg, type, name); netlink_done(nlmsg); int ifindex = if_nametoindex(link); netlink_attr(nlmsg, IFLA_LINK, &ifindex, sizeof(ifindex)); int err = netlink_send(nlmsg, sock); (void)err; } static void netlink_add_vlan(struct nlmsg* nlmsg, int sock, const char* name, const char* link, uint16_t id, uint16_t proto) { netlink_add_device_impl(nlmsg, "vlan", name); netlink_nest(nlmsg, IFLA_INFO_DATA); netlink_attr(nlmsg, IFLA_VLAN_ID, &id, sizeof(id)); netlink_attr(nlmsg, IFLA_VLAN_PROTOCOL, &proto, sizeof(proto)); netlink_done(nlmsg); netlink_done(nlmsg); int ifindex = if_nametoindex(link); netlink_attr(nlmsg, IFLA_LINK, &ifindex, sizeof(ifindex)); int err = netlink_send(nlmsg, sock); (void)err; } static void netlink_add_macvlan(struct nlmsg* nlmsg, int sock, const char* name, const char* link) { netlink_add_device_impl(nlmsg, "macvlan", name); netlink_nest(nlmsg, IFLA_INFO_DATA); uint32_t mode = MACVLAN_MODE_BRIDGE; netlink_attr(nlmsg, IFLA_MACVLAN_MODE, &mode, sizeof(mode)); netlink_done(nlmsg); netlink_done(nlmsg); int ifindex = if_nametoindex(link); netlink_attr(nlmsg, IFLA_LINK, &ifindex, sizeof(ifindex)); int err = netlink_send(nlmsg, sock); (void)err; } static void netlink_add_geneve(struct nlmsg* nlmsg, int sock, const char* name, uint32_t vni, struct in_addr* addr4, struct in6_addr* addr6) { netlink_add_device_impl(nlmsg, "geneve", name); netlink_nest(nlmsg, IFLA_INFO_DATA); netlink_attr(nlmsg, IFLA_GENEVE_ID, &vni, sizeof(vni)); if (addr4) netlink_attr(nlmsg, IFLA_GENEVE_REMOTE, addr4, sizeof(*addr4)); if (addr6) netlink_attr(nlmsg, IFLA_GENEVE_REMOTE6, addr6, sizeof(*addr6)); netlink_done(nlmsg); netlink_done(nlmsg); int err = netlink_send(nlmsg, sock); (void)err; } #define IFLA_IPVLAN_FLAGS 2 #define IPVLAN_MODE_L3S 2 #undef IPVLAN_F_VEPA #define IPVLAN_F_VEPA 2 static void netlink_add_ipvlan(struct nlmsg* nlmsg, int sock, const char* name, const char* link, uint16_t mode, uint16_t flags) { netlink_add_device_impl(nlmsg, "ipvlan", name); netlink_nest(nlmsg, IFLA_INFO_DATA); netlink_attr(nlmsg, IFLA_IPVLAN_MODE, &mode, sizeof(mode)); netlink_attr(nlmsg, IFLA_IPVLAN_FLAGS, &flags, sizeof(flags)); netlink_done(nlmsg); netlink_done(nlmsg); int ifindex = if_nametoindex(link); netlink_attr(nlmsg, IFLA_LINK, &ifindex, sizeof(ifindex)); int err = netlink_send(nlmsg, sock); (void)err; } static void netlink_device_change(struct nlmsg* nlmsg, int sock, const char* name, bool up, const char* master, const void* mac, int macsize, const char* new_name) { struct ifinfomsg hdr; memset(&hdr, 0, sizeof(hdr)); if (up) hdr.ifi_flags = hdr.ifi_change = IFF_UP; hdr.ifi_index = if_nametoindex(name); netlink_init(nlmsg, RTM_NEWLINK, 0, &hdr, sizeof(hdr)); if (new_name) netlink_attr(nlmsg, IFLA_IFNAME, new_name, strlen(new_name)); if (master) { int ifindex = if_nametoindex(master); netlink_attr(nlmsg, IFLA_MASTER, &ifindex, sizeof(ifindex)); } if (macsize) netlink_attr(nlmsg, IFLA_ADDRESS, mac, macsize); int err = netlink_send(nlmsg, sock); (void)err; } static int netlink_add_addr(struct nlmsg* nlmsg, 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(nlmsg, RTM_NEWADDR, NLM_F_CREATE | NLM_F_REPLACE, &hdr, sizeof(hdr)); netlink_attr(nlmsg, IFA_LOCAL, addr, addrsize); netlink_attr(nlmsg, IFA_ADDRESS, addr, addrsize); return netlink_send(nlmsg, sock); } static void netlink_add_addr4(struct nlmsg* nlmsg, 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(nlmsg, sock, dev, &in_addr, sizeof(in_addr)); (void)err; } static void netlink_add_addr6(struct nlmsg* nlmsg, 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(nlmsg, sock, dev, &in6_addr, sizeof(in6_addr)); (void)err; } static void netlink_add_neigh(struct nlmsg* nlmsg, 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(nlmsg, RTM_NEWNEIGH, NLM_F_EXCL | NLM_F_CREATE, &hdr, sizeof(hdr)); netlink_attr(nlmsg, NDA_DST, addr, addrsize); netlink_attr(nlmsg, NDA_LLADDR, mac, macsize); int err = netlink_send(nlmsg, sock); (void)err; } static struct nlmsg nlmsg; static int tunfd = -1; #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 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; if (ioctl(tunfd, TUNSETIFF, (void*)&ifr) < 0) { exit(1); } 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(&nlmsg, sock, TUN_IFACE, LOCAL_IPV4); netlink_add_addr6(&nlmsg, 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(&nlmsg, 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(&nlmsg, sock, TUN_IFACE, &in6_addr, sizeof(in6_addr), &macaddr, ETH_ALEN); macaddr = LOCAL_MAC; netlink_device_change(&nlmsg, sock, TUN_IFACE, true, 0, &macaddr, ETH_ALEN, NULL); close(sock); } #define DEVLINK_FAMILY_NAME "devlink" #define DEVLINK_CMD_PORT_GET 5 #define DEVLINK_ATTR_BUS_NAME 1 #define DEVLINK_ATTR_DEV_NAME 2 #define DEVLINK_ATTR_NETDEV_NAME 7 static struct nlmsg nlmsg2; static void initialize_devlink_ports(const char* bus_name, const char* dev_name, const char* netdev_prefix) { struct genlmsghdr genlhdr; int len, total_len, id, err, offset; uint16_t netdev_index; int sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); if (sock == -1) exit(1); int rtsock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); if (rtsock == -1) exit(1); id = netlink_query_family_id(&nlmsg, sock, DEVLINK_FAMILY_NAME); if (id == -1) goto error; memset(&genlhdr, 0, sizeof(genlhdr)); genlhdr.cmd = DEVLINK_CMD_PORT_GET; netlink_init(&nlmsg, id, NLM_F_DUMP, &genlhdr, sizeof(genlhdr)); netlink_attr(&nlmsg, DEVLINK_ATTR_BUS_NAME, bus_name, strlen(bus_name) + 1); netlink_attr(&nlmsg, DEVLINK_ATTR_DEV_NAME, dev_name, strlen(dev_name) + 1); err = netlink_send_ext(&nlmsg, sock, id, &total_len); if (err < 0) { goto error; } offset = 0; netdev_index = 0; while ((len = netlink_next_msg(&nlmsg, offset, total_len)) != -1) { struct nlattr* attr = (struct nlattr*)(nlmsg.buf + offset + NLMSG_HDRLEN + NLMSG_ALIGN(sizeof(genlhdr))); for (; (char*)attr < nlmsg.buf + offset + len; attr = (struct nlattr*)((char*)attr + NLMSG_ALIGN(attr->nla_len))) { if (attr->nla_type == DEVLINK_ATTR_NETDEV_NAME) { char* port_name; char netdev_name[IFNAMSIZ]; port_name = (char*)(attr + 1); snprintf(netdev_name, sizeof(netdev_name), "%s%d", netdev_prefix, netdev_index); netlink_device_change(&nlmsg2, rtsock, port_name, true, 0, 0, 0, netdev_name); break; } } offset += len; netdev_index++; } error: close(rtsock); close(sock); } #define DEV_IPV4 "172.20.20.%d" #define DEV_IPV6 "fe80::%02x" #define DEV_MAC 0x00aaaaaaaaaa static void netdevsim_add(unsigned int addr, unsigned int port_count) { char buf[16]; sprintf(buf, "%u %u", addr, port_count); if (write_file("/sys/bus/netdevsim/new_device", buf)) { snprintf(buf, sizeof(buf), "netdevsim%d", addr); initialize_devlink_ports("netdevsim", buf, "netdevsim"); } } #define WG_GENL_NAME "wireguard" enum wg_cmd { WG_CMD_GET_DEVICE, WG_CMD_SET_DEVICE, }; enum wgdevice_attribute { WGDEVICE_A_UNSPEC, WGDEVICE_A_IFINDEX, WGDEVICE_A_IFNAME, WGDEVICE_A_PRIVATE_KEY, WGDEVICE_A_PUBLIC_KEY, WGDEVICE_A_FLAGS, WGDEVICE_A_LISTEN_PORT, WGDEVICE_A_FWMARK, WGDEVICE_A_PEERS, }; enum wgpeer_attribute { WGPEER_A_UNSPEC, WGPEER_A_PUBLIC_KEY, WGPEER_A_PRESHARED_KEY, WGPEER_A_FLAGS, WGPEER_A_ENDPOINT, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, WGPEER_A_LAST_HANDSHAKE_TIME, WGPEER_A_RX_BYTES, WGPEER_A_TX_BYTES, WGPEER_A_ALLOWEDIPS, WGPEER_A_PROTOCOL_VERSION, }; enum wgallowedip_attribute { WGALLOWEDIP_A_UNSPEC, WGALLOWEDIP_A_FAMILY, WGALLOWEDIP_A_IPADDR, WGALLOWEDIP_A_CIDR_MASK, }; static void netlink_wireguard_setup(void) { const char ifname_a[] = "wg0"; const char ifname_b[] = "wg1"; const char ifname_c[] = "wg2"; const char private_a[] = "\xa0\x5c\xa8\x4f\x6c\x9c\x8e\x38\x53\xe2\xfd\x7a" "\x70\xae\x0f\xb2\x0f\xa1\x52\x60\x0c\xb0\x08\x45" "\x17\x4f\x08\x07\x6f\x8d\x78\x43"; const char private_b[] = "\xb0\x80\x73\xe8\xd4\x4e\x91\xe3\xda\x92\x2c\x22" "\x43\x82\x44\xbb\x88\x5c\x69\xe2\x69\xc8\xe9\xd8" "\x35\xb1\x14\x29\x3a\x4d\xdc\x6e"; const char private_c[] = "\xa0\xcb\x87\x9a\x47\xf5\xbc\x64\x4c\x0e\x69\x3f" "\xa6\xd0\x31\xc7\x4a\x15\x53\xb6\xe9\x01\xb9\xff" "\x2f\x51\x8c\x78\x04\x2f\xb5\x42"; const char public_a[] = "\x97\x5c\x9d\x81\xc9\x83\xc8\x20\x9e\xe7\x81\x25\x4b" "\x89\x9f\x8e\xd9\x25\xae\x9f\x09\x23\xc2\x3c\x62\xf5" "\x3c\x57\xcd\xbf\x69\x1c"; const char public_b[] = "\xd1\x73\x28\x99\xf6\x11\xcd\x89\x94\x03\x4d\x7f\x41" "\x3d\xc9\x57\x63\x0e\x54\x93\xc2\x85\xac\xa4\x00\x65" "\xcb\x63\x11\xbe\x69\x6b"; const char public_c[] = "\xf4\x4d\xa3\x67\xa8\x8e\xe6\x56\x4f\x02\x02\x11\x45" "\x67\x27\x08\x2f\x5c\xeb\xee\x8b\x1b\xf5\xeb\x73\x37" "\x34\x1b\x45\x9b\x39\x22"; const uint16_t listen_a = 20001; const uint16_t listen_b = 20002; const uint16_t listen_c = 20003; const uint16_t af_inet = AF_INET; const uint16_t af_inet6 = AF_INET6; const struct sockaddr_in endpoint_b_v4 = { .sin_family = AF_INET, .sin_port = htons(listen_b), .sin_addr = {htonl(INADDR_LOOPBACK)}}; const struct sockaddr_in endpoint_c_v4 = { .sin_family = AF_INET, .sin_port = htons(listen_c), .sin_addr = {htonl(INADDR_LOOPBACK)}}; struct sockaddr_in6 endpoint_a_v6 = {.sin6_family = AF_INET6, .sin6_port = htons(listen_a)}; endpoint_a_v6.sin6_addr = in6addr_loopback; struct sockaddr_in6 endpoint_c_v6 = {.sin6_family = AF_INET6, .sin6_port = htons(listen_c)}; endpoint_c_v6.sin6_addr = in6addr_loopback; const struct in_addr first_half_v4 = {0}; const struct in_addr second_half_v4 = {(uint32_t)htonl(128 << 24)}; const struct in6_addr first_half_v6 = {{{0}}}; const struct in6_addr second_half_v6 = {{{0x80}}}; const uint8_t half_cidr = 1; const uint16_t persistent_keepalives[] = {1, 3, 7, 9, 14, 19}; struct genlmsghdr genlhdr = {.cmd = WG_CMD_SET_DEVICE, .version = 1}; int sock; int id, err; sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); if (sock == -1) { return; } id = netlink_query_family_id(&nlmsg, sock, WG_GENL_NAME); if (id == -1) goto error; netlink_init(&nlmsg, id, 0, &genlhdr, sizeof(genlhdr)); netlink_attr(&nlmsg, WGDEVICE_A_IFNAME, ifname_a, strlen(ifname_a) + 1); netlink_attr(&nlmsg, WGDEVICE_A_PRIVATE_KEY, private_a, 32); netlink_attr(&nlmsg, WGDEVICE_A_LISTEN_PORT, &listen_a, 2); netlink_nest(&nlmsg, NLA_F_NESTED | WGDEVICE_A_PEERS); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_b, 32); netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_b_v4, sizeof(endpoint_b_v4)); netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[0], 2); netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v4, sizeof(first_half_v4)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v6, sizeof(first_half_v6)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_c, 32); netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_c_v6, sizeof(endpoint_c_v6)); netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[1], 2); netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v4, sizeof(second_half_v4)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v6, sizeof(second_half_v6)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_done(&nlmsg); err = netlink_send(&nlmsg, sock); if (err < 0) { } netlink_init(&nlmsg, id, 0, &genlhdr, sizeof(genlhdr)); netlink_attr(&nlmsg, WGDEVICE_A_IFNAME, ifname_b, strlen(ifname_b) + 1); netlink_attr(&nlmsg, WGDEVICE_A_PRIVATE_KEY, private_b, 32); netlink_attr(&nlmsg, WGDEVICE_A_LISTEN_PORT, &listen_b, 2); netlink_nest(&nlmsg, NLA_F_NESTED | WGDEVICE_A_PEERS); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_a, 32); netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_a_v6, sizeof(endpoint_a_v6)); netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[2], 2); netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v4, sizeof(first_half_v4)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v6, sizeof(first_half_v6)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_c, 32); netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_c_v4, sizeof(endpoint_c_v4)); netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[3], 2); netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v4, sizeof(second_half_v4)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v6, sizeof(second_half_v6)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_done(&nlmsg); err = netlink_send(&nlmsg, sock); if (err < 0) { } netlink_init(&nlmsg, id, 0, &genlhdr, sizeof(genlhdr)); netlink_attr(&nlmsg, WGDEVICE_A_IFNAME, ifname_c, strlen(ifname_c) + 1); netlink_attr(&nlmsg, WGDEVICE_A_PRIVATE_KEY, private_c, 32); netlink_attr(&nlmsg, WGDEVICE_A_LISTEN_PORT, &listen_c, 2); netlink_nest(&nlmsg, NLA_F_NESTED | WGDEVICE_A_PEERS); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_a, 32); netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_a_v6, sizeof(endpoint_a_v6)); netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[4], 2); netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v4, sizeof(first_half_v4)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &first_half_v6, sizeof(first_half_v6)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGPEER_A_PUBLIC_KEY, public_b, 32); netlink_attr(&nlmsg, WGPEER_A_ENDPOINT, &endpoint_b_v4, sizeof(endpoint_b_v4)); netlink_attr(&nlmsg, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL, &persistent_keepalives[5], 2); netlink_nest(&nlmsg, NLA_F_NESTED | WGPEER_A_ALLOWEDIPS); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v4, sizeof(second_half_v4)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_nest(&nlmsg, NLA_F_NESTED | 0); netlink_attr(&nlmsg, WGALLOWEDIP_A_FAMILY, &af_inet6, 2); netlink_attr(&nlmsg, WGALLOWEDIP_A_IPADDR, &second_half_v6, sizeof(second_half_v6)); netlink_attr(&nlmsg, WGALLOWEDIP_A_CIDR_MASK, &half_cidr, 1); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_done(&nlmsg); netlink_done(&nlmsg); err = netlink_send(&nlmsg, sock); if (err < 0) { } error: close(sock); } 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}, {"xfrm", "xfrm0"}, {"wireguard", "wg0"}, {"wireguard", "wg1"}, {"wireguard", "wg2"}, }; const char* devmasters[] = {"bridge", "bond", "team", "batadv"}; 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}, {"vxcan0", 0, true}, {"vxcan1", 0, true}, {"caif0", ETH_ALEN}, {"batadv0", ETH_ALEN}, {netdevsim, ETH_ALEN}, {"xfrm0", ETH_ALEN}, {"veth0_virt_wifi", ETH_ALEN}, {"veth1_virt_wifi", ETH_ALEN}, {"virt_wifi0", ETH_ALEN}, {"veth0_vlan", ETH_ALEN}, {"veth1_vlan", ETH_ALEN}, {"vlan0", ETH_ALEN}, {"vlan1", ETH_ALEN}, {"macvlan0", ETH_ALEN}, {"macvlan1", ETH_ALEN}, {"ipvlan0", ETH_ALEN}, {"ipvlan1", ETH_ALEN}, {"veth0_macvtap", ETH_ALEN}, {"veth1_macvtap", ETH_ALEN}, {"macvtap0", ETH_ALEN}, {"macsec0", ETH_ALEN}, {"veth0_to_batadv", ETH_ALEN}, {"veth1_to_batadv", ETH_ALEN}, {"batadv_slave_0", ETH_ALEN}, {"batadv_slave_1", ETH_ALEN}, {"geneve0", ETH_ALEN}, {"geneve1", ETH_ALEN}, {"wg0", 0}, {"wg1", 0}, {"wg2", 0}, }; 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(&nlmsg, 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(&nlmsg, sock, slave0, veth0); sprintf(slave1, "%s_slave_1", devmasters[i]); sprintf(veth1, "veth1_to_%s", devmasters[i]); netlink_add_veth(&nlmsg, sock, slave1, veth1); sprintf(master, "%s0", devmasters[i]); netlink_device_change(&nlmsg, sock, slave0, false, master, 0, 0, NULL); netlink_device_change(&nlmsg, sock, slave1, false, master, 0, 0, NULL); } netlink_device_change(&nlmsg, sock, "bridge_slave_0", true, 0, 0, 0, NULL); netlink_device_change(&nlmsg, sock, "bridge_slave_1", true, 0, 0, 0, NULL); netlink_add_veth(&nlmsg, sock, "hsr_slave_0", "veth0_to_hsr"); netlink_add_veth(&nlmsg, sock, "hsr_slave_1", "veth1_to_hsr"); netlink_add_hsr(&nlmsg, sock, "hsr0", "hsr_slave_0", "hsr_slave_1"); netlink_device_change(&nlmsg, sock, "hsr_slave_0", true, 0, 0, 0, NULL); netlink_device_change(&nlmsg, sock, "hsr_slave_1", true, 0, 0, 0, NULL); netlink_add_veth(&nlmsg, sock, "veth0_virt_wifi", "veth1_virt_wifi"); netlink_add_linked(&nlmsg, sock, "virt_wifi", "virt_wifi0", "veth1_virt_wifi"); netlink_add_veth(&nlmsg, sock, "veth0_vlan", "veth1_vlan"); netlink_add_vlan(&nlmsg, sock, "vlan0", "veth0_vlan", 0, htons(ETH_P_8021Q)); netlink_add_vlan(&nlmsg, sock, "vlan1", "veth0_vlan", 1, htons(ETH_P_8021AD)); netlink_add_macvlan(&nlmsg, sock, "macvlan0", "veth1_vlan"); netlink_add_macvlan(&nlmsg, sock, "macvlan1", "veth1_vlan"); netlink_add_ipvlan(&nlmsg, sock, "ipvlan0", "veth0_vlan", IPVLAN_MODE_L2, 0); netlink_add_ipvlan(&nlmsg, sock, "ipvlan1", "veth0_vlan", IPVLAN_MODE_L3S, IPVLAN_F_VEPA); netlink_add_veth(&nlmsg, sock, "veth0_macvtap", "veth1_macvtap"); netlink_add_linked(&nlmsg, sock, "macvtap", "macvtap0", "veth0_macvtap"); netlink_add_linked(&nlmsg, sock, "macsec", "macsec0", "veth1_macvtap"); char addr[32]; sprintf(addr, DEV_IPV4, 14 + 10); struct in_addr geneve_addr4; if (inet_pton(AF_INET, addr, &geneve_addr4) <= 0) exit(1); struct in6_addr geneve_addr6; if (inet_pton(AF_INET6, "fc00::01", &geneve_addr6) <= 0) exit(1); netlink_add_geneve(&nlmsg, sock, "geneve0", 0, &geneve_addr4, 0); netlink_add_geneve(&nlmsg, sock, "geneve1", 1, 0, &geneve_addr6); netdevsim_add((int)procid, 4); netlink_wireguard_setup(); for (i = 0; i < sizeof(devices) / (sizeof(devices[0])); i++) { char addr[32]; sprintf(addr, DEV_IPV4, i + 10); netlink_add_addr4(&nlmsg, sock, devices[i].name, addr); if (!devices[i].noipv6) { sprintf(addr, DEV_IPV6, i + 10); netlink_add_addr6(&nlmsg, sock, devices[i].name, addr); } uint64_t macaddr = DEV_MAC + ((i + 10ull) << 40); netlink_device_change(&nlmsg, sock, devices[i].name, true, 0, &macaddr, devices[i].macsize, NULL); } 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(&nlmsg, sock, dev, addr); if (!devtypes[i].noipv6) { sprintf(addr, "fe88::%02x:%02x", i, (int)procid + 1); netlink_add_addr6(&nlmsg, 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(&nlmsg, sock, dev, !devtypes[i].noup, 0, &macaddr, macsize, NULL); } 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 || errno == EBADFD) return -1; exit(1); } return rv; } static void flush_tun() { char data[1000]; while (read_tun(&data[0], sizeof(data)) != -1) { } } #define MAX_FDS 30 const char kvm_asm16_cpl3[] = "\x0f\x20\xc0\x66\x83\xc8\x01\x0f\x22\xc0\xb8\xa0" "\x00\x0f\x00\xd8\xb8\x2b\x00\x8e\xd8\x8e\xc0\x8e" "\xe0\x8e\xe8\xbc\x00\x01\xc7\x06\x00\x01\x1d\xba" "\xc7\x06\x02\x01\x23\x00\xc7\x06\x04\x01\x00\x01" "\xc7\x06\x06\x01\x2b\x00\xcb"; const char kvm_asm32_paged[] = "\x0f\x20\xc0\x0d\x00\x00\x00\x80\x0f\x22\xc0"; const char kvm_asm32_vm86[] = "\x66\xb8\xb8\x00\x0f\x00\xd8\xea\x00\x00\x00\x00\xd0\x00"; const char kvm_asm32_paged_vm86[] = "\x0f\x20\xc0\x0d\x00\x00\x00\x80\x0f\x22" "\xc0\x66\xb8\xb8\x00\x0f\x00\xd8\xea\x00" "\x00\x00\x00\xd0\x00"; const char kvm_asm64_enable_long[] = "\x0f\x20\xc0\x0d\x00\x00\x00\x80\x0f\x22" "\xc0\xea\xde\xc0\xad\x0b\x50\x00\x48\xc7" "\xc0\xd8\x00\x00\x00\x0f\x00\xd8"; const char kvm_asm64_init_vm[] = "\x0f\x20\xc0\x0d\x00\x00\x00\x80\x0f\x22\xc0\xea\xde\xc0\xad\x0b\x50\x00" "\x48\xc7\xc0\xd8\x00\x00\x00\x0f\x00\xd8\x48\xc7\xc1\x3a\x00\x00\x00\x0f" "\x32\x48\x83\xc8\x05\x0f\x30\x0f\x20\xe0\x48\x0d\x00\x20\x00\x00\x0f\x22" "\xe0\x48\xc7\xc1\x80\x04\x00\x00\x0f\x32\x48\xc7\xc2\x00\x60\x00\x00\x89" "\x02\x48\xc7\xc2\x00\x70\x00\x00\x89\x02\x48\xc7\xc0\x00\x5f\x00\x00\xf3" "\x0f\xc7\x30\x48\xc7\xc0\x08\x5f\x00\x00\x66\x0f\xc7\x30\x0f\xc7\x30\x48" "\xc7\xc1\x81\x04\x00\x00\x0f\x32\x48\x83\xc8\x3f\x48\x21\xd0\x48\xc7\xc2" "\x00\x40\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x02\x40\x00\x00\x48\xb8\x84\x9e" "\x99\xf3\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x1e\x40\x00\x00\x48\xc7" "\xc0\x81\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc1\x83\x04\x00\x00\x0f\x32\x48" "\x0d\xff\x6f\x03\x00\x48\x21\xd0\x48\xc7\xc2\x0c\x40\x00\x00\x0f\x79\xd0" "\x48\xc7\xc1\x84\x04\x00\x00\x0f\x32\x48\x0d\xff\x17\x00\x00\x48\x21\xd0" "\x48\xc7\xc2\x12\x40\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x04\x2c\x00\x00\x48" "\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x00\x28\x00\x00\x48\xc7" "\xc0\xff\xff\xff\xff\x0f\x79\xd0\x48\xc7\xc2\x02\x0c\x00\x00\x48\xc7\xc0" "\x50\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc0\x58\x00\x00\x00\x48\xc7\xc2\x00" "\x0c\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x04\x0c\x00\x00\x0f\x79\xd0\x48\xc7" "\xc2\x06\x0c\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x08\x0c\x00\x00\x0f\x79\xd0" "\x48\xc7\xc2\x0a\x0c\x00\x00\x0f\x79\xd0\x48\xc7\xc0\xd8\x00\x00\x00\x48" "\xc7\xc2\x0c\x0c\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x02\x2c\x00\x00\x48\xc7" "\xc0\x00\x05\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x00\x4c\x00\x00\x48\xc7\xc0" "\x50\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x10\x6c\x00\x00\x48\xc7\xc0\x00" "\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x12\x6c\x00\x00\x48\xc7\xc0\x00\x00" "\x00\x00\x0f\x79\xd0\x0f\x20\xc0\x48\xc7\xc2\x00\x6c\x00\x00\x48\x89\xc0" "\x0f\x79\xd0\x0f\x20\xd8\x48\xc7\xc2\x02\x6c\x00\x00\x48\x89\xc0\x0f\x79" "\xd0\x0f\x20\xe0\x48\xc7\xc2\x04\x6c\x00\x00\x48\x89\xc0\x0f\x79\xd0\x48" "\xc7\xc2\x06\x6c\x00\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7" "\xc2\x08\x6c\x00\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2" "\x0a\x6c\x00\x00\x48\xc7\xc0\x00\x3a\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x0c" "\x6c\x00\x00\x48\xc7\xc0\x00\x10\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x0e\x6c" "\x00\x00\x48\xc7\xc0\x00\x38\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x14\x6c\x00" "\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x16\x6c\x00\x00" "\x48\x8b\x04\x25\x10\x5f\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x00\x00\x00\x00" "\x48\xc7\xc0\x01\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x02\x00\x00\x00\x48" "\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x00\x20\x00\x00\x48\xc7" "\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x02\x20\x00\x00\x48\xc7\xc0" "\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x04\x20\x00\x00\x48\xc7\xc0\x00" "\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x06\x20\x00\x00\x48\xc7\xc0\x00\x00" "\x00\x00\x0f\x79\xd0\x48\xc7\xc1\x77\x02\x00\x00\x0f\x32\x48\xc1\xe2\x20" "\x48\x09\xd0\x48\xc7\xc2\x00\x2c\x00\x00\x48\x89\xc0\x0f\x79\xd0\x48\xc7" "\xc2\x04\x40\x00\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2" "\x0a\x40\x00\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x0e" "\x40\x00\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x10\x40" "\x00\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x16\x40\x00" "\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x14\x40\x00\x00" "\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x00\x60\x00\x00\x48" "\xc7\xc0\xff\xff\xff\xff\x0f\x79\xd0\x48\xc7\xc2\x02\x60\x00\x00\x48\xc7" "\xc0\xff\xff\xff\xff\x0f\x79\xd0\x48\xc7\xc2\x1c\x20\x00\x00\x48\xc7\xc0" "\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x1e\x20\x00\x00\x48\xc7\xc0\x00" "\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x20\x20\x00\x00\x48\xc7\xc0\x00\x00" "\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x22\x20\x00\x00\x48\xc7\xc0\x00\x00\x00" "\x00\x0f\x79\xd0\x48\xc7\xc2\x00\x08\x00\x00\x48\xc7\xc0\x58\x00\x00\x00" "\x0f\x79\xd0\x48\xc7\xc2\x02\x08\x00\x00\x48\xc7\xc0\x50\x00\x00\x00\x0f" "\x79\xd0\x48\xc7\xc2\x04\x08\x00\x00\x48\xc7\xc0\x58\x00\x00\x00\x0f\x79" "\xd0\x48\xc7\xc2\x06\x08\x00\x00\x48\xc7\xc0\x58\x00\x00\x00\x0f\x79\xd0" "\x48\xc7\xc2\x08\x08\x00\x00\x48\xc7\xc0\x58\x00\x00\x00\x0f\x79\xd0\x48" "\xc7\xc2\x0a\x08\x00\x00\x48\xc7\xc0\x58\x00\x00\x00\x0f\x79\xd0\x48\xc7" "\xc2\x0c\x08\x00\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2" "\x0e\x08\x00\x00\x48\xc7\xc0\xd8\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x12" "\x68\x00\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x14\x68" "\x00\x00\x48\xc7\xc0\x00\x3a\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x16\x68\x00" "\x00\x48\xc7\xc0\x00\x10\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x18\x68\x00\x00" "\x48\xc7\xc0\x00\x38\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x00\x48\x00\x00\x48" "\xc7\xc0\xff\xff\x0f\x00\x0f\x79\xd0\x48\xc7\xc2\x02\x48\x00\x00\x48\xc7" "\xc0\xff\xff\x0f\x00\x0f\x79\xd0\x48\xc7\xc2\x04\x48\x00\x00\x48\xc7\xc0" "\xff\xff\x0f\x00\x0f\x79\xd0\x48\xc7\xc2\x06\x48\x00\x00\x48\xc7\xc0\xff" "\xff\x0f\x00\x0f\x79\xd0\x48\xc7\xc2\x08\x48\x00\x00\x48\xc7\xc0\xff\xff" "\x0f\x00\x0f\x79\xd0\x48\xc7\xc2\x0a\x48\x00\x00\x48\xc7\xc0\xff\xff\x0f" "\x00\x0f\x79\xd0\x48\xc7\xc2\x0c\x48\x00\x00\x48\xc7\xc0\x00\x00\x00\x00" "\x0f\x79\xd0\x48\xc7\xc2\x0e\x48\x00\x00\x48\xc7\xc0\xff\x1f\x00\x00\x0f" "\x79\xd0\x48\xc7\xc2\x10\x48\x00\x00\x48\xc7\xc0\xff\x1f\x00\x00\x0f\x79" "\xd0\x48\xc7\xc2\x12\x48\x00\x00\x48\xc7\xc0\xff\x1f\x00\x00\x0f\x79\xd0" "\x48\xc7\xc2\x14\x48\x00\x00\x48\xc7\xc0\x93\x40\x00\x00\x0f\x79\xd0\x48" "\xc7\xc2\x16\x48\x00\x00\x48\xc7\xc0\x9b\x20\x00\x00\x0f\x79\xd0\x48\xc7" "\xc2\x18\x48\x00\x00\x48\xc7\xc0\x93\x40\x00\x00\x0f\x79\xd0\x48\xc7\xc2" "\x1a\x48\x00\x00\x48\xc7\xc0\x93\x40\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x1c" "\x48\x00\x00\x48\xc7\xc0\x93\x40\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x1e\x48" "\x00\x00\x48\xc7\xc0\x93\x40\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x20\x48\x00" "\x00\x48\xc7\xc0\x82\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x22\x48\x00\x00" "\x48\xc7\xc0\x8b\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x1c\x68\x00\x00\x48" "\xc7\xc0\x00\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x1e\x68\x00\x00\x48\xc7" "\xc0\x00\x91\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x20\x68\x00\x00\x48\xc7\xc0" "\x02\x00\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x06\x28\x00\x00\x48\xc7\xc0\x00" "\x05\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x0a\x28\x00\x00\x48\xc7\xc0\x00\x00" "\x00\x00\x0f\x79\xd0\x48\xc7\xc2\x0c\x28\x00\x00\x48\xc7\xc0\x00\x00\x00" "\x00\x0f\x79\xd0\x48\xc7\xc2\x0e\x28\x00\x00\x48\xc7\xc0\x00\x00\x00\x00" "\x0f\x79\xd0\x48\xc7\xc2\x10\x28\x00\x00\x48\xc7\xc0\x00\x00\x00\x00\x0f" "\x79\xd0\x0f\x20\xc0\x48\xc7\xc2\x00\x68\x00\x00\x48\x89\xc0\x0f\x79\xd0" "\x0f\x20\xd8\x48\xc7\xc2\x02\x68\x00\x00\x48\x89\xc0\x0f\x79\xd0\x0f\x20" "\xe0\x48\xc7\xc2\x04\x68\x00\x00\x48\x89\xc0\x0f\x79\xd0\x48\xc7\xc0\x18" "\x5f\x00\x00\x48\x8b\x10\x48\xc7\xc0\x20\x5f\x00\x00\x48\x8b\x08\x48\x31" "\xc0\x0f\x78\xd0\x48\x31\xc8\x0f\x79\xd0\x0f\x01\xc2\x48\xc7\xc2\x00\x44" "\x00\x00\x0f\x78\xd0\xf4"; const char kvm_asm64_vm_exit[] = "\x48\xc7\xc3\x00\x44\x00\x00\x0f\x78\xda\x48" "\xc7\xc3\x02\x44\x00\x00\x0f\x78\xd9\x48\xc7" "\xc0\x00\x64\x00\x00\x0f\x78\xc0\x48\xc7\xc3" "\x1e\x68\x00\x00\x0f\x78\xdb\xf4"; const char kvm_asm64_cpl3[] = "\x0f\x20\xc0\x0d\x00\x00\x00\x80\x0f\x22\xc0\xea\xde\xc0\xad\x0b\x50\x00" "\x48\xc7\xc0\xd8\x00\x00\x00\x0f\x00\xd8\x48\xc7\xc0\x6b\x00\x00\x00\x8e" "\xd8\x8e\xc0\x8e\xe0\x8e\xe8\x48\xc7\xc4\x80\x0f\x00\x00\x48\xc7\x04\x24" "\x1d\xba\x00\x00\x48\xc7\x44\x24\x04\x63\x00\x00\x00\x48\xc7\x44\x24\x08" "\x80\x0f\x00\x00\x48\xc7\x44\x24\x0c\x6b\x00\x00\x00\xcb"; #define ADDR_TEXT 0x0000 #define ADDR_GDT 0x1000 #define ADDR_LDT 0x1800 #define ADDR_PML4 0x2000 #define ADDR_PDP 0x3000 #define ADDR_PD 0x4000 #define ADDR_STACK0 0x0f80 #define ADDR_VAR_HLT 0x2800 #define ADDR_VAR_SYSRET 0x2808 #define ADDR_VAR_SYSEXIT 0x2810 #define ADDR_VAR_IDT 0x3800 #define ADDR_VAR_TSS64 0x3a00 #define ADDR_VAR_TSS64_CPL3 0x3c00 #define ADDR_VAR_TSS16 0x3d00 #define ADDR_VAR_TSS16_2 0x3e00 #define ADDR_VAR_TSS16_CPL3 0x3f00 #define ADDR_VAR_TSS32 0x4800 #define ADDR_VAR_TSS32_2 0x4a00 #define ADDR_VAR_TSS32_CPL3 0x4c00 #define ADDR_VAR_TSS32_VM86 0x4e00 #define ADDR_VAR_VMXON_PTR 0x5f00 #define ADDR_VAR_VMCS_PTR 0x5f08 #define ADDR_VAR_VMEXIT_PTR 0x5f10 #define ADDR_VAR_VMWRITE_FLD 0x5f18 #define ADDR_VAR_VMWRITE_VAL 0x5f20 #define ADDR_VAR_VMXON 0x6000 #define ADDR_VAR_VMCS 0x7000 #define ADDR_VAR_VMEXIT_CODE 0x9000 #define ADDR_VAR_USER_CODE 0x9100 #define ADDR_VAR_USER_CODE2 0x9120 #define SEL_LDT (1 << 3) #define SEL_CS16 (2 << 3) #define SEL_DS16 (3 << 3) #define SEL_CS16_CPL3 ((4 << 3) + 3) #define SEL_DS16_CPL3 ((5 << 3) + 3) #define SEL_CS32 (6 << 3) #define SEL_DS32 (7 << 3) #define SEL_CS32_CPL3 ((8 << 3) + 3) #define SEL_DS32_CPL3 ((9 << 3) + 3) #define SEL_CS64 (10 << 3) #define SEL_DS64 (11 << 3) #define SEL_CS64_CPL3 ((12 << 3) + 3) #define SEL_DS64_CPL3 ((13 << 3) + 3) #define SEL_CGATE16 (14 << 3) #define SEL_TGATE16 (15 << 3) #define SEL_CGATE32 (16 << 3) #define SEL_TGATE32 (17 << 3) #define SEL_CGATE64 (18 << 3) #define SEL_CGATE64_HI (19 << 3) #define SEL_TSS16 (20 << 3) #define SEL_TSS16_2 (21 << 3) #define SEL_TSS16_CPL3 ((22 << 3) + 3) #define SEL_TSS32 (23 << 3) #define SEL_TSS32_2 (24 << 3) #define SEL_TSS32_CPL3 ((25 << 3) + 3) #define SEL_TSS32_VM86 (26 << 3) #define SEL_TSS64 (27 << 3) #define SEL_TSS64_HI (28 << 3) #define SEL_TSS64_CPL3 ((29 << 3) + 3) #define SEL_TSS64_CPL3_HI (30 << 3) #define MSR_IA32_FEATURE_CONTROL 0x3a #define MSR_IA32_VMX_BASIC 0x480 #define MSR_IA32_SMBASE 0x9e #define MSR_IA32_SYSENTER_CS 0x174 #define MSR_IA32_SYSENTER_ESP 0x175 #define MSR_IA32_SYSENTER_EIP 0x176 #define MSR_IA32_STAR 0xC0000081 #define MSR_IA32_LSTAR 0xC0000082 #define MSR_IA32_VMX_PROCBASED_CTLS2 0x48B #define NEXT_INSN $0xbadc0de #define PREFIX_SIZE 0xba1d #define KVM_SMI _IO(KVMIO, 0xb7) #define CR0_PE 1 #define CR0_MP (1 << 1) #define CR0_EM (1 << 2) #define CR0_TS (1 << 3) #define CR0_ET (1 << 4) #define CR0_NE (1 << 5) #define CR0_WP (1 << 16) #define CR0_AM (1 << 18) #define CR0_NW (1 << 29) #define CR0_CD (1 << 30) #define CR0_PG (1 << 31) #define CR4_VME 1 #define CR4_PVI (1 << 1) #define CR4_TSD (1 << 2) #define CR4_DE (1 << 3) #define CR4_PSE (1 << 4) #define CR4_PAE (1 << 5) #define CR4_MCE (1 << 6) #define CR4_PGE (1 << 7) #define CR4_PCE (1 << 8) #define CR4_OSFXSR (1 << 8) #define CR4_OSXMMEXCPT (1 << 10) #define CR4_UMIP (1 << 11) #define CR4_VMXE (1 << 13) #define CR4_SMXE (1 << 14) #define CR4_FSGSBASE (1 << 16) #define CR4_PCIDE (1 << 17) #define CR4_OSXSAVE (1 << 18) #define CR4_SMEP (1 << 20) #define CR4_SMAP (1 << 21) #define CR4_PKE (1 << 22) #define EFER_SCE 1 #define EFER_LME (1 << 8) #define EFER_LMA (1 << 10) #define EFER_NXE (1 << 11) #define EFER_SVME (1 << 12) #define EFER_LMSLE (1 << 13) #define EFER_FFXSR (1 << 14) #define EFER_TCE (1 << 15) #define PDE32_PRESENT 1 #define PDE32_RW (1 << 1) #define PDE32_USER (1 << 2) #define PDE32_PS (1 << 7) #define PDE64_PRESENT 1 #define PDE64_RW (1 << 1) #define PDE64_USER (1 << 2) #define PDE64_ACCESSED (1 << 5) #define PDE64_DIRTY (1 << 6) #define PDE64_PS (1 << 7) #define PDE64_G (1 << 8) struct tss16 { uint16_t prev; uint16_t sp0; uint16_t ss0; uint16_t sp1; uint16_t ss1; uint16_t sp2; uint16_t ss2; uint16_t ip; uint16_t flags; uint16_t ax; uint16_t cx; uint16_t dx; uint16_t bx; uint16_t sp; uint16_t bp; uint16_t si; uint16_t di; uint16_t es; uint16_t cs; uint16_t ss; uint16_t ds; uint16_t ldt; } __attribute__((packed)); struct tss32 { uint16_t prev, prevh; uint32_t sp0; uint16_t ss0, ss0h; uint32_t sp1; uint16_t ss1, ss1h; uint32_t sp2; uint16_t ss2, ss2h; uint32_t cr3; uint32_t ip; uint32_t flags; uint32_t ax; uint32_t cx; uint32_t dx; uint32_t bx; uint32_t sp; uint32_t bp; uint32_t si; uint32_t di; uint16_t es, esh; uint16_t cs, csh; uint16_t ss, ssh; uint16_t ds, dsh; uint16_t fs, fsh; uint16_t gs, gsh; uint16_t ldt, ldth; uint16_t trace; uint16_t io_bitmap; } __attribute__((packed)); struct tss64 { uint32_t reserved0; uint64_t rsp[3]; uint64_t reserved1; uint64_t ist[7]; uint64_t reserved2; uint32_t reserved3; uint32_t io_bitmap; } __attribute__((packed)); static void fill_segment_descriptor(uint64_t* dt, uint64_t* lt, struct kvm_segment* seg) { uint16_t index = seg->selector >> 3; uint64_t limit = seg->g ? seg->limit >> 12 : seg->limit; uint64_t sd = (limit & 0xffff) | (seg->base & 0xffffff) << 16 | (uint64_t)seg->type << 40 | (uint64_t)seg->s << 44 | (uint64_t)seg->dpl << 45 | (uint64_t)seg->present << 47 | (limit & 0xf0000ULL) << 48 | (uint64_t)seg->avl << 52 | (uint64_t)seg->l << 53 | (uint64_t)seg->db << 54 | (uint64_t)seg->g << 55 | (seg->base & 0xff000000ULL) << 56; dt[index] = sd; lt[index] = sd; } static void fill_segment_descriptor_dword(uint64_t* dt, uint64_t* lt, struct kvm_segment* seg) { fill_segment_descriptor(dt, lt, seg); uint16_t index = seg->selector >> 3; dt[index + 1] = 0; lt[index + 1] = 0; } static void setup_syscall_msrs(int cpufd, uint16_t sel_cs, uint16_t sel_cs_cpl3) { char buf[sizeof(struct kvm_msrs) + 5 * sizeof(struct kvm_msr_entry)]; memset(buf, 0, sizeof(buf)); struct kvm_msrs* msrs = (struct kvm_msrs*)buf; struct kvm_msr_entry* entries = msrs->entries; msrs->nmsrs = 5; entries[0].index = MSR_IA32_SYSENTER_CS; entries[0].data = sel_cs; entries[1].index = MSR_IA32_SYSENTER_ESP; entries[1].data = ADDR_STACK0; entries[2].index = MSR_IA32_SYSENTER_EIP; entries[2].data = ADDR_VAR_SYSEXIT; entries[3].index = MSR_IA32_STAR; entries[3].data = ((uint64_t)sel_cs << 32) | ((uint64_t)sel_cs_cpl3 << 48); entries[4].index = MSR_IA32_LSTAR; entries[4].data = ADDR_VAR_SYSRET; ioctl(cpufd, KVM_SET_MSRS, msrs); } static void setup_32bit_idt(struct kvm_sregs* sregs, char* host_mem, uintptr_t guest_mem) { sregs->idt.base = guest_mem + ADDR_VAR_IDT; sregs->idt.limit = 0x1ff; uint64_t* idt = (uint64_t*)(host_mem + sregs->idt.base); for (int i = 0; i < 32; i++) { struct kvm_segment gate; gate.selector = i << 3; switch (i % 6) { case 0: gate.type = 6; gate.base = SEL_CS16; break; case 1: gate.type = 7; gate.base = SEL_CS16; break; case 2: gate.type = 3; gate.base = SEL_TGATE16; break; case 3: gate.type = 14; gate.base = SEL_CS32; break; case 4: gate.type = 15; gate.base = SEL_CS32; break; case 5: gate.type = 11; gate.base = SEL_TGATE32; break; } gate.limit = guest_mem + ADDR_VAR_USER_CODE2; gate.present = 1; gate.dpl = 0; gate.s = 0; gate.g = 0; gate.db = 0; gate.l = 0; gate.avl = 0; fill_segment_descriptor(idt, idt, &gate); } } static void setup_64bit_idt(struct kvm_sregs* sregs, char* host_mem, uintptr_t guest_mem) { sregs->idt.base = guest_mem + ADDR_VAR_IDT; sregs->idt.limit = 0x1ff; uint64_t* idt = (uint64_t*)(host_mem + sregs->idt.base); for (int i = 0; i < 32; i++) { struct kvm_segment gate; gate.selector = (i * 2) << 3; gate.type = (i & 1) ? 14 : 15; gate.base = SEL_CS64; gate.limit = guest_mem + ADDR_VAR_USER_CODE2; gate.present = 1; gate.dpl = 0; gate.s = 0; gate.g = 0; gate.db = 0; gate.l = 0; gate.avl = 0; fill_segment_descriptor_dword(idt, idt, &gate); } } struct kvm_text { uintptr_t typ; const void* text; uintptr_t size; }; struct kvm_opt { uint64_t typ; uint64_t val; }; #define KVM_SETUP_PAGING (1 << 0) #define KVM_SETUP_PAE (1 << 1) #define KVM_SETUP_PROTECTED (1 << 2) #define KVM_SETUP_CPL3 (1 << 3) #define KVM_SETUP_VIRT86 (1 << 4) #define KVM_SETUP_SMM (1 << 5) #define KVM_SETUP_VM (1 << 6) static long syz_kvm_setup_cpu(volatile long a0, volatile long a1, volatile long a2, volatile long a3, volatile long a4, volatile long a5, volatile long a6, volatile long a7) { const int vmfd = a0; const int cpufd = a1; char* const host_mem = (char*)a2; const struct kvm_text* const text_array_ptr = (struct kvm_text*)a3; const uintptr_t text_count = a4; const uintptr_t flags = a5; const struct kvm_opt* const opt_array_ptr = (struct kvm_opt*)a6; uintptr_t opt_count = a7; const uintptr_t page_size = 4 << 10; const uintptr_t ioapic_page = 10; const uintptr_t guest_mem_size = 24 * page_size; const uintptr_t guest_mem = 0; (void)text_count; int text_type = text_array_ptr[0].typ; const void* text = text_array_ptr[0].text; uintptr_t text_size = text_array_ptr[0].size; for (uintptr_t i = 0; i < guest_mem_size / page_size; i++) { struct kvm_userspace_memory_region memreg; memreg.slot = i; memreg.flags = 0; memreg.guest_phys_addr = guest_mem + i * page_size; if (i == ioapic_page) memreg.guest_phys_addr = 0xfec00000; memreg.memory_size = page_size; memreg.userspace_addr = (uintptr_t)host_mem + i * page_size; ioctl(vmfd, KVM_SET_USER_MEMORY_REGION, &memreg); } struct kvm_userspace_memory_region memreg; memreg.slot = 1 + (1 << 16); memreg.flags = 0; memreg.guest_phys_addr = 0x30000; memreg.memory_size = 64 << 10; memreg.userspace_addr = (uintptr_t)host_mem; ioctl(vmfd, KVM_SET_USER_MEMORY_REGION, &memreg); struct kvm_sregs sregs; if (ioctl(cpufd, KVM_GET_SREGS, &sregs)) return -1; struct kvm_regs regs; memset(®s, 0, sizeof(regs)); regs.rip = guest_mem + ADDR_TEXT; regs.rsp = ADDR_STACK0; sregs.gdt.base = guest_mem + ADDR_GDT; sregs.gdt.limit = 256 * sizeof(uint64_t) - 1; uint64_t* gdt = (uint64_t*)(host_mem + sregs.gdt.base); struct kvm_segment seg_ldt; seg_ldt.selector = SEL_LDT; seg_ldt.type = 2; seg_ldt.base = guest_mem + ADDR_LDT; seg_ldt.limit = 256 * sizeof(uint64_t) - 1; seg_ldt.present = 1; seg_ldt.dpl = 0; seg_ldt.s = 0; seg_ldt.g = 0; seg_ldt.db = 1; seg_ldt.l = 0; sregs.ldt = seg_ldt; uint64_t* ldt = (uint64_t*)(host_mem + sregs.ldt.base); struct kvm_segment seg_cs16; seg_cs16.selector = SEL_CS16; seg_cs16.type = 11; seg_cs16.base = 0; seg_cs16.limit = 0xfffff; seg_cs16.present = 1; seg_cs16.dpl = 0; seg_cs16.s = 1; seg_cs16.g = 0; seg_cs16.db = 0; seg_cs16.l = 0; struct kvm_segment seg_ds16 = seg_cs16; seg_ds16.selector = SEL_DS16; seg_ds16.type = 3; struct kvm_segment seg_cs16_cpl3 = seg_cs16; seg_cs16_cpl3.selector = SEL_CS16_CPL3; seg_cs16_cpl3.dpl = 3; struct kvm_segment seg_ds16_cpl3 = seg_ds16; seg_ds16_cpl3.selector = SEL_DS16_CPL3; seg_ds16_cpl3.dpl = 3; struct kvm_segment seg_cs32 = seg_cs16; seg_cs32.selector = SEL_CS32; seg_cs32.db = 1; struct kvm_segment seg_ds32 = seg_ds16; seg_ds32.selector = SEL_DS32; seg_ds32.db = 1; struct kvm_segment seg_cs32_cpl3 = seg_cs32; seg_cs32_cpl3.selector = SEL_CS32_CPL3; seg_cs32_cpl3.dpl = 3; struct kvm_segment seg_ds32_cpl3 = seg_ds32; seg_ds32_cpl3.selector = SEL_DS32_CPL3; seg_ds32_cpl3.dpl = 3; struct kvm_segment seg_cs64 = seg_cs16; seg_cs64.selector = SEL_CS64; seg_cs64.l = 1; struct kvm_segment seg_ds64 = seg_ds32; seg_ds64.selector = SEL_DS64; struct kvm_segment seg_cs64_cpl3 = seg_cs64; seg_cs64_cpl3.selector = SEL_CS64_CPL3; seg_cs64_cpl3.dpl = 3; struct kvm_segment seg_ds64_cpl3 = seg_ds64; seg_ds64_cpl3.selector = SEL_DS64_CPL3; seg_ds64_cpl3.dpl = 3; struct kvm_segment seg_tss32; seg_tss32.selector = SEL_TSS32; seg_tss32.type = 9; seg_tss32.base = ADDR_VAR_TSS32; seg_tss32.limit = 0x1ff; seg_tss32.present = 1; seg_tss32.dpl = 0; seg_tss32.s = 0; seg_tss32.g = 0; seg_tss32.db = 0; seg_tss32.l = 0; struct kvm_segment seg_tss32_2 = seg_tss32; seg_tss32_2.selector = SEL_TSS32_2; seg_tss32_2.base = ADDR_VAR_TSS32_2; struct kvm_segment seg_tss32_cpl3 = seg_tss32; seg_tss32_cpl3.selector = SEL_TSS32_CPL3; seg_tss32_cpl3.base = ADDR_VAR_TSS32_CPL3; struct kvm_segment seg_tss32_vm86 = seg_tss32; seg_tss32_vm86.selector = SEL_TSS32_VM86; seg_tss32_vm86.base = ADDR_VAR_TSS32_VM86; struct kvm_segment seg_tss16 = seg_tss32; seg_tss16.selector = SEL_TSS16; seg_tss16.base = ADDR_VAR_TSS16; seg_tss16.limit = 0xff; seg_tss16.type = 1; struct kvm_segment seg_tss16_2 = seg_tss16; seg_tss16_2.selector = SEL_TSS16_2; seg_tss16_2.base = ADDR_VAR_TSS16_2; seg_tss16_2.dpl = 0; struct kvm_segment seg_tss16_cpl3 = seg_tss16; seg_tss16_cpl3.selector = SEL_TSS16_CPL3; seg_tss16_cpl3.base = ADDR_VAR_TSS16_CPL3; seg_tss16_cpl3.dpl = 3; struct kvm_segment seg_tss64 = seg_tss32; seg_tss64.selector = SEL_TSS64; seg_tss64.base = ADDR_VAR_TSS64; seg_tss64.limit = 0x1ff; struct kvm_segment seg_tss64_cpl3 = seg_tss64; seg_tss64_cpl3.selector = SEL_TSS64_CPL3; seg_tss64_cpl3.base = ADDR_VAR_TSS64_CPL3; seg_tss64_cpl3.dpl = 3; struct kvm_segment seg_cgate16; seg_cgate16.selector = SEL_CGATE16; seg_cgate16.type = 4; seg_cgate16.base = SEL_CS16 | (2 << 16); seg_cgate16.limit = ADDR_VAR_USER_CODE2; seg_cgate16.present = 1; seg_cgate16.dpl = 0; seg_cgate16.s = 0; seg_cgate16.g = 0; seg_cgate16.db = 0; seg_cgate16.l = 0; seg_cgate16.avl = 0; struct kvm_segment seg_tgate16 = seg_cgate16; seg_tgate16.selector = SEL_TGATE16; seg_tgate16.type = 3; seg_cgate16.base = SEL_TSS16_2; seg_tgate16.limit = 0; struct kvm_segment seg_cgate32 = seg_cgate16; seg_cgate32.selector = SEL_CGATE32; seg_cgate32.type = 12; seg_cgate32.base = SEL_CS32 | (2 << 16); struct kvm_segment seg_tgate32 = seg_cgate32; seg_tgate32.selector = SEL_TGATE32; seg_tgate32.type = 11; seg_tgate32.base = SEL_TSS32_2; seg_tgate32.limit = 0; struct kvm_segment seg_cgate64 = seg_cgate16; seg_cgate64.selector = SEL_CGATE64; seg_cgate64.type = 12; seg_cgate64.base = SEL_CS64; int kvmfd = open("/dev/kvm", O_RDWR); char buf[sizeof(struct kvm_cpuid2) + 128 * sizeof(struct kvm_cpuid_entry2)]; memset(buf, 0, sizeof(buf)); struct kvm_cpuid2* cpuid = (struct kvm_cpuid2*)buf; cpuid->nent = 128; ioctl(kvmfd, KVM_GET_SUPPORTED_CPUID, cpuid); ioctl(cpufd, KVM_SET_CPUID2, cpuid); close(kvmfd); const char* text_prefix = 0; int text_prefix_size = 0; char* host_text = host_mem + ADDR_TEXT; if (text_type == 8) { if (flags & KVM_SETUP_SMM) { if (flags & KVM_SETUP_PROTECTED) { sregs.cs = seg_cs16; sregs.ds = sregs.es = sregs.fs = sregs.gs = sregs.ss = seg_ds16; sregs.cr0 |= CR0_PE; } else { sregs.cs.selector = 0; sregs.cs.base = 0; } *(host_mem + ADDR_TEXT) = 0xf4; host_text = host_mem + 0x8000; ioctl(cpufd, KVM_SMI, 0); } else if (flags & KVM_SETUP_VIRT86) { sregs.cs = seg_cs32; sregs.ds = sregs.es = sregs.fs = sregs.gs = sregs.ss = seg_ds32; sregs.cr0 |= CR0_PE; sregs.efer |= EFER_SCE; setup_syscall_msrs(cpufd, SEL_CS32, SEL_CS32_CPL3); setup_32bit_idt(&sregs, host_mem, guest_mem); if (flags & KVM_SETUP_PAGING) { uint64_t pd_addr = guest_mem + ADDR_PD; uint64_t* pd = (uint64_t*)(host_mem + ADDR_PD); pd[0] = PDE32_PRESENT | PDE32_RW | PDE32_USER | PDE32_PS; sregs.cr3 = pd_addr; sregs.cr4 |= CR4_PSE; text_prefix = kvm_asm32_paged_vm86; text_prefix_size = sizeof(kvm_asm32_paged_vm86) - 1; } else { text_prefix = kvm_asm32_vm86; text_prefix_size = sizeof(kvm_asm32_vm86) - 1; } } else { sregs.cs.selector = 0; sregs.cs.base = 0; } } else if (text_type == 16) { if (flags & KVM_SETUP_CPL3) { sregs.cs = seg_cs16; sregs.ds = sregs.es = sregs.fs = sregs.gs = sregs.ss = seg_ds16; text_prefix = kvm_asm16_cpl3; text_prefix_size = sizeof(kvm_asm16_cpl3) - 1; } else { sregs.cr0 |= CR0_PE; sregs.cs = seg_cs16; sregs.ds = sregs.es = sregs.fs = sregs.gs = sregs.ss = seg_ds16; } } else if (text_type == 32) { sregs.cr0 |= CR0_PE; sregs.efer |= EFER_SCE; setup_syscall_msrs(cpufd, SEL_CS32, SEL_CS32_CPL3); setup_32bit_idt(&sregs, host_mem, guest_mem); if (flags & KVM_SETUP_SMM) { sregs.cs = seg_cs32; sregs.ds = sregs.es = sregs.fs = sregs.gs = sregs.ss = seg_ds32; *(host_mem + ADDR_TEXT) = 0xf4; host_text = host_mem + 0x8000; ioctl(cpufd, KVM_SMI, 0); } else if (flags & KVM_SETUP_PAGING) { sregs.cs = seg_cs32; sregs.ds = sregs.es = sregs.fs = sregs.gs = sregs.ss = seg_ds32; uint64_t pd_addr = guest_mem + ADDR_PD; uint64_t* pd = (uint64_t*)(host_mem + ADDR_PD); pd[0] = PDE32_PRESENT | PDE32_RW | PDE32_USER | PDE32_PS; sregs.cr3 = pd_addr; sregs.cr4 |= CR4_PSE; text_prefix = kvm_asm32_paged; text_prefix_size = sizeof(kvm_asm32_paged) - 1; } else if (flags & KVM_SETUP_CPL3) { sregs.cs = seg_cs32_cpl3; sregs.ds = sregs.es = sregs.fs = sregs.gs = sregs.ss = seg_ds32_cpl3; } else { sregs.cs = seg_cs32; sregs.ds = sregs.es = sregs.fs = sregs.gs = sregs.ss = seg_ds32; } } else { sregs.efer |= EFER_LME | EFER_SCE; sregs.cr0 |= CR0_PE; setup_syscall_msrs(cpufd, SEL_CS64, SEL_CS64_CPL3); setup_64bit_idt(&sregs, host_mem, guest_mem); sregs.cs = seg_cs32; sregs.ds = sregs.es = sregs.fs = sregs.gs = sregs.ss = seg_ds32; uint64_t pml4_addr = guest_mem + ADDR_PML4; uint64_t* pml4 = (uint64_t*)(host_mem + ADDR_PML4); uint64_t pdpt_addr = guest_mem + ADDR_PDP; uint64_t* pdpt = (uint64_t*)(host_mem + ADDR_PDP); uint64_t pd_addr = guest_mem + ADDR_PD; uint64_t* pd = (uint64_t*)(host_mem + ADDR_PD); pml4[0] = PDE64_PRESENT | PDE64_RW | PDE64_USER | pdpt_addr; pdpt[0] = PDE64_PRESENT | PDE64_RW | PDE64_USER | pd_addr; pd[0] = PDE64_PRESENT | PDE64_RW | PDE64_USER | PDE64_PS; sregs.cr3 = pml4_addr; sregs.cr4 |= CR4_PAE; if (flags & KVM_SETUP_VM) { sregs.cr0 |= CR0_NE; *((uint64_t*)(host_mem + ADDR_VAR_VMXON_PTR)) = ADDR_VAR_VMXON; *((uint64_t*)(host_mem + ADDR_VAR_VMCS_PTR)) = ADDR_VAR_VMCS; memcpy(host_mem + ADDR_VAR_VMEXIT_CODE, kvm_asm64_vm_exit, sizeof(kvm_asm64_vm_exit) - 1); *((uint64_t*)(host_mem + ADDR_VAR_VMEXIT_PTR)) = ADDR_VAR_VMEXIT_CODE; text_prefix = kvm_asm64_init_vm; text_prefix_size = sizeof(kvm_asm64_init_vm) - 1; } else if (flags & KVM_SETUP_CPL3) { text_prefix = kvm_asm64_cpl3; text_prefix_size = sizeof(kvm_asm64_cpl3) - 1; } else { text_prefix = kvm_asm64_enable_long; text_prefix_size = sizeof(kvm_asm64_enable_long) - 1; } } struct tss16 tss16; memset(&tss16, 0, sizeof(tss16)); tss16.ss0 = tss16.ss1 = tss16.ss2 = SEL_DS16; tss16.sp0 = tss16.sp1 = tss16.sp2 = ADDR_STACK0; tss16.ip = ADDR_VAR_USER_CODE2; tss16.flags = (1 << 1); tss16.cs = SEL_CS16; tss16.es = tss16.ds = tss16.ss = SEL_DS16; tss16.ldt = SEL_LDT; struct tss16* tss16_addr = (struct tss16*)(host_mem + seg_tss16_2.base); memcpy(tss16_addr, &tss16, sizeof(tss16)); memset(&tss16, 0, sizeof(tss16)); tss16.ss0 = tss16.ss1 = tss16.ss2 = SEL_DS16; tss16.sp0 = tss16.sp1 = tss16.sp2 = ADDR_STACK0; tss16.ip = ADDR_VAR_USER_CODE2; tss16.flags = (1 << 1); tss16.cs = SEL_CS16_CPL3; tss16.es = tss16.ds = tss16.ss = SEL_DS16_CPL3; tss16.ldt = SEL_LDT; struct tss16* tss16_cpl3_addr = (struct tss16*)(host_mem + seg_tss16_cpl3.base); memcpy(tss16_cpl3_addr, &tss16, sizeof(tss16)); struct tss32 tss32; memset(&tss32, 0, sizeof(tss32)); tss32.ss0 = tss32.ss1 = tss32.ss2 = SEL_DS32; tss32.sp0 = tss32.sp1 = tss32.sp2 = ADDR_STACK0; tss32.ip = ADDR_VAR_USER_CODE; tss32.flags = (1 << 1) | (1 << 17); tss32.ldt = SEL_LDT; tss32.cr3 = sregs.cr3; tss32.io_bitmap = offsetof(struct tss32, io_bitmap); struct tss32* tss32_addr = (struct tss32*)(host_mem + seg_tss32_vm86.base); memcpy(tss32_addr, &tss32, sizeof(tss32)); memset(&tss32, 0, sizeof(tss32)); tss32.ss0 = tss32.ss1 = tss32.ss2 = SEL_DS32; tss32.sp0 = tss32.sp1 = tss32.sp2 = ADDR_STACK0; tss32.ip = ADDR_VAR_USER_CODE; tss32.flags = (1 << 1); tss32.cr3 = sregs.cr3; tss32.es = tss32.ds = tss32.ss = tss32.gs = tss32.fs = SEL_DS32; tss32.cs = SEL_CS32; tss32.ldt = SEL_LDT; tss32.cr3 = sregs.cr3; tss32.io_bitmap = offsetof(struct tss32, io_bitmap); struct tss32* tss32_cpl3_addr = (struct tss32*)(host_mem + seg_tss32_2.base); memcpy(tss32_cpl3_addr, &tss32, sizeof(tss32)); struct tss64 tss64; memset(&tss64, 0, sizeof(tss64)); tss64.rsp[0] = ADDR_STACK0; tss64.rsp[1] = ADDR_STACK0; tss64.rsp[2] = ADDR_STACK0; tss64.io_bitmap = offsetof(struct tss64, io_bitmap); struct tss64* tss64_addr = (struct tss64*)(host_mem + seg_tss64.base); memcpy(tss64_addr, &tss64, sizeof(tss64)); memset(&tss64, 0, sizeof(tss64)); tss64.rsp[0] = ADDR_STACK0; tss64.rsp[1] = ADDR_STACK0; tss64.rsp[2] = ADDR_STACK0; tss64.io_bitmap = offsetof(struct tss64, io_bitmap); struct tss64* tss64_cpl3_addr = (struct tss64*)(host_mem + seg_tss64_cpl3.base); memcpy(tss64_cpl3_addr, &tss64, sizeof(tss64)); if (text_size > 1000) text_size = 1000; if (text_prefix) { memcpy(host_text, text_prefix, text_prefix_size); void* patch = memmem(host_text, text_prefix_size, "\xde\xc0\xad\x0b", 4); if (patch) *((uint32_t*)patch) = guest_mem + ADDR_TEXT + ((char*)patch - host_text) + 6; uint16_t magic = PREFIX_SIZE; patch = memmem(host_text, text_prefix_size, &magic, sizeof(magic)); if (patch) *((uint16_t*)patch) = guest_mem + ADDR_TEXT + text_prefix_size; } memcpy((void*)(host_text + text_prefix_size), text, text_size); *(host_text + text_prefix_size + text_size) = 0xf4; memcpy(host_mem + ADDR_VAR_USER_CODE, text, text_size); *(host_mem + ADDR_VAR_USER_CODE + text_size) = 0xf4; *(host_mem + ADDR_VAR_HLT) = 0xf4; memcpy(host_mem + ADDR_VAR_SYSRET, "\x0f\x07\xf4", 3); memcpy(host_mem + ADDR_VAR_SYSEXIT, "\x0f\x35\xf4", 3); *(uint64_t*)(host_mem + ADDR_VAR_VMWRITE_FLD) = 0; *(uint64_t*)(host_mem + ADDR_VAR_VMWRITE_VAL) = 0; if (opt_count > 2) opt_count = 2; for (uintptr_t i = 0; i < opt_count; i++) { uint64_t typ = opt_array_ptr[i].typ; uint64_t val = opt_array_ptr[i].val; switch (typ % 9) { case 0: sregs.cr0 ^= val & (CR0_MP | CR0_EM | CR0_ET | CR0_NE | CR0_WP | CR0_AM | CR0_NW | CR0_CD); break; case 1: sregs.cr4 ^= val & (CR4_VME | CR4_PVI | CR4_TSD | CR4_DE | CR4_MCE | CR4_PGE | CR4_PCE | CR4_OSFXSR | CR4_OSXMMEXCPT | CR4_UMIP | CR4_VMXE | CR4_SMXE | CR4_FSGSBASE | CR4_PCIDE | CR4_OSXSAVE | CR4_SMEP | CR4_SMAP | CR4_PKE); break; case 2: sregs.efer ^= val & (EFER_SCE | EFER_NXE | EFER_SVME | EFER_LMSLE | EFER_FFXSR | EFER_TCE); break; case 3: val &= ((1 << 8) | (1 << 9) | (1 << 10) | (1 << 12) | (1 << 13) | (1 << 14) | (1 << 15) | (1 << 18) | (1 << 19) | (1 << 20) | (1 << 21)); regs.rflags ^= val; tss16_addr->flags ^= val; tss16_cpl3_addr->flags ^= val; tss32_addr->flags ^= val; tss32_cpl3_addr->flags ^= val; break; case 4: seg_cs16.type = val & 0xf; seg_cs32.type = val & 0xf; seg_cs64.type = val & 0xf; break; case 5: seg_cs16_cpl3.type = val & 0xf; seg_cs32_cpl3.type = val & 0xf; seg_cs64_cpl3.type = val & 0xf; break; case 6: seg_ds16.type = val & 0xf; seg_ds32.type = val & 0xf; seg_ds64.type = val & 0xf; break; case 7: seg_ds16_cpl3.type = val & 0xf; seg_ds32_cpl3.type = val & 0xf; seg_ds64_cpl3.type = val & 0xf; break; case 8: *(uint64_t*)(host_mem + ADDR_VAR_VMWRITE_FLD) = (val & 0xffff); *(uint64_t*)(host_mem + ADDR_VAR_VMWRITE_VAL) = (val >> 16); break; default: exit(1); } } regs.rflags |= 2; fill_segment_descriptor(gdt, ldt, &seg_ldt); fill_segment_descriptor(gdt, ldt, &seg_cs16); fill_segment_descriptor(gdt, ldt, &seg_ds16); fill_segment_descriptor(gdt, ldt, &seg_cs16_cpl3); fill_segment_descriptor(gdt, ldt, &seg_ds16_cpl3); fill_segment_descriptor(gdt, ldt, &seg_cs32); fill_segment_descriptor(gdt, ldt, &seg_ds32); fill_segment_descriptor(gdt, ldt, &seg_cs32_cpl3); fill_segment_descriptor(gdt, ldt, &seg_ds32_cpl3); fill_segment_descriptor(gdt, ldt, &seg_cs64); fill_segment_descriptor(gdt, ldt, &seg_ds64); fill_segment_descriptor(gdt, ldt, &seg_cs64_cpl3); fill_segment_descriptor(gdt, ldt, &seg_ds64_cpl3); fill_segment_descriptor(gdt, ldt, &seg_tss32); fill_segment_descriptor(gdt, ldt, &seg_tss32_2); fill_segment_descriptor(gdt, ldt, &seg_tss32_cpl3); fill_segment_descriptor(gdt, ldt, &seg_tss32_vm86); fill_segment_descriptor(gdt, ldt, &seg_tss16); fill_segment_descriptor(gdt, ldt, &seg_tss16_2); fill_segment_descriptor(gdt, ldt, &seg_tss16_cpl3); fill_segment_descriptor_dword(gdt, ldt, &seg_tss64); fill_segment_descriptor_dword(gdt, ldt, &seg_tss64_cpl3); fill_segment_descriptor(gdt, ldt, &seg_cgate16); fill_segment_descriptor(gdt, ldt, &seg_tgate16); fill_segment_descriptor(gdt, ldt, &seg_cgate32); fill_segment_descriptor(gdt, ldt, &seg_tgate32); fill_segment_descriptor_dword(gdt, ldt, &seg_cgate64); if (ioctl(cpufd, KVM_SET_SREGS, &sregs)) return -1; if (ioctl(cpufd, KVM_SET_REGS, ®s)) return -1; return 0; } 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); 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 (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(); 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); 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_test() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); write_file("/proc/self/oom_score_adj", "1000"); flush_tun(); } 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() { static struct { const char* name; const char* data; } files[] = { {"/sys/kernel/debug/x86/nmi_longest_ns", "10000000000"}, {"/proc/sys/kernel/hung_task_check_interval_secs", "20"}, {"/proc/sys/net/core/bpf_jit_enable", "1"}, {"/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/net/ipv4/ping_group_range", "0 65535"}, {"/proc/sys/kernel/keys/gc_delay", "1"}, {"/proc/sys/vm/nr_overcommit_hugepages", "4"}, {"/proc/sys/vm/oom_kill_allocating_task", "1"}, }; 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; int collide = 0; again: for (call = 0; call < 11; 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, 50); 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) { int iter = 0; for (;; iter++) { 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 < 5000) { continue; } kill_and_wait(pid, &status); break; } } } uint64_t r[2] = {0xffffffffffffffff, 0xffffffffffffffff}; void execute_call(int call) { intptr_t res = 0; switch (call) { case 0: syscall(__NR_setsockopt, -1, 6, 0x1f, 0ul, 0ul); break; case 1: NONFAILING(syz_kvm_setup_cpu(-1, -1, 0x2000b000, 0, 0, 0, 0, 0)); break; case 2: res = syscall(__NR_socket, 2ul, 2ul, 0); if (res != -1) r[0] = res; break; case 3: res = syscall(__NR_socket, 0xful, 3ul, 2); if (res != -1) r[1] = res; break; case 4: NONFAILING(*(uint64_t*)0x20000000 = 0x40000000); NONFAILING(*(uint32_t*)0x20000008 = 0); NONFAILING(*(uint64_t*)0x20000010 = 0x20000040); NONFAILING(*(uint64_t*)0x20000040 = 0x20000240); NONFAILING(memcpy((void*)0x20000240, "\x02\x07\x00\x09\x02", 5)); NONFAILING(*(uint64_t*)0x20000048 = 0x10); NONFAILING(*(uint64_t*)0x20000018 = 1); NONFAILING(*(uint64_t*)0x20000020 = 0); NONFAILING(*(uint64_t*)0x20000028 = 0); NONFAILING(*(uint32_t*)0x20000030 = 0); syscall(__NR_sendmsg, r[1], 0x20000000ul, 0ul); break; case 5: NONFAILING(*(uint16_t*)0x200001c0 = 2); NONFAILING(*(uint16_t*)0x200001c2 = htobe16(0)); NONFAILING(*(uint8_t*)0x200001c4 = 0xac); NONFAILING(*(uint8_t*)0x200001c5 = 0x14); NONFAILING(*(uint8_t*)0x200001c6 = 0x14); NONFAILING(*(uint8_t*)0x200001c7 = 0xaa); syscall(__NR_bind, r[0], 0x200001c0ul, 0x16ul); break; case 6: syscall(__NR_ioctl, -1, 0x40042408, r[0]); break; case 7: NONFAILING(*(uint16_t*)0x20000480 = 2); NONFAILING(*(uint16_t*)0x20000482 = htobe16(0)); NONFAILING(*(uint32_t*)0x20000484 = htobe32(0xe0000001)); syscall(__NR_connect, r[0], 0x20000480ul, 0x10ul); break; case 8: NONFAILING(*(uint8_t*)0x20000080 = 0); NONFAILING(*(uint8_t*)0x20000081 = 0); NONFAILING(*(uint8_t*)0x20000082 = 0); NONFAILING(*(uint8_t*)0x20000083 = 0); NONFAILING(*(uint8_t*)0x20000084 = 0); NONFAILING(*(uint8_t*)0x20000085 = 0); NONFAILING(*(uint8_t*)0x20000086 = 0); NONFAILING(*(uint8_t*)0x20000087 = 0); NONFAILING(*(uint8_t*)0x20000088 = 0); NONFAILING(*(uint8_t*)0x20000089 = 0); NONFAILING(*(uint8_t*)0x2000008a = -1); NONFAILING(*(uint8_t*)0x2000008b = -1); NONFAILING(*(uint8_t*)0x2000008c = 0xac); NONFAILING(*(uint8_t*)0x2000008d = 0x14); NONFAILING(*(uint8_t*)0x2000008e = 0x14); NONFAILING(*(uint8_t*)0x2000008f = 0); NONFAILING(*(uint8_t*)0x20000090 = 0xfc); NONFAILING(*(uint8_t*)0x20000091 = 0); NONFAILING(*(uint8_t*)0x20000092 = 0); NONFAILING(*(uint8_t*)0x20000093 = 0); NONFAILING(*(uint8_t*)0x20000094 = 0); NONFAILING(*(uint8_t*)0x20000095 = 0); NONFAILING(*(uint8_t*)0x20000096 = 0); NONFAILING(*(uint8_t*)0x20000097 = 0); NONFAILING(*(uint8_t*)0x20000098 = 0); NONFAILING(*(uint8_t*)0x20000099 = 0); NONFAILING(*(uint8_t*)0x2000009a = 0); NONFAILING(*(uint8_t*)0x2000009b = 0); NONFAILING(*(uint8_t*)0x2000009c = 0); NONFAILING(*(uint8_t*)0x2000009d = 0); NONFAILING(*(uint8_t*)0x2000009e = 0); NONFAILING(*(uint8_t*)0x2000009f = 1); NONFAILING(*(uint16_t*)0x200000a0 = htobe16(0x4e21)); NONFAILING(*(uint16_t*)0x200000a2 = htobe16(0)); NONFAILING(*(uint16_t*)0x200000a4 = htobe16(0)); NONFAILING(*(uint16_t*)0x200000a6 = htobe16(0)); NONFAILING(*(uint16_t*)0x200000a8 = 2); NONFAILING(*(uint8_t*)0x200000aa = 0); NONFAILING(*(uint8_t*)0x200000ab = 0); NONFAILING(*(uint8_t*)0x200000ac = 0); NONFAILING(*(uint32_t*)0x200000b0 = 0); NONFAILING(*(uint32_t*)0x200000b4 = 0xee01); NONFAILING(*(uint64_t*)0x200000b8 = 0x38590000000000); NONFAILING(*(uint64_t*)0x200000c0 = 0); NONFAILING(*(uint64_t*)0x200000c8 = 0); NONFAILING(*(uint64_t*)0x200000d0 = 0); NONFAILING(*(uint64_t*)0x200000d8 = 0x200000000000000); NONFAILING(*(uint64_t*)0x200000e0 = 0); NONFAILING(*(uint64_t*)0x200000e8 = 0); NONFAILING(*(uint64_t*)0x200000f0 = 3); NONFAILING(*(uint64_t*)0x200000f8 = 0); NONFAILING(*(uint64_t*)0x20000100 = 0); NONFAILING(*(uint64_t*)0x20000108 = 0); NONFAILING(*(uint64_t*)0x20000110 = 0); NONFAILING(*(uint32_t*)0x20000118 = -1); NONFAILING(*(uint32_t*)0x2000011c = 0); NONFAILING(*(uint8_t*)0x20000120 = 1); NONFAILING(*(uint8_t*)0x20000121 = 0); NONFAILING(*(uint8_t*)0x20000122 = 0); NONFAILING(*(uint8_t*)0x20000123 = 0); NONFAILING(*(uint32_t*)0x20000128 = htobe32(0x7f000001)); NONFAILING(*(uint32_t*)0x20000138 = htobe32(0x10000)); NONFAILING(*(uint8_t*)0x2000013c = 0x32); NONFAILING(*(uint16_t*)0x20000140 = 0); NONFAILING(*(uint64_t*)0x20000144 = htobe64(0)); NONFAILING(*(uint64_t*)0x2000014c = htobe64(1)); NONFAILING(*(uint32_t*)0x20000154 = 0); NONFAILING(*(uint8_t*)0x20000158 = 0); NONFAILING(*(uint8_t*)0x20000159 = 1); NONFAILING(*(uint8_t*)0x2000015a = 0xb7); NONFAILING(*(uint32_t*)0x2000015c = 0x1fd); NONFAILING(*(uint32_t*)0x20000160 = 0xfffffffe); NONFAILING(*(uint32_t*)0x20000164 = 0); syscall(__NR_setsockopt, r[0], 0, 0x11, 0x20000080ul, 0xe8ul); break; case 9: syscall(__NR_sendmmsg, r[0], 0x20007fc0ul, 0x800001dul, 0ul); break; case 10: syscall(__NR_openat, 0xffffffffffffff9cul, 0ul, 0x4a0040ul, 0ul); break; } } int main(void) { syscall(__NR_mmap, 0x1ffff000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul); syscall(__NR_mmap, 0x20000000ul, 0x1000000ul, 7ul, 0x32ul, -1, 0ul); syscall(__NR_mmap, 0x21000000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul); setup_sysctl(); setup_binfmt_misc(); install_segv_handler(); for (procid = 0; procid < 6; procid++) { if (fork() == 0) { do_sandbox_none(); } } sleep(1000000); return 0; }