Hello, This program will trigger kvm_spurious_fault cause a kernel bug when cpus are executing vmx_vcpu_load and __loaded_vmcs_clear function. The root cause should be hidden some race condition. reproducer + panic report is provided, tested on master available at the time of writing and on 4.20-rc3 as well as 4.20-rc2, 4.18 and 4.15 is not affected. Thank you! ww9210 ----- // autogenerated by syzkaller (https://github.com/google/syzkaller) #define _GNU_SOURCE #include <arpa/inet.h> #include <dirent.h> #include <endian.h> #include <errno.h> #include <fcntl.h> #include <net/if_arp.h> #include <netinet/in.h> #include <pthread.h> #include <sched.h> #include <setjmp.h> #include <signal.h> #include <stdarg.h> #include <stdbool.h> #include <stddef.h> #include <stdint.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/mount.h> #include <sys/prctl.h> #include <sys/resource.h> #include <sys/socket.h> #include <sys/stat.h> #include <sys/syscall.h> #include <sys/time.h> #include <sys/types.h> #include <sys/uio.h> #include <sys/wait.h> #include <time.h> #include <unistd.h> #include <linux/futex.h> #include <linux/if.h> #include <linux/if_ether.h> #include <linux/if_tun.h> #include <linux/ip.h> #include <linux/kvm.h> #include <linux/net.h> #include <linux/tcp.h> 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 use_temporary_dir(void) { char tmpdir_template[] = "./syzkaller.XXXXXX"; char* tmpdir = mkdtemp(tmpdir_template); if (!tmpdir) exit(1); if (chmod(tmpdir, 0777)) exit(1); if (chdir(tmpdir)) exit(1); } static void thread_start(void* (*fn)(void*), void* arg) { pthread_t th; pthread_attr_t attr; pthread_attr_init(&attr); pthread_attr_setstacksize(&attr, 128 << 10); if (pthread_create(&th, &attr, fn, arg)) exit(1); pthread_attr_destroy(&attr); } 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 void vsnprintf_check(char* str, size_t size, const char* format, va_list args) { int rv; rv = vsnprintf(str, size, format, args); if (rv < 0) exit(1); if ((size_t)rv >= size) exit(1); } #define COMMAND_MAX_LEN 128 #define PATH_PREFIX \ "PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin " #define PATH_PREFIX_LEN (sizeof(PATH_PREFIX) - 1) static void execute_command(bool panic, const char* format, ...) { va_list args; char command[PATH_PREFIX_LEN + COMMAND_MAX_LEN]; int rv; va_start(args, format); memcpy(command, PATH_PREFIX, PATH_PREFIX_LEN); vsnprintf_check(command + PATH_PREFIX_LEN, COMMAND_MAX_LEN, format, args); va_end(args); rv = system(command); if (rv) { if (panic) exit(1); } } static int tunfd = -1; static int tun_frags_enabled; #define SYZ_TUN_MAX_PACKET_SIZE 1000 #define TUN_IFACE "syz_tun" #define LOCAL_MAC "aa:aa:aa:aa:aa:aa" #define REMOTE_MAC "aa:aa:aa:aa:aa:bb" #define LOCAL_IPV4 "172.20.20.170" #define REMOTE_IPV4 "172.20.20.187" #define LOCAL_IPV6 "fe80::aa" #define REMOTE_IPV6 "fe80::bb" #define IFF_NAPI 0x0010 #define IFF_NAPI_FRAGS 0x0020 static void initialize_tun(void) { tunfd = open("/dev/net/tun", O_RDWR | O_NONBLOCK); if (tunfd == -1) { printf("tun: can't open /dev/net/tun: please enable CONFIG_TUN=y\n"); printf("otherwise fuzzing or reproducing might not work as intended\n"); return; } const int kTunFd = 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; execute_command(0, "sysctl -w net.ipv6.conf.%s.accept_dad=0", TUN_IFACE); execute_command(0, "sysctl -w net.ipv6.conf.%s.router_solicitations=0", TUN_IFACE); execute_command(1, "ip link set dev %s address %s", TUN_IFACE, LOCAL_MAC); execute_command(1, "ip addr add %s/24 dev %s", LOCAL_IPV4, TUN_IFACE); execute_command(1, "ip neigh add %s lladdr %s dev %s nud permanent", REMOTE_IPV4, REMOTE_MAC, TUN_IFACE); execute_command(0, "ip -6 addr add %s/120 dev %s", LOCAL_IPV6, TUN_IFACE); execute_command(0, "ip -6 neigh add %s lladdr %s dev %s nud permanent", REMOTE_IPV6, REMOTE_MAC, TUN_IFACE); execute_command(1, "ip link set dev %s up", TUN_IFACE); } #define DEV_IPV4 "172.20.20.%d" #define DEV_IPV6 "fe80::%02hx" #define DEV_MAC "aa:aa:aa:aa:aa:%02hx" static void snprintf_check(char* str, size_t size, const char* format, ...) { va_list args; va_start(args, format); vsnprintf_check(str, size, format, args); va_end(args); } static void initialize_netdevices(void) { unsigned i; const char* devtypes[] = {"ip6gretap", "bridge", "vcan", "bond", "team"}; const char* devnames[] = {"lo", "sit0", "bridge0", "vcan0", "tunl0", "gre0", "gretap0", "ip_vti0", "ip6_vti0", "ip6tnl0", "ip6gre0", "ip6gretap0", "erspan0", "bond0", "veth0", "veth1", "team0", "veth0_to_bridge", "veth1_to_bridge", "veth0_to_bond", "veth1_to_bond", "veth0_to_team", "veth1_to_team"}; const char* devmasters[] = {"bridge", "bond", "team"}; for (i = 0; i < sizeof(devtypes) / (sizeof(devtypes[0])); i++) execute_command(0, "ip link add dev %s0 type %s", devtypes[i], devtypes[i]); execute_command(0, "ip link add type veth"); for (i = 0; i < sizeof(devmasters) / (sizeof(devmasters[0])); i++) { execute_command( 0, "ip link add name %s_slave_0 type veth peer name veth0_to_%s", devmasters[i], devmasters[i]); execute_command( 0, "ip link add name %s_slave_1 type veth peer name veth1_to_%s", devmasters[i], devmasters[i]); execute_command(0, "ip link set %s_slave_0 master %s0", devmasters[i], devmasters[i]); execute_command(0, "ip link set %s_slave_1 master %s0", devmasters[i], devmasters[i]); execute_command(0, "ip link set veth0_to_%s up", devmasters[i]); execute_command(0, "ip link set veth1_to_%s up", devmasters[i]); } execute_command(0, "ip link set bridge_slave_0 up"); execute_command(0, "ip link set bridge_slave_1 up"); for (i = 0; i < sizeof(devnames) / (sizeof(devnames[0])); i++) { char addr[32]; snprintf_check(addr, sizeof(addr), DEV_IPV4, i + 10); execute_command(0, "ip -4 addr add %s/24 dev %s", addr, devnames[i]); snprintf_check(addr, sizeof(addr), DEV_IPV6, i + 10); execute_command(0, "ip -6 addr add %s/120 dev %s", addr, devnames[i]); snprintf_check(addr, sizeof(addr), DEV_MAC, i + 10); execute_command(0, "ip link set dev %s address %s", devnames[i], addr); execute_command(0, "ip link set dev %s up", devnames[i]); } } static int read_tun(char* data, int size) { if (tunfd < 0) return -1; int rv = read(tunfd, data, size); if (rv < 0) { if (errno == EAGAIN) return -1; if (errno == EBADFD) return -1; exit(1); } return rv; } static void flush_tun() { char data[SYZ_TUN_MAX_PACKET_SIZE]; while (read_tun(&data[0], sizeof(data)) != -1) { } } 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_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; NONFAILING(dt[index] = sd); NONFAILING(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; NONFAILING(dt[index + 1] = 0); NONFAILING(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); int i; for (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 6: 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); int i; for (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 uintptr_t syz_kvm_setup_cpu(uintptr_t a0, uintptr_t a1, uintptr_t a2, uintptr_t a3, uintptr_t a4, uintptr_t a5, uintptr_t a6, uintptr_t 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 = 0; const void* text = 0; uintptr_t text_size = 0; NONFAILING(text_type = text_array_ptr[0].typ); NONFAILING(text = text_array_ptr[0].text); NONFAILING(text_size = text_array_ptr[0].size); uintptr_t i; for (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; } NONFAILING(*(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); NONFAILING(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; NONFAILING(*(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); NONFAILING(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); NONFAILING(pml4[0] = PDE64_PRESENT | PDE64_RW | PDE64_USER | pdpt_addr); NONFAILING(pdpt[0] = PDE64_PRESENT | PDE64_RW | PDE64_USER | pd_addr); NONFAILING(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; NONFAILING(*((uint64_t*)(host_mem + ADDR_VAR_VMXON_PTR)) = ADDR_VAR_VMXON); NONFAILING(*((uint64_t*)(host_mem + ADDR_VAR_VMCS_PTR)) = ADDR_VAR_VMCS); NONFAILING(memcpy(host_mem + ADDR_VAR_VMEXIT_CODE, kvm_asm64_vm_exit, sizeof(kvm_asm64_vm_exit) - 1)); NONFAILING(*((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); NONFAILING(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); NONFAILING(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); NONFAILING(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); NONFAILING(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); NONFAILING(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); NONFAILING(memcpy(tss64_cpl3_addr, &tss64, sizeof(tss64))); if (text_size > 1000) text_size = 1000; if (text_prefix) { NONFAILING(memcpy(host_text, text_prefix, text_prefix_size)); void* patch = 0; NONFAILING(patch = memmem(host_text, text_prefix_size, "\xde\xc0\xad\x0b", 4)); if (patch) NONFAILING(*((uint32_t*)patch) = guest_mem + ADDR_TEXT + ((char*)patch - host_text) + 6); uint16_t magic = PREFIX_SIZE; patch = 0; NONFAILING(patch = memmem(host_text, text_prefix_size, &magic, sizeof(magic))); if (patch) NONFAILING(*((uint16_t*)patch) = guest_mem + ADDR_TEXT + text_prefix_size); } NONFAILING(memcpy((void*)(host_text + text_prefix_size), text, text_size)); NONFAILING(*(host_text + text_prefix_size + text_size) = 0xf4); NONFAILING(memcpy(host_mem + ADDR_VAR_USER_CODE, text, text_size)); NONFAILING(*(host_mem + ADDR_VAR_USER_CODE + text_size) = 0xf4); NONFAILING(*(host_mem + ADDR_VAR_HLT) = 0xf4); NONFAILING(memcpy(host_mem + ADDR_VAR_SYSRET, "\x0f\x07\xf4", 3)); NONFAILING(memcpy(host_mem + ADDR_VAR_SYSEXIT, "\x0f\x35\xf4", 3)); NONFAILING(*(uint64_t*)(host_mem + ADDR_VAR_VMWRITE_FLD) = 0); NONFAILING(*(uint64_t*)(host_mem + ADDR_VAR_VMWRITE_VAL) = 0); if (opt_count > 2) opt_count = 2; for (i = 0; i < opt_count; i++) { uint64_t typ = 0; uint64_t val = 0; NONFAILING(typ = opt_array_ptr[i].typ); NONFAILING(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; NONFAILING(tss16_addr->flags ^= val); NONFAILING(tss16_cpl3_addr->flags ^= val); NONFAILING(tss32_addr->flags ^= val); NONFAILING(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: NONFAILING(*(uint64_t*)(host_mem + ADDR_VAR_VMWRITE_FLD) = (val & 0xffff)); NONFAILING(*(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 bool write_file(const char* file, const char* what, ...) { char buf[1024]; va_list args; va_start(args, what); vsnprintf(buf, sizeof(buf), what, args); va_end(args); buf[sizeof(buf) - 1] = 0; int len = strlen(buf); int fd = open(file, O_WRONLY | O_CLOEXEC); if (fd == -1) return false; if (write(fd, buf, len) != len) { int err = errno; close(fd); errno = err; return false; } close(fd); return true; } #define 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_cgroups() { if (mkdir("/syzcgroup", 0777)) { } if (mkdir("/syzcgroup/unified", 0777)) { } if (mount("none", "/syzcgroup/unified", "cgroup2", 0, NULL)) { } if (chmod("/syzcgroup/unified", 0777)) { } if (!write_file("/syzcgroup/unified/cgroup.subtree_control", "+cpu +memory +io +pids +rdma")) { } if (mkdir("/syzcgroup/cpu", 0777)) { } if (mount("none", "/syzcgroup/cpu", "cgroup", 0, "cpuset,cpuacct,perf_event,hugetlb")) { } if (!write_file("/syzcgroup/cpu/cgroup.clone_children", "1")) { } if (chmod("/syzcgroup/cpu", 0777)) { } if (mkdir("/syzcgroup/net", 0777)) { } if (mount("none", "/syzcgroup/net", "cgroup", 0, "net_cls,net_prio,devices,freezer")) { } if (chmod("/syzcgroup/net", 0777)) { } } static void setup_binfmt_misc() { if (mount(0, "/proc/sys/fs/binfmt_misc", "binfmt_misc", 0, 0)) { } if (!write_file("/proc/sys/fs/binfmt_misc/register", ":syz0:M:0:\x01::./file0:")) { } if (!write_file("/proc/sys/fs/binfmt_misc/register", ":syz1:M:1:\x02::./file0:POC")) { } } static void setup_common() { if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) { } setup_cgroups(); setup_binfmt_misc(); } 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)) { } } 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(); if (unshare(CLONE_NEWNET)) { } initialize_tun(); initialize_netdevices(); loop(); exit(1); } #define FS_IOC_SETFLAGS _IOW('f', 2, long) static void remove_dir(const char* dir) { DIR* dp; struct dirent* ep; int iter = 0; retry: while (umount2(dir, MNT_DETACH) == 0) { } dp = opendir(dir); if (dp == NULL) { if (errno == EMFILE) { exit(1); } exit(1); } while ((ep = readdir(dp))) { if (strcmp(ep->d_name, ".") == 0 || strcmp(ep->d_name, "..") == 0) continue; char filename[FILENAME_MAX]; snprintf(filename, sizeof(filename), "%s/%s", dir, ep->d_name); while (umount2(filename, MNT_DETACH) == 0) { } struct stat st; if (lstat(filename, &st)) exit(1); if (S_ISDIR(st.st_mode)) { remove_dir(filename); continue; } int i; for (i = 0;; i++) { if (unlink(filename) == 0) break; if (errno == EPERM) { int fd = open(filename, O_RDONLY); if (fd != -1) { long flags = 0; if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0) close(fd); continue; } } if (errno == EROFS) { break; } if (errno != EBUSY || i > 100) exit(1); if (umount2(filename, MNT_DETACH)) exit(1); } } closedir(dp); int i; for (i = 0;; i++) { if (rmdir(dir) == 0) break; if (i < 100) { if (errno == EPERM) { int fd = open(dir, O_RDONLY); if (fd != -1) { long flags = 0; if (ioctl(fd, FS_IOC_SETFLAGS, &flags) == 0) close(fd); continue; } } if (errno == EROFS) { break; } if (errno == EBUSY) { if (umount2(dir, MNT_DETACH)) exit(1); continue; } if (errno == ENOTEMPTY) { if (iter < 100) { iter++; goto retry; } } } exit(1); } } static void kill_and_wait(int pid, int* status) { kill(-pid, SIGKILL); kill(pid, SIGKILL); 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) { } } #define SYZ_HAVE_SETUP_LOOP 1 static void setup_loop() { int pid = getpid(); char cgroupdir[64]; char file[128]; snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid); if (mkdir(cgroupdir, 0777)) { } snprintf(file, sizeof(file), "%s/pids.max", cgroupdir); if (!write_file(file, "32")) { } snprintf(file, sizeof(file), "%s/memory.low", cgroupdir); if (!write_file(file, "%d", 298 << 20)) { } snprintf(file, sizeof(file), "%s/memory.high", cgroupdir); if (!write_file(file, "%d", 299 << 20)) { } snprintf(file, sizeof(file), "%s/memory.max", cgroupdir); if (!write_file(file, "%d", 300 << 20)) { } snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir); if (!write_file(file, "%d", pid)) { } snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid); if (mkdir(cgroupdir, 0777)) { } snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir); if (!write_file(file, "%d", pid)) { } snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid); if (mkdir(cgroupdir, 0777)) { } snprintf(file, sizeof(file), "%s/cgroup.procs", cgroupdir); if (!write_file(file, "%d", pid)) { } checkpoint_net_namespace(); } #define SYZ_HAVE_RESET_LOOP 1 static void reset_loop() { reset_net_namespace(); } #define SYZ_HAVE_SETUP_TEST 1 static void setup_test() { prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); setpgrp(); char cgroupdir[64]; snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/unified/syz%llu", procid); if (symlink(cgroupdir, "./cgroup")) { } snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/cpu/syz%llu", procid); if (symlink(cgroupdir, "./cgroup.cpu")) { } snprintf(cgroupdir, sizeof(cgroupdir), "/syzcgroup/net/syz%llu", procid); if (symlink(cgroupdir, "./cgroup.net")) { } if (!write_file("/proc/self/oom_score_adj", "1000")) { } flush_tun(); } #define SYZ_HAVE_RESET_TEST 1 static void reset_test() { 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 < 6; 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); 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++) { char cwdbuf[32]; sprintf(cwdbuf, "./%d", iter); if (mkdir(cwdbuf, 0777)) exit(1); reset_loop(); int pid = fork(); if (pid < 0) exit(1); if (pid == 0) { if (chdir(cwdbuf)) exit(1); setup_test(); execute_one(); reset_test(); 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; } remove_dir(cwdbuf); } } uint64_t r[3] = {0xffffffffffffffff, 0xffffffffffffffff, 0xffffffffffffffff}; void execute_call(int call) { long res; switch (call) { case 0: NONFAILING(memcpy((void*)0x20000200, "/dev/kvm", 9)); res = syscall(__NR_openat, 0xffffffffffffff9c, 0x20000200, 0, 0); if (res != -1) r[0] = res; break; case 1: res = syscall(__NR_ioctl, r[0], 0xae01, 0); if (res != -1) r[1] = res; break; case 2: res = syscall(__NR_ioctl, r[1], 0xae41, 0); if (res != -1) r[2] = res; break; case 3: NONFAILING(*(uint64_t*)0x20000080 = 0x40); NONFAILING(*(uint64_t*)0x20000088 = 0x20000000); NONFAILING(memcpy( (void*)0x20000000, "\x48\xb8\x00\x00\x00\x00\x00\x00\x00\x80\x0f\x23\xd0\x0f\x21\xf8\x35" "\x00\x00\x00\x04\x0f\x23\xf8\x44\x0f\x20\xc0\x35\x04\x00\x00\x00\x44" "\x0f\x22\xc0\xc4\xa2\x79\x34\x33\xc7\x44\x24\x00\x00\x50\x00\x00\xc7" "\x44\x24\x02\xdc\xa8\xe3\x94\xc7\x44\x24\x06\x00\x00\x00\x00\x0f\x01" "\x1c\x24\x66\xba\xf8\x0c\xb8\x18\x08\xae\x8f\xef\x66\xba\xfc\x0c\xed" "\xf3\x46\x0f\x1a\xd3\xc4\xe2\x2a\xf5\xa5\x00\x98\x00\x00\x0f\x20\xc0" "\x35\x00\x00\x00\x80\x0f\x22\xc0\x45\x0f\x07\x66\xf2\x41\xf4", 117)); NONFAILING(*(uint64_t*)0x20000090 = 0x75); syz_kvm_setup_cpu(r[1], r[2], 0x20fe8000, 0x20000080, 1, 0, 0x20000100, 0); break; case 4: syscall(__NR_ioctl, r[2], 0xae80, 0); break; case 5: NONFAILING(*(uint8_t*)0x20000100 = 1); NONFAILING(*(uint8_t*)0x20000101 = 3); NONFAILING(*(uint8_t*)0x20000102 = 2); NONFAILING(*(uint8_t*)0x20000103 = 0); NONFAILING(*(uint32_t*)0x20000104 = 0x66c2); NONFAILING(*(uint8_t*)0x20000108 = 0); NONFAILING(*(uint8_t*)0x20000109 = 0xfa); NONFAILING(*(uint8_t*)0x2000010a = 0); NONFAILING(*(uint8_t*)0x2000010b = 0x80); NONFAILING(*(uint8_t*)0x2000010c = 9); NONFAILING(*(uint8_t*)0x2000010d = -1); NONFAILING(*(uint8_t*)0x2000010e = 1); NONFAILING(*(uint8_t*)0x2000010f = 0); NONFAILING(*(uint32_t*)0x20000110 = 9); NONFAILING(*(uint32_t*)0x20000114 = 0); NONFAILING(*(uint8_t*)0x20000118 = 9); NONFAILING(*(uint8_t*)0x20000119 = 8); NONFAILING(*(uint8_t*)0x2000011a = 5); NONFAILING(*(uint8_t*)0x2000011b = 0x3b); syscall(__NR_ioctl, r[2], 0x4040aea0, 0x20000100); break; } } int main(void) { syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0); install_segv_handler(); for (procid = 0; procid < 8; procid++) { if (fork() == 0) { use_temporary_dir(); do_sandbox_none(); } } sleep(1000000); return 0; } ----- [ 36.572752] ------------[ cut here ]------------ [ 36.573580] kernel BUG at /home/ww9210/kernel/linux-v4.20-rc2/arch/x86/kvm/x86.c:353! [ 36.574931] invalid opcode: 0000 [#1] SMP PTI [ 36.575685] CPU: 1 PID: 6654 Comm: poc Not tainted 4.20.0-rc2 #4 [ 36.576711] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 36.578234] RIP: 0010:kvm_spurious_fault+0x5/0x10 [ 36.579042] Code: 70 19 00 89 1d 7c e7 70 01 5b 5d e9 b5 70 19 00 e8 b0 70 19 00 0f 0b 0f 1f 40 00 66 2e 0f 1f 84 00 00 00 00 00 e8 9b 70 19 00 <0f> 0b 66 0f 1f 84 00 00 00 00 00 41 57 41 56 49 89 fe 41 55 41 54 [ 36.582164] RSP: 0018:ffffc90003617c40 EFLAGS: 00010293 [ 36.583050] RAX: ffff888079952880 RBX: 0000000075e5e000 RCX: ffffffff810379c5 [ 36.584249] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff888075e5e000 [ 36.585455] RBP: ffff8880f5e5e000 R08: 0000000000000000 R09: 0000000000001b37 [ 36.586652] R10: ffffc90003617dc0 R11: 0000000000000001 R12: ffff888075e5e000 [ 36.587846] R13: 0000000000000001 R14: ffff888075fad828 R15: 0000000000014110 [ 36.589048] FS: 00000000024aa940(0000) GS:ffff88807db00000(0000) knlGS:0000000000000000 [ 36.590411] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 36.591382] CR2: ffffc90003617c50 CR3: 0000000075f3e003 CR4: 00000000001626e0 [ 36.592584] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 8000000000000000 [ 36.593792] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 36.594990] Call Trace: [ 36.595441] kvm_fastop_exception+0x264/0x549c [ 36.596204] ? vmcs_load+0x56/0xb0 [ 36.596799] vmx_vcpu_load+0x10b/0x3f0 [ 36.597446] ? schedule_timeout+0x25b/0x480 [ 36.598162] ? __queue_delayed_work+0xb7/0x120 [ 36.598924] ? kvm_arch_vcpu_load+0x8f/0x320 [ 36.599653] ? __x86_set_memory_region+0x150/0x220 [ 36.600471] ? __synchronize_srcu.part.17+0x8c/0xc0 [ 36.601307] ? trace_event_raw_event_rcu_torture_read+0xf0/0xf0 [ 36.602310] ? handle_invpcid+0x450/0x450 [ 36.602999] kvm_arch_vcpu_load+0x8f/0x320 [ 36.603704] ? vcpu_load+0x24/0x30 [ 36.604292] vcpu_load+0x24/0x30 [ 36.604856] kvm_arch_destroy_vm+0xa5/0x1e0 [ 36.605570] kvm_destroy_vm+0x178/0x2e0 [ 36.606228] ? kvm_vm_compat_ioctl+0x100/0x100 [ 36.606985] kvm_vcpu_release+0x3b/0x50 [ 36.607646] __fput+0x108/0x260 [ 36.608201] task_work_run+0xaa/0xd0 [ 36.608823] exit_to_usermode_loop+0x110/0x120 [ 36.609580] do_syscall_64+0x122/0x150 [ 36.610225] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 36.611083] RIP: 0033:0x40c4b7 [ 36.611613] Code: 00 00 0f 05 48 3d 00 f0 ff ff 77 3f f3 c3 0f 1f 44 00 00 53 89 fb 48 83 ec 10 e8 f4 fb ff ff 89 df 89 c2 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 2b 89 d7 89 44 24 0c e8 36 fc ff ff 8b 44 24 [ 36.614761] RSP: 002b:00007ffef2bfffd0 EFLAGS: 00000293 ORIG_RAX: 0000000000000003 [ 36.616035] RAX: 0000000000000000 RBX: 0000000000000005 RCX: 000000000040c4b7 [ 36.617239] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000005 [ 36.618437] RBP: 00007ffef2c00000 R08: 0000000000000000 R09: 000000000000002d [ 36.619636] R10: 00007ffef2bfffb0 R11: 0000000000000293 R12: 000000000040e6f0 [ 36.620839] R13: 0000000000000000 R14: 00000000006e0018 R15: 0000000000000000 [ 36.622039] Modules linked in: [ 36.622570] Dumping ftrace buffer: [ 36.623156] (ftrace buffer empty) [ 36.623800] ------------[ cut here ]------------ [ 36.624586] kernel BUG at /home/ww9210/kernel/linux-v4.20-rc2/arch/x86/kvm/x86.c:353! [ 36.625912] invalid opcode: 0000 [#2] SMP PTI [ 36.626655] CPU: 1 PID: 6654 Comm: poc Tainted: G D 4.20.0-rc2 #4 [ 36.627894] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 36.629403] RIP: 0010:kvm_spurious_fault+0x5/0x10 [ 36.630205] Code: 70 19 00 89 1d 7c e7 70 01 5b 5d e9 b5 70 19 00 e8 b0 70 19 00 0f 0b 0f 1f 40 00 66 2e 0f 1f 84 00 00 00 00 00 e8 9b 70 19 00 <0f> 0b 66 0f 1f 84 00 00 00 00 00 41 57 41 56 49 89 fe 41 55 41 54 [ 36.633325] RSP: 0018:ffff88807db03f50 EFLAGS: 00010006 [ 36.634213] RAX: ffff888079952880 RBX: 000000007549c000 RCX: ffffffff810379c5 [ 36.635409] RDX: 0000000000010000 RSI: 0000000000000000 RDI: ffff88807549c000 [ 36.636607] RBP: ffff8880f549c000 R08: 0000000000000000 R09: 0000000000000000 [ 36.637809] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88807549c000 [ 36.639010] R13: ffff88807db00000 R14: ffff8880754cd828 R15: 0000000000000000 [ 36.640211] FS: 00000000024aa940(0000) GS:ffff88807db00000(0000) knlGS:0000000000000000 [ 36.641574] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 36.642545] CR2: ffff88807db03f60 CR3: 0000000075f3e003 CR4: 00000000001626e0 [ 36.643744] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 8000000000000000 [ 36.644949] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 36.646149] Call Trace: [ 36.646578] <IRQ> [ 36.646940] kvm_fastop_exception+0x24c/0x549c [ 36.647700] ? vmcs_clear+0x4c/0xa0 [ 36.648303] __loaded_vmcs_clear+0x8b/0xf0 [ 36.649009] ? crash_vmclear_local_loaded_vmcss+0x80/0x80 [ 36.649929] flush_smp_call_function_queue+0x66/0x160 [ 36.650788] smp_call_function_single_interrupt+0x35/0xd0 [ 36.651706] call_function_single_interrupt+0xf/0x20 [ 36.652548] </IRQ> [ 36.652927] RIP: 0010:oops_end+0x56/0xc0 [ 36.653602] Code: 00 00 00 bf 07 00 00 00 c7 05 22 03 58 01 ff ff ff ff e8 dd e0 04 00 83 2d 7e 2c d6 01 01 75 07 c6 05 79 2c d6 01 00 41 54 9d <e8> 05 e6 04 00 be 02 00 00 00 48 c7 c7 80 41 e1 82 e8 74 b2 ff ff [ 36.656733] RSP: 0018:ffffc90003617b10 EFLAGS: 00000293 ORIG_RAX: ffffffffffffff04 [ 36.658010] RAX: ffff888079952880 RBX: 000000000000000b RCX: ffffffff810ff5d5 [ 36.659213] RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000007 [ 36.660415] RBP: ffffc90003617b98 R08: 0000000c090c7fca R09: 0000000000000018 [ 36.661625] R10: 0000000000000003 R11: 000000000000002b R12: 0000000000000293 [ 36.662828] R13: 0000000000000004 R14: 0000000000000002 R15: ffffffff82402acb [ 36.664039] ? add_taint+0x15/0x50 [ 36.664637] do_trap+0x81/0x100 [ 36.665187] ? kvm_spurious_fault+0x5/0x10 [ 36.665887] do_invalid_op+0x31/0x40 [ 36.666502] ? kvm_spurious_fault+0x5/0x10 [ 36.667204] invalid_op+0x14/0x20 [ 36.667776] RIP: 0010:kvm_spurious_fault+0x5/0x10 [ 36.668580] Code: 70 19 00 89 1d 7c e7 70 01 5b 5d e9 b5 70 19 00 e8 b0 70 19 00 0f 0b 0f 1f 40 00 66 2e 0f 1f 84 00 00 00 00 00 e8 9b 70 19 00 <0f> 0b 66 0f 1f 84 00 00 00 00 00 41 57 41 56 49 89 fe 41 55 41 54 [ 36.671710] RSP: 0018:ffffc90003617c40 EFLAGS: 00010293 [ 36.672598] RAX: ffff888079952880 RBX: 0000000075e5e000 RCX: ffffffff810379c5 [ 36.673809] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff888075e5e000 [ 36.675011] RBP: ffff8880f5e5e000 R08: 0000000000000000 R09: 0000000000001b37 [ 36.676207] R10: ffffc90003617dc0 R11: 0000000000000001 R12: ffff888075e5e000 [ 36.677411] R13: 0000000000000001 R14: ffff888075fad828 R15: 0000000000014110 [ 36.678618] ? kvm_spurious_fault+0x5/0x10 [ 36.679323] kvm_fastop_exception+0x264/0x549c [ 36.680084] ? vmcs_load+0x56/0xb0 [ 36.680678] vmx_vcpu_load+0x10b/0x3f0 [ 36.681324] ? schedule_timeout+0x25b/0x480 [ 36.682042] ? __queue_delayed_work+0xb7/0x120 [ 36.682804] ? kvm_arch_vcpu_load+0x8f/0x320 [ 36.683534] ? __x86_set_memory_region+0x150/0x220 [ 36.684354] ? __synchronize_srcu.part.17+0x8c/0xc0 [ 36.685194] ? trace_event_raw_event_rcu_torture_read+0xf0/0xf0 [ 36.686196] ? handle_invpcid+0x450/0x450 [ 36.686884] kvm_arch_vcpu_load+0x8f/0x320 [ 36.687588] ? vcpu_load+0x24/0x30 [ 36.688175] vcpu_load+0x24/0x30 [ 36.688740] kvm_arch_destroy_vm+0xa5/0x1e0 [ 36.689454] kvm_destroy_vm+0x178/0x2e0 [ 36.690112] ? kvm_vm_compat_ioctl+0x100/0x100 [ 36.690870] kvm_vcpu_release+0x3b/0x50 [ 36.691533] __fput+0x108/0x260 [ 36.692078] task_work_run+0xaa/0xd0 [ 36.692701] exit_to_usermode_loop+0x110/0x120 [ 36.693481] do_syscall_64+0x122/0x150 [ 36.694128] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 36.694986] RIP: 0033:0x40c4b7 [ 36.695516] Code: 00 00 0f 05 48 3d 00 f0 ff ff 77 3f f3 c3 0f 1f 44 00 00 53 89 fb 48 83 ec 10 e8 f4 fb ff ff 89 df 89 c2 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 2b 89 d7 89 44 24 0c e8 36 fc ff ff 8b 44 24 [ 36.698645] RSP: 002b:00007ffef2bfffd0 EFLAGS: 00000293 ORIG_RAX: 0000000000000003 [ 36.699919] RAX: 0000000000000000 RBX: 0000000000000005 RCX: 000000000040c4b7 [ 36.701126] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000005 [ 36.702329] RBP: 00007ffef2c00000 R08: 0000000000000000 R09: 000000000000002d [ 36.703532] R10: 00007ffef2bfffb0 R11: 0000000000000293 R12: 000000000040e6f0 [ 36.704739] R13: 0000000000000000 R14: 00000000006e0018 R15: 0000000000000000 [ 36.705942] Modules linked in: [ 36.706473] Dumping ftrace buffer: [ 36.707061] (ftrace buffer empty) [ 36.707679] ---[ end trace 8155a549cb1669e1 ]--- [ 36.708470] RIP: 0010:kvm_spurious_fault+0x5/0x10 [ 36.709277] Code: 70 19 00 89 1d 7c e7 70 01 5b 5d e9 b5 70 19 00 e8 b0 70 19 00 0f 0b 0f 1f 40 00 66 2e 0f 1f 84 00 00 00 00 00 e8 9b 70 19 00 <0f> 0b 66 0f 1f 84 00 00 00 00 00 41 57 41 56 49 89 fe 41 55 41 54 [ 36.712392] RSP: 0018:ffffc90003617c40 EFLAGS: 00010293 [ 36.713287] RAX: ffff888079952880 RBX: 0000000075e5e000 RCX: ffffffff810379c5 [ 36.714485] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff888075e5e000 [ 36.715686] RBP: ffff8880f5e5e000 R08: 0000000000000000 R09: 0000000000001b37 [ 36.716891] R10: ffffc90003617dc0 R11: 0000000000000001 R12: ffff888075e5e000 [ 36.718093] R13: 0000000000000001 R14: ffff888075fad828 R15: 0000000000014110 [ 36.719296] FS: 00000000024aa940(0000) GS:ffff88807db00000(0000) knlGS:0000000000000000 [ 36.720661] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 36.721632] CR2: ffff88807db03f60 CR3: 0000000075f3e003 CR4: 00000000001626e0 [ 36.722835] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 8000000000000000 [ 36.724035] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 36.725241] Kernel panic - not syncing: Fatal exception in interrupt [ 36.726356] Dumping ftrace buffer: [ 36.726939] (ftrace buffer empty) [ 36.727572] Kernel Offset: disabled [ 36.728168] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- [ 36.729444] ------------[ cut here ]------------ [ 36.730220] sched: Unexpected reschedule of offline CPU#0! [ 36.731153] WARNING: CPU: 1 PID: 6654 at /home/ww9210/kernel/linux-v4.20-rc2/arch/x86/kernel/smp.c:128 native_smp_send_reschedule+0x2f/0x40 [ 36.733220] Kernel panic - not syncing: panic_on_warn set ... [ 36.734199] Dumping ftrace buffer: [ 36.734776] (ftrace buffer empty) [ 36.735381] Kernel Offset: disabled [ 36.735972] ---[ end Kernel panic - not syncing: panic_on_warn set ... ]---
