| // BUG: unable to handle kernel paging request in vmx_vcpu_run |
| // https://syzkaller.appspot.com/bug?id=b67fcc95c0d84ea5424813a0d8703fc5c06de7ee |
| // status:open |
| // autogenerated by syzkaller (http://github.com/google/syzkaller) |
| |
| #define _GNU_SOURCE |
| #include <dirent.h> |
| #include <endian.h> |
| #include <errno.h> |
| #include <errno.h> |
| #include <fcntl.h> |
| #include <linux/futex.h> |
| #include <linux/kvm.h> |
| #include <linux/net.h> |
| #include <netinet/in.h> |
| #include <pthread.h> |
| #include <signal.h> |
| #include <stdarg.h> |
| #include <stdarg.h> |
| #include <stddef.h> |
| #include <stdio.h> |
| #include <stdio.h> |
| #include <stdlib.h> |
| #include <sys/ioctl.h> |
| #include <sys/mount.h> |
| #include <sys/prctl.h> |
| #include <sys/socket.h> |
| #include <sys/stat.h> |
| #include <sys/syscall.h> |
| #include <sys/time.h> |
| #include <sys/wait.h> |
| #include <time.h> |
| #include <unistd.h> |
| |
| __attribute__((noreturn)) static void doexit(int status) |
| { |
| volatile unsigned i; |
| syscall(__NR_exit_group, status); |
| for (i = 0;; i++) { |
| } |
| } |
| #include <errno.h> |
| #include <setjmp.h> |
| #include <signal.h> |
| #include <stdarg.h> |
| #include <stdint.h> |
| #include <stdio.h> |
| #include <stdlib.h> |
| #include <string.h> |
| #include <string.h> |
| #include <sys/stat.h> |
| |
| const int kFailStatus = 67; |
| const int kRetryStatus = 69; |
| |
| static void fail(const char* msg, ...) |
| { |
| int e = errno; |
| va_list args; |
| va_start(args, msg); |
| vfprintf(stderr, msg, args); |
| va_end(args); |
| fprintf(stderr, " (errno %d)\n", e); |
| doexit((e == ENOMEM || e == EAGAIN) ? kRetryStatus : kFailStatus); |
| } |
| |
| static void exitf(const char* msg, ...) |
| { |
| int e = errno; |
| va_list args; |
| va_start(args, msg); |
| vfprintf(stderr, msg, args); |
| va_end(args); |
| fprintf(stderr, " (errno %d)\n", e); |
| doexit(kRetryStatus); |
| } |
| |
| static __thread int skip_segv; |
| static __thread jmp_buf segv_env; |
| |
| static void segv_handler(int sig, siginfo_t* info, void* uctx) |
| { |
| 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); |
| } |
| doexit(sig); |
| } |
| |
| static void install_segv_handler() |
| { |
| 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 uint64_t current_time_ms() |
| { |
| struct timespec ts; |
| |
| if (clock_gettime(CLOCK_MONOTONIC, &ts)) |
| fail("clock_gettime failed"); |
| return (uint64_t)ts.tv_sec * 1000 + (uint64_t)ts.tv_nsec / 1000000; |
| } |
| |
| static void use_temporary_dir() |
| { |
| char tmpdir_template[] = "./syzkaller.XXXXXX"; |
| char* tmpdir = mkdtemp(tmpdir_template); |
| if (!tmpdir) |
| fail("failed to mkdtemp"); |
| if (chmod(tmpdir, 0777)) |
| fail("failed to chmod"); |
| if (chdir(tmpdir)) |
| fail("failed to chdir"); |
| } |
| |
| 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: |
| fail("bad kvm setup opt"); |
| } |
| } |
| 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; |
| } |
| |
| #define XT_TABLE_SIZE 1536 |
| #define XT_MAX_ENTRIES 10 |
| |
| struct xt_counters { |
| uint64_t pcnt, bcnt; |
| }; |
| |
| struct ipt_getinfo { |
| char name[32]; |
| unsigned int valid_hooks; |
| unsigned int hook_entry[5]; |
| unsigned int underflow[5]; |
| unsigned int num_entries; |
| unsigned int size; |
| }; |
| |
| struct ipt_get_entries { |
| char name[32]; |
| unsigned int size; |
| void* entrytable[XT_TABLE_SIZE / sizeof(void*)]; |
| }; |
| |
| struct ipt_replace { |
| char name[32]; |
| unsigned int valid_hooks; |
| unsigned int num_entries; |
| unsigned int size; |
| unsigned int hook_entry[5]; |
| unsigned int underflow[5]; |
| unsigned int num_counters; |
| struct xt_counters* counters; |
| char entrytable[XT_TABLE_SIZE]; |
| }; |
| |
| struct ipt_table_desc { |
| const char* name; |
| struct ipt_getinfo info; |
| struct ipt_replace replace; |
| }; |
| |
| static struct ipt_table_desc ipv4_tables[] = { |
| {.name = "filter"}, {.name = "nat"}, {.name = "mangle"}, |
| {.name = "raw"}, {.name = "security"}, |
| }; |
| |
| static struct ipt_table_desc ipv6_tables[] = { |
| {.name = "filter"}, {.name = "nat"}, {.name = "mangle"}, |
| {.name = "raw"}, {.name = "security"}, |
| }; |
| |
| #define IPT_BASE_CTL 64 |
| #define IPT_SO_SET_REPLACE (IPT_BASE_CTL) |
| #define IPT_SO_GET_INFO (IPT_BASE_CTL) |
| #define IPT_SO_GET_ENTRIES (IPT_BASE_CTL + 1) |
| |
| struct arpt_getinfo { |
| char name[32]; |
| unsigned int valid_hooks; |
| unsigned int hook_entry[3]; |
| unsigned int underflow[3]; |
| unsigned int num_entries; |
| unsigned int size; |
| }; |
| |
| struct arpt_get_entries { |
| char name[32]; |
| unsigned int size; |
| void* entrytable[XT_TABLE_SIZE / sizeof(void*)]; |
| }; |
| |
| struct arpt_replace { |
| char name[32]; |
| unsigned int valid_hooks; |
| unsigned int num_entries; |
| unsigned int size; |
| unsigned int hook_entry[3]; |
| unsigned int underflow[3]; |
| unsigned int num_counters; |
| struct xt_counters* counters; |
| char entrytable[XT_TABLE_SIZE]; |
| }; |
| |
| struct arpt_table_desc { |
| const char* name; |
| struct arpt_getinfo info; |
| struct arpt_replace replace; |
| }; |
| |
| static struct arpt_table_desc arpt_tables[] = { |
| {.name = "filter"}, |
| }; |
| |
| #define ARPT_BASE_CTL 96 |
| #define ARPT_SO_SET_REPLACE (ARPT_BASE_CTL) |
| #define ARPT_SO_GET_INFO (ARPT_BASE_CTL) |
| #define ARPT_SO_GET_ENTRIES (ARPT_BASE_CTL + 1) |
| |
| static void checkpoint_iptables(struct ipt_table_desc* tables, int num_tables, |
| int family, int level) |
| { |
| struct ipt_get_entries entries; |
| socklen_t optlen; |
| int fd, i; |
| |
| fd = socket(family, SOCK_STREAM, IPPROTO_TCP); |
| if (fd == -1) |
| fail("socket(%d, SOCK_STREAM, IPPROTO_TCP)", family); |
| for (i = 0; i < num_tables; i++) { |
| struct ipt_table_desc* table = &tables[i]; |
| strcpy(table->info.name, table->name); |
| strcpy(table->replace.name, table->name); |
| optlen = sizeof(table->info); |
| if (getsockopt(fd, level, IPT_SO_GET_INFO, &table->info, &optlen)) { |
| switch (errno) { |
| case EPERM: |
| case ENOENT: |
| case ENOPROTOOPT: |
| continue; |
| } |
| fail("getsockopt(IPT_SO_GET_INFO)"); |
| } |
| if (table->info.size > sizeof(table->replace.entrytable)) |
| fail("table size is too large: %u", table->info.size); |
| if (table->info.num_entries > XT_MAX_ENTRIES) |
| fail("too many counters: %u", table->info.num_entries); |
| memset(&entries, 0, sizeof(entries)); |
| strcpy(entries.name, table->name); |
| entries.size = table->info.size; |
| optlen = sizeof(entries) - sizeof(entries.entrytable) + table->info.size; |
| if (getsockopt(fd, level, IPT_SO_GET_ENTRIES, &entries, &optlen)) |
| fail("getsockopt(IPT_SO_GET_ENTRIES)"); |
| table->replace.valid_hooks = table->info.valid_hooks; |
| table->replace.num_entries = table->info.num_entries; |
| table->replace.size = table->info.size; |
| memcpy(table->replace.hook_entry, table->info.hook_entry, |
| sizeof(table->replace.hook_entry)); |
| memcpy(table->replace.underflow, table->info.underflow, |
| sizeof(table->replace.underflow)); |
| memcpy(table->replace.entrytable, entries.entrytable, table->info.size); |
| } |
| close(fd); |
| } |
| |
| static void reset_iptables(struct ipt_table_desc* tables, int num_tables, |
| int family, int level) |
| { |
| struct xt_counters counters[XT_MAX_ENTRIES]; |
| struct ipt_get_entries entries; |
| struct ipt_getinfo info; |
| socklen_t optlen; |
| int fd, i; |
| |
| fd = socket(family, SOCK_STREAM, IPPROTO_TCP); |
| if (fd == -1) |
| fail("socket(%d, SOCK_STREAM, IPPROTO_TCP)", family); |
| for (i = 0; i < num_tables; i++) { |
| struct ipt_table_desc* table = &tables[i]; |
| if (table->info.valid_hooks == 0) |
| continue; |
| memset(&info, 0, sizeof(info)); |
| strcpy(info.name, table->name); |
| optlen = sizeof(info); |
| if (getsockopt(fd, level, IPT_SO_GET_INFO, &info, &optlen)) |
| fail("getsockopt(IPT_SO_GET_INFO)"); |
| if (memcmp(&table->info, &info, sizeof(table->info)) == 0) { |
| memset(&entries, 0, sizeof(entries)); |
| strcpy(entries.name, table->name); |
| entries.size = table->info.size; |
| optlen = sizeof(entries) - sizeof(entries.entrytable) + entries.size; |
| if (getsockopt(fd, level, IPT_SO_GET_ENTRIES, &entries, &optlen)) |
| fail("getsockopt(IPT_SO_GET_ENTRIES)"); |
| if (memcmp(table->replace.entrytable, entries.entrytable, |
| table->info.size) == 0) |
| continue; |
| } |
| table->replace.num_counters = info.num_entries; |
| table->replace.counters = counters; |
| optlen = sizeof(table->replace) - sizeof(table->replace.entrytable) + |
| table->replace.size; |
| if (setsockopt(fd, level, IPT_SO_SET_REPLACE, &table->replace, optlen)) |
| fail("setsockopt(IPT_SO_SET_REPLACE)"); |
| } |
| close(fd); |
| } |
| |
| static void checkpoint_arptables(void) |
| { |
| struct arpt_get_entries entries; |
| socklen_t optlen; |
| unsigned i; |
| int fd; |
| |
| fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); |
| if (fd == -1) |
| fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)"); |
| for (i = 0; i < sizeof(arpt_tables) / sizeof(arpt_tables[0]); i++) { |
| struct arpt_table_desc* table = &arpt_tables[i]; |
| strcpy(table->info.name, table->name); |
| strcpy(table->replace.name, table->name); |
| optlen = sizeof(table->info); |
| if (getsockopt(fd, SOL_IP, ARPT_SO_GET_INFO, &table->info, &optlen)) { |
| switch (errno) { |
| case EPERM: |
| case ENOENT: |
| case ENOPROTOOPT: |
| continue; |
| } |
| fail("getsockopt(ARPT_SO_GET_INFO)"); |
| } |
| if (table->info.size > sizeof(table->replace.entrytable)) |
| fail("table size is too large: %u", table->info.size); |
| if (table->info.num_entries > XT_MAX_ENTRIES) |
| fail("too many counters: %u", table->info.num_entries); |
| memset(&entries, 0, sizeof(entries)); |
| strcpy(entries.name, table->name); |
| entries.size = table->info.size; |
| optlen = sizeof(entries) - sizeof(entries.entrytable) + table->info.size; |
| if (getsockopt(fd, SOL_IP, ARPT_SO_GET_ENTRIES, &entries, &optlen)) |
| fail("getsockopt(ARPT_SO_GET_ENTRIES)"); |
| table->replace.valid_hooks = table->info.valid_hooks; |
| table->replace.num_entries = table->info.num_entries; |
| table->replace.size = table->info.size; |
| memcpy(table->replace.hook_entry, table->info.hook_entry, |
| sizeof(table->replace.hook_entry)); |
| memcpy(table->replace.underflow, table->info.underflow, |
| sizeof(table->replace.underflow)); |
| memcpy(table->replace.entrytable, entries.entrytable, table->info.size); |
| } |
| close(fd); |
| } |
| |
| static void reset_arptables() |
| { |
| struct xt_counters counters[XT_MAX_ENTRIES]; |
| struct arpt_get_entries entries; |
| struct arpt_getinfo info; |
| socklen_t optlen; |
| unsigned i; |
| int fd; |
| |
| fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); |
| if (fd == -1) |
| fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)"); |
| for (i = 0; i < sizeof(arpt_tables) / sizeof(arpt_tables[0]); i++) { |
| struct arpt_table_desc* table = &arpt_tables[i]; |
| if (table->info.valid_hooks == 0) |
| continue; |
| memset(&info, 0, sizeof(info)); |
| strcpy(info.name, table->name); |
| optlen = sizeof(info); |
| if (getsockopt(fd, SOL_IP, ARPT_SO_GET_INFO, &info, &optlen)) |
| fail("getsockopt(ARPT_SO_GET_INFO)"); |
| if (memcmp(&table->info, &info, sizeof(table->info)) == 0) { |
| memset(&entries, 0, sizeof(entries)); |
| strcpy(entries.name, table->name); |
| entries.size = table->info.size; |
| optlen = sizeof(entries) - sizeof(entries.entrytable) + entries.size; |
| if (getsockopt(fd, SOL_IP, ARPT_SO_GET_ENTRIES, &entries, &optlen)) |
| fail("getsockopt(ARPT_SO_GET_ENTRIES)"); |
| if (memcmp(table->replace.entrytable, entries.entrytable, |
| table->info.size) == 0) |
| continue; |
| } |
| table->replace.num_counters = info.num_entries; |
| table->replace.counters = counters; |
| optlen = sizeof(table->replace) - sizeof(table->replace.entrytable) + |
| table->replace.size; |
| if (setsockopt(fd, SOL_IP, ARPT_SO_SET_REPLACE, &table->replace, optlen)) |
| fail("setsockopt(ARPT_SO_SET_REPLACE)"); |
| } |
| close(fd); |
| } |
| #include <linux/if.h> |
| #include <linux/netfilter_bridge/ebtables.h> |
| |
| struct ebt_table_desc { |
| const char* name; |
| struct ebt_replace replace; |
| char entrytable[XT_TABLE_SIZE]; |
| }; |
| |
| static struct ebt_table_desc ebt_tables[] = { |
| {.name = "filter"}, {.name = "nat"}, {.name = "broute"}, |
| }; |
| |
| static void checkpoint_ebtables(void) |
| { |
| socklen_t optlen; |
| unsigned i; |
| int fd; |
| |
| fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); |
| if (fd == -1) |
| fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)"); |
| for (i = 0; i < sizeof(ebt_tables) / sizeof(ebt_tables[0]); i++) { |
| struct ebt_table_desc* table = &ebt_tables[i]; |
| strcpy(table->replace.name, table->name); |
| optlen = sizeof(table->replace); |
| if (getsockopt(fd, SOL_IP, EBT_SO_GET_INIT_INFO, &table->replace, |
| &optlen)) { |
| switch (errno) { |
| case EPERM: |
| case ENOENT: |
| case ENOPROTOOPT: |
| continue; |
| } |
| fail("getsockopt(EBT_SO_GET_INIT_INFO)"); |
| } |
| if (table->replace.entries_size > sizeof(table->entrytable)) |
| fail("table size is too large: %u", table->replace.entries_size); |
| table->replace.num_counters = 0; |
| table->replace.entries = table->entrytable; |
| optlen = sizeof(table->replace) + table->replace.entries_size; |
| if (getsockopt(fd, SOL_IP, EBT_SO_GET_INIT_ENTRIES, &table->replace, |
| &optlen)) |
| fail("getsockopt(EBT_SO_GET_INIT_ENTRIES)"); |
| } |
| close(fd); |
| } |
| |
| static void reset_ebtables() |
| { |
| struct ebt_replace replace; |
| char entrytable[XT_TABLE_SIZE]; |
| socklen_t optlen; |
| unsigned i, j, h; |
| int fd; |
| |
| fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); |
| if (fd == -1) |
| fail("socket(AF_INET, SOCK_STREAM, IPPROTO_TCP)"); |
| for (i = 0; i < sizeof(ebt_tables) / sizeof(ebt_tables[0]); i++) { |
| struct ebt_table_desc* table = &ebt_tables[i]; |
| if (table->replace.valid_hooks == 0) |
| continue; |
| memset(&replace, 0, sizeof(replace)); |
| strcpy(replace.name, table->name); |
| optlen = sizeof(replace); |
| if (getsockopt(fd, SOL_IP, EBT_SO_GET_INFO, &replace, &optlen)) |
| fail("getsockopt(EBT_SO_GET_INFO)"); |
| replace.num_counters = 0; |
| 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)) |
| fail("getsockopt(EBT_SO_GET_ENTRIES)"); |
| if (memcmp(table->entrytable, entrytable, replace.entries_size) == 0) |
| continue; |
| } |
| for (j = 0, h = 0; h < NF_BR_NUMHOOKS; h++) { |
| if (table->replace.valid_hooks & (1 << h)) { |
| table->replace.hook_entry[h] = |
| (struct ebt_entries*)table->entrytable + j; |
| j++; |
| } |
| } |
| 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)) |
| fail("setsockopt(EBT_SO_SET_ENTRIES)"); |
| } |
| close(fd); |
| } |
| |
| static void checkpoint_net_namespace(void) |
| { |
| checkpoint_ebtables(); |
| checkpoint_arptables(); |
| checkpoint_iptables(ipv4_tables, sizeof(ipv4_tables) / sizeof(ipv4_tables[0]), |
| AF_INET, SOL_IP); |
| checkpoint_iptables(ipv6_tables, sizeof(ipv6_tables) / sizeof(ipv6_tables[0]), |
| AF_INET6, SOL_IPV6); |
| } |
| |
| static void reset_net_namespace(void) |
| { |
| reset_ebtables(); |
| reset_arptables(); |
| reset_iptables(ipv4_tables, sizeof(ipv4_tables) / sizeof(ipv4_tables[0]), |
| AF_INET, SOL_IP); |
| reset_iptables(ipv6_tables, sizeof(ipv6_tables) / sizeof(ipv6_tables[0]), |
| AF_INET6, SOL_IPV6); |
| } |
| |
| static void remove_dir(const char* dir) |
| { |
| DIR* dp; |
| struct dirent* ep; |
| int iter = 0; |
| retry: |
| while (umount2(dir, MNT_DETACH) == 0) { |
| } |
| dp = opendir(dir); |
| if (dp == NULL) { |
| if (errno == EMFILE) { |
| exitf("opendir(%s) failed due to NOFILE, exiting", dir); |
| } |
| exitf("opendir(%s) failed", dir); |
| } |
| while ((ep = readdir(dp))) { |
| if (strcmp(ep->d_name, ".") == 0 || strcmp(ep->d_name, "..") == 0) |
| continue; |
| char filename[FILENAME_MAX]; |
| snprintf(filename, sizeof(filename), "%s/%s", dir, ep->d_name); |
| struct stat st; |
| if (lstat(filename, &st)) |
| exitf("lstat(%s) failed", filename); |
| if (S_ISDIR(st.st_mode)) { |
| remove_dir(filename); |
| continue; |
| } |
| int i; |
| for (i = 0;; i++) { |
| if (unlink(filename) == 0) |
| break; |
| if (errno == EROFS) { |
| break; |
| } |
| if (errno != EBUSY || i > 100) |
| exitf("unlink(%s) failed", filename); |
| if (umount2(filename, MNT_DETACH)) |
| exitf("umount(%s) failed", filename); |
| } |
| } |
| closedir(dp); |
| int i; |
| for (i = 0;; i++) { |
| if (rmdir(dir) == 0) |
| break; |
| if (i < 100) { |
| if (errno == EROFS) { |
| break; |
| } |
| if (errno == EBUSY) { |
| if (umount2(dir, MNT_DETACH)) |
| exitf("umount(%s) failed", dir); |
| continue; |
| } |
| if (errno == ENOTEMPTY) { |
| if (iter < 100) { |
| iter++; |
| goto retry; |
| } |
| } |
| } |
| exitf("rmdir(%s) failed", dir); |
| } |
| } |
| |
| static void execute_one(); |
| extern unsigned long long procid; |
| |
| static void loop() |
| { |
| checkpoint_net_namespace(); |
| int iter; |
| for (iter = 0;; iter++) { |
| char cwdbuf[32]; |
| sprintf(cwdbuf, "./%d", iter); |
| if (mkdir(cwdbuf, 0777)) |
| fail("failed to mkdir"); |
| int pid = fork(); |
| if (pid < 0) |
| fail("clone failed"); |
| if (pid == 0) { |
| prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0); |
| setpgrp(); |
| if (chdir(cwdbuf)) |
| fail("failed to chdir"); |
| execute_one(); |
| doexit(0); |
| } |
| |
| int status = 0; |
| uint64_t start = current_time_ms(); |
| for (;;) { |
| int res = waitpid(-1, &status, __WALL | WNOHANG); |
| if (res == pid) { |
| break; |
| } |
| usleep(1000); |
| if (current_time_ms() - start < 3 * 1000) |
| continue; |
| kill(-pid, SIGKILL); |
| kill(pid, SIGKILL); |
| while (waitpid(-1, &status, __WALL) != pid) { |
| } |
| break; |
| } |
| remove_dir(cwdbuf); |
| reset_net_namespace(); |
| } |
| } |
| |
| struct thread_t { |
| int created, running, call; |
| pthread_t th; |
| }; |
| |
| static struct thread_t threads[16]; |
| static void execute_call(int call); |
| static int running; |
| static int collide; |
| |
| static void* thr(void* arg) |
| { |
| struct thread_t* th = (struct thread_t*)arg; |
| for (;;) { |
| while (!__atomic_load_n(&th->running, __ATOMIC_ACQUIRE)) |
| syscall(SYS_futex, &th->running, FUTEX_WAIT, 0, 0); |
| execute_call(th->call); |
| __atomic_fetch_sub(&running, 1, __ATOMIC_RELAXED); |
| __atomic_store_n(&th->running, 0, __ATOMIC_RELEASE); |
| syscall(SYS_futex, &th->running, FUTEX_WAKE); |
| } |
| return 0; |
| } |
| |
| static void execute(int num_calls) |
| { |
| int call, thread; |
| running = 0; |
| for (call = 0; call < num_calls; call++) { |
| for (thread = 0; thread < sizeof(threads) / sizeof(threads[0]); thread++) { |
| struct thread_t* th = &threads[thread]; |
| if (!th->created) { |
| th->created = 1; |
| pthread_attr_t attr; |
| pthread_attr_init(&attr); |
| pthread_attr_setstacksize(&attr, 128 << 10); |
| pthread_create(&th->th, &attr, thr, th); |
| } |
| if (!__atomic_load_n(&th->running, __ATOMIC_ACQUIRE)) { |
| th->call = call; |
| __atomic_fetch_add(&running, 1, __ATOMIC_RELAXED); |
| __atomic_store_n(&th->running, 1, __ATOMIC_RELEASE); |
| syscall(SYS_futex, &th->running, FUTEX_WAKE); |
| if (collide && call % 2) |
| break; |
| struct timespec ts; |
| ts.tv_sec = 0; |
| ts.tv_nsec = 20 * 1000 * 1000; |
| syscall(SYS_futex, &th->running, FUTEX_WAIT, 1, &ts); |
| if (running) |
| usleep((call == num_calls - 1) ? 10000 : 1000); |
| break; |
| } |
| } |
| } |
| } |
| |
| uint64_t r[6] = {0xffffffffffffffff, 0xffffffffffffffff, 0xffffffffffffffff, |
| 0xffffffffffffffff, 0xffffffffffffffff, 0x0}; |
| unsigned long long procid; |
| void execute_call(int call) |
| { |
| long res; |
| switch (call) { |
| case 0: |
| NONFAILING(memcpy((void*)0x20000180, "/dev/kvm", 9)); |
| res = syscall(__NR_openat, 0xffffffffffffff9c, 0x20000180, 0, 0); |
| if (res != -1) |
| r[0] = res; |
| break; |
| case 1: |
| res = syscall(__NR_dup, r[0]); |
| if (res != -1) |
| r[1] = res; |
| break; |
| case 2: |
| res = syscall(__NR_ioctl, r[0], 0xae01, 0); |
| if (res != -1) |
| r[2] = res; |
| break; |
| case 3: |
| res = syscall(__NR_ioctl, r[2], 0xae41, 0); |
| if (res != -1) |
| r[3] = res; |
| break; |
| case 4: |
| NONFAILING(*(uint64_t*)0x20000040 = 0x20); |
| NONFAILING(*(uint64_t*)0x20000048 = 0x200000c0); |
| NONFAILING(memcpy( |
| (void*)0x200000c0, |
| "\xea\x00\x28\x00\x00\xb3\x00\x82\xd6\x54\x0f\x30\xea\x03\x00\x00\x00" |
| "\x2c\x00\x66\xb8\x50\x00\x0f\x00\xd0\x66\xba\x42\x00\xb8\x02\x00\x00" |
| "\x00\xef\xc7\x44\x24\x00\x0a\x00\x00\x00\xc7\x44\x24\x02\xac\xc7\x00" |
| "\x00\xc7\x44\x24\x06\x00\x00\x00\x00\x0f\x01\x14\x24\x0f\x20\xe0\x35" |
| "\x10\x00\x00\x00\x0f\x22\xe0\x3e\x64\x36\x0f\x01\xcf\x0f\x22\xc7", |
| 84)); |
| NONFAILING(*(uint64_t*)0x20000050 = 0x54); |
| NONFAILING(*(uint64_t*)0x20000380 = 7); |
| NONFAILING(*(uint64_t*)0x20000388 = 5); |
| syz_kvm_setup_cpu(r[3], r[3], 0x20016000, 0x20000040, 1, 0, 0x20000380, 1); |
| break; |
| case 5: |
| NONFAILING(memcpy((void*)0x20000000, "\x0f\x22", 2)); |
| syscall(__NR_ioctl, -1, 0x4004ae8b, 0x20000000); |
| break; |
| case 6: |
| NONFAILING(memcpy((void*)0x20000080, "./file0", 8)); |
| res = syscall(__NR_openat, r[3], 0x20000080, 0x40000, 0x20); |
| if (res != -1) |
| r[4] = res; |
| break; |
| case 7: |
| syscall(__NR_ioctl, r[4], 0x541b, 0x20000140); |
| break; |
| case 8: |
| NONFAILING(*(uint32_t*)0x20bf7000 = 0); |
| NONFAILING(*(uint32_t*)0x20bf7004 = 0); |
| NONFAILING(*(uint64_t*)0x20bf7008 = 0); |
| NONFAILING(*(uint64_t*)0x20bf7010 = 0x2000); |
| NONFAILING(*(uint64_t*)0x20bf7018 = 0x20000000); |
| syscall(__NR_ioctl, r[2], 0x4020ae46, 0x20bf7000); |
| break; |
| case 9: |
| NONFAILING(*(uint32_t*)0x200001c0 = 0); |
| NONFAILING(*(uint16_t*)0x200001c8 = 2); |
| NONFAILING(*(uint16_t*)0x200001ca = htobe16(0x4e22)); |
| NONFAILING(*(uint32_t*)0x200001cc = htobe32(0)); |
| NONFAILING(*(uint8_t*)0x200001d0 = 0); |
| NONFAILING(*(uint8_t*)0x200001d1 = 0); |
| NONFAILING(*(uint8_t*)0x200001d2 = 0); |
| NONFAILING(*(uint8_t*)0x200001d3 = 0); |
| NONFAILING(*(uint8_t*)0x200001d4 = 0); |
| NONFAILING(*(uint8_t*)0x200001d5 = 0); |
| NONFAILING(*(uint8_t*)0x200001d6 = 0); |
| NONFAILING(*(uint8_t*)0x200001d7 = 0); |
| NONFAILING(*(uint64_t*)0x20000248 = 1); |
| NONFAILING(*(uint64_t*)0x20000250 = 6); |
| NONFAILING(*(uint64_t*)0x20000258 = 5); |
| NONFAILING(*(uint64_t*)0x20000260 = 1); |
| NONFAILING(*(uint64_t*)0x20000268 = 4); |
| NONFAILING(*(uint64_t*)0x20000270 = 3); |
| NONFAILING(*(uint64_t*)0x20000278 = 0x987); |
| NONFAILING(*(uint64_t*)0x20000280 = 0x3ff); |
| NONFAILING(*(uint64_t*)0x20000288 = 0x3f); |
| NONFAILING(*(uint64_t*)0x20000290 = 0x101); |
| NONFAILING(*(uint64_t*)0x20000298 = 1); |
| NONFAILING(*(uint64_t*)0x200002a0 = 6); |
| NONFAILING(*(uint64_t*)0x200002a8 = 0x10000); |
| NONFAILING(*(uint64_t*)0x200002b0 = 9); |
| NONFAILING(*(uint64_t*)0x200002b8 = 7); |
| NONFAILING(*(uint32_t*)0x200002c0 = 0x100); |
| res = syscall(__NR_getsockopt, r[4], 0x84, 0x70, 0x200001c0, 0x200002c0); |
| if (res != -1) |
| NONFAILING(r[5] = *(uint32_t*)0x200001c0); |
| break; |
| case 10: |
| NONFAILING(*(uint32_t*)0x20000300 = r[5]); |
| NONFAILING(*(uint32_t*)0x20000304 = 1); |
| syscall(__NR_setsockopt, r[4], 0x84, 0x75, 0x20000300, 8); |
| break; |
| case 11: |
| NONFAILING(memcpy( |
| (void*)0x200003c0, |
| "\x65\xa4\x2d\x88\x05\x69\xbd\x05\x5f\x56\xa4\xec\xea\x7c\x51\x21\x12" |
| "\x8b\x1a\xd8\x4e\xda\xb5\x67\x66\xce\x33\x04\xeb\x69\x42\x63\xc6\x06" |
| "\x10\xad\xf9\xa8\x62\xcc\x66\x0f\x7b\xf6\xc6\xc9\xa1\xb4\x6f\xa5\xc5" |
| "\x71\x64\x2d\xfe\x9f\x45\xa5\x19\xea\xee\x67\x8a\xb1\x72\x87\x18\xe7" |
| "\x5a\xd9\xbe\x2b\x5f\x78\x5e\xd8\x87\x7b\xdf\x7d\xca\x30\x6e\x2b\x8f" |
| "\x23\x1a\xa8\x3a\xea\x66\xcf\x39\xa0\x18\x58\xf4\xe7\x4b\x99\x24\x30" |
| "\xb2\xff\xcb\x73\x4d\xeb\x23\xd4\x66\x7b\x67\x66\xc4\xa0\x4f\x2e\x87" |
| "\xea\x81\xe2\xc4\x79\x34\x75\xd1\xed\xd4\xfc\x78\x18\xa5\xa4\xf1\x8b" |
| "\x7f\xa6\x8e\x11\x9a\x52\x21\x1f\xb4\x17\x57\xc9\x0f\x05\x17\x06\x67" |
| "\xc9\xa9\x72\x59\x33\x41\xa0\xa1\x62\xc0\x12\x0e\x5a\x93\x2d\x47\x2f" |
| "\x7e\x99\x9b\xfc\x5b\x58\xdd\xa1\xfc\x35\x80\x62\x36\x0d\xfa\x0c\x0f" |
| "\x8f\x2c\x97\xa9\xd0\x33\x16\x52\x9e\xbc\x83\x00\x16\x00\xf2\x44\x1a" |
| "\xb6\x20\x11\x79\x6a\x5e\x9a\xf4\xe0\x95\xaa\xef\xdc\xf5\x65\xbc\x17" |
| "\xa9\x15\x16\xc5\xd1\xb2\x64\x53\xfb\xa7\x74\x14\x25\x99\x48\xa4\x3c" |
| "\xe4\x22\xf5\x4f\x65\x92\xf4\xd8\xfb\x39\xc4\x98", |
| 250)); |
| syscall(__NR_setsockopt, r[1], 6, 0x1c, 0x200003c0, 0xfa); |
| break; |
| case 12: |
| syscall(__NR_ioctl, r[3], 0xae80, 0); |
| break; |
| case 13: |
| NONFAILING(*(uint32_t*)0x200004c0 = 0); |
| NONFAILING(*(uint32_t*)0x200004c4 = 0x80000000); |
| NONFAILING(*(uint32_t*)0x200004c8 = 3); |
| NONFAILING(*(uint32_t*)0x200004cc = 6); |
| syscall(__NR_setsockopt, r[4], 0x107, 0xd, 0x200004c0, 0x10); |
| break; |
| } |
| } |
| |
| void execute_one() |
| { |
| execute(14); |
| collide = 1; |
| execute(14); |
| } |
| |
| int main() |
| { |
| syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0); |
| char* cwd = get_current_dir_name(); |
| for (procid = 0; procid < 8; procid++) { |
| if (fork() == 0) { |
| install_segv_handler(); |
| for (;;) { |
| if (chdir(cwd)) |
| fail("failed to chdir"); |
| use_temporary_dir(); |
| loop(); |
| } |
| } |
| } |
| sleep(1000000); |
| return 0; |
| } |
