WARNING: zero-size vmalloc in sel_write_load

WARNING: zero-size vmalloc in sel_write_load

[Ubisectech Sirius]

[-- Attachment #1: Type: text/plain, Size: 2610 bytes --]

Hello.
We are Ubisectech Sirius Team, the vulnerability lab of China ValiantSec. Recently, our team has discovered a issue in Linux kernel 6.8. Attached to the email were a PoC file of the issue.

Stack dump:

------------[ cut here ]------------
WARNING: CPU: 1 PID: 13730 at mm/vmalloc.c:3247 __vmalloc_node_range+0x10a4/0x1490 mm/vmalloc.c:3247
Modules linked in:
CPU: 1 PID: 13730 Comm: syz.2.627 Not tainted 6.8.0 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
RIP: 0010:__vmalloc_node_range+0x10a4/0x1490 mm/vmalloc.c:3247
Code: 25 28 00 00 00 0f 85 9f 02 00 00 48 81 c4 70 01 00 00 4c 89 e0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc e8 ad e2 b4 ff 90 <0f> 0b 90 45 31 e4 eb 9d e8 9f e2 b4 ff 48 8b 4c 24 40 31 f6 45 31
RSP: 0018:ffffc90001847978 EFLAGS: 00010212
RAX: 00000000000018a9 RBX: dffffc0000000000 RCX: ffffc9000bb89000
RDX: 0000000000040000 RSI: ffffffff81d5ca03 RDI: 0000000000000007
RBP: 0000000000000000 R08: 0000000000000007 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000001 R12: ffff888000deeb48
R13: dffffc0000000000 R14: 0000000000000000 R15: 1ffff92000308faf
FS:  00007f7457ffb640(0000) GS:ffff88807ec00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 000000001ef56000 CR4: 0000000000750ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <TASK>
 __vmalloc_node mm/vmalloc.c:3385 [inline]
 vmalloc+0x6b/0x90 mm/vmalloc.c:3418
 sel_write_load+0x286/0x1b60 security/selinux/selinuxfs.c:592
 vfs_write+0x2b2/0x1090 fs/read_write.c:588
 ksys_write+0x122/0x250 fs/read_write.c:643
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xd5/0x270 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x6f/0x77
RIP: 0033:0x7f74571958cd
Code: 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f7457ffafa8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007f7457333f60 RCX: 00007f74571958cd
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00007f745721bb06 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007f7457333f60 R15: 00007f7457fdb000
 </TASK>

Thank you for taking the time to read this email and we look forward to working with you further.

[-- Attachment #2: poc.c --]
[-- Type: application/octet-stream, Size: 8207 bytes --]

// autogenerated by syzkaller (https://github.com/google/syzkaller)

#define _GNU_SOURCE

#include <dirent.h>
#include <endian.h>
#include <errno.h>
#include <fcntl.h>
#include <sched.h>
#include <signal.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mount.h>
#include <sys/prctl.h>
#include <sys/resource.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <time.h>
#include <unistd.h>

#include <linux/capability.h>

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 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 MAX_FDS 30

static void sandbox_common_mount_tmpfs(void)
{
  write_file("/proc/sys/fs/mount-max", "100000");
  if (mkdir("./syz-tmp", 0777))
    exit(1);
  if (mount("", "./syz-tmp", "tmpfs", 0, NULL))
    exit(1);
  if (mkdir("./syz-tmp/newroot", 0777))
    exit(1);
  if (mkdir("./syz-tmp/newroot/dev", 0700))
    exit(1);
  unsigned bind_mount_flags = MS_BIND | MS_REC | MS_PRIVATE;
  if (mount("/dev", "./syz-tmp/newroot/dev", NULL, bind_mount_flags, NULL))
    exit(1);
  if (mkdir("./syz-tmp/newroot/proc", 0700))
    exit(1);
  if (mount("syz-proc", "./syz-tmp/newroot/proc", "proc", 0, NULL))
    exit(1);
  if (mkdir("./syz-tmp/newroot/selinux", 0700))
    exit(1);
  const char* selinux_path = "./syz-tmp/newroot/selinux";
  if (mount("/selinux", selinux_path, NULL, bind_mount_flags, NULL)) {
    if (errno != ENOENT)
      exit(1);
    if (mount("/sys/fs/selinux", selinux_path, NULL, bind_mount_flags, NULL) &&
        errno != ENOENT)
      exit(1);
  }
  if (mkdir("./syz-tmp/newroot/sys", 0700))
    exit(1);
  if (mount("/sys", "./syz-tmp/newroot/sys", 0, bind_mount_flags, NULL))
    exit(1);
  if (mkdir("./syz-tmp/pivot", 0777))
    exit(1);
  if (syscall(SYS_pivot_root, "./syz-tmp", "./syz-tmp/pivot")) {
    if (chdir("./syz-tmp"))
      exit(1);
  } else {
    if (chdir("/"))
      exit(1);
    if (umount2("./pivot", MNT_DETACH))
      exit(1);
  }
  if (chroot("./newroot"))
    exit(1);
  if (chdir("/"))
    exit(1);
}

static void setup_common()
{
  if (mount(0, "/sys/fs/fuse/connections", "fusectl", 0, 0)) {
  }
}

static void setup_binderfs()
{
  if (mkdir("/dev/binderfs", 0777)) {
  }
  if (mount("binder", "/dev/binderfs", "binder", 0, NULL)) {
  }
  if (symlink("/dev/binderfs", "./binderfs")) {
  }
}

static void loop();

static void sandbox_common()
{
  prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
  setsid();
  struct rlimit rlim;
  rlim.rlim_cur = rlim.rlim_max = (200 << 20);
  setrlimit(RLIMIT_AS, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 32 << 20;
  setrlimit(RLIMIT_MEMLOCK, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 136 << 20;
  setrlimit(RLIMIT_FSIZE, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 1 << 20;
  setrlimit(RLIMIT_STACK, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 128 << 20;
  setrlimit(RLIMIT_CORE, &rlim);
  rlim.rlim_cur = rlim.rlim_max = 256;
  setrlimit(RLIMIT_NOFILE, &rlim);
  if (unshare(CLONE_NEWNS)) {
  }
  if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL)) {
  }
  if (unshare(CLONE_NEWIPC)) {
  }
  if (unshare(0x02000000)) {
  }
  if (unshare(CLONE_NEWUTS)) {
  }
  if (unshare(CLONE_SYSVSEM)) {
  }
  typedef struct {
    const char* name;
    const char* value;
  } sysctl_t;
  static const sysctl_t sysctls[] = {
      {"/proc/sys/kernel/shmmax", "16777216"},
      {"/proc/sys/kernel/shmall", "536870912"},
      {"/proc/sys/kernel/shmmni", "1024"},
      {"/proc/sys/kernel/msgmax", "8192"},
      {"/proc/sys/kernel/msgmni", "1024"},
      {"/proc/sys/kernel/msgmnb", "1024"},
      {"/proc/sys/kernel/sem", "1024 1048576 500 1024"},
  };
  unsigned i;
  for (i = 0; i < sizeof(sysctls) / sizeof(sysctls[0]); i++)
    write_file(sysctls[i].name, sysctls[i].value);
}

static int wait_for_loop(int pid)
{
  if (pid < 0)
    exit(1);
  int status = 0;
  while (waitpid(-1, &status, __WALL) != pid) {
  }
  return WEXITSTATUS(status);
}

static void drop_caps(void)
{
  struct __user_cap_header_struct cap_hdr = {};
  struct __user_cap_data_struct cap_data[2] = {};
  cap_hdr.version = _LINUX_CAPABILITY_VERSION_3;
  cap_hdr.pid = getpid();
  if (syscall(SYS_capget, &cap_hdr, &cap_data))
    exit(1);
  const int drop = (1 << CAP_SYS_PTRACE) | (1 << CAP_SYS_NICE);
  cap_data[0].effective &= ~drop;
  cap_data[0].permitted &= ~drop;
  cap_data[0].inheritable &= ~drop;
  if (syscall(SYS_capset, &cap_hdr, &cap_data))
    exit(1);
}

static int do_sandbox_none(void)
{
  if (unshare(CLONE_NEWPID)) {
  }
  int pid = fork();
  if (pid != 0)
    return wait_for_loop(pid);
  setup_common();
  sandbox_common();
  drop_caps();
  if (unshare(CLONE_NEWNET)) {
  }
  write_file("/proc/sys/net/ipv4/ping_group_range", "0 65535");
  sandbox_common_mount_tmpfs();
  setup_binderfs();
  loop();
  exit(1);
}

static void kill_and_wait(int pid, int* status)
{
  kill(-pid, SIGKILL);
  kill(pid, SIGKILL);
  for (int i = 0; i < 100; i++) {
    if (waitpid(-1, status, WNOHANG | __WALL) == pid)
      return;
    usleep(1000);
  }
  DIR* dir = opendir("/sys/fs/fuse/connections");
  if (dir) {
    for (;;) {
      struct dirent* ent = readdir(dir);
      if (!ent)
        break;
      if (strcmp(ent->d_name, ".") == 0 || strcmp(ent->d_name, "..") == 0)
        continue;
      char abort[300];
      snprintf(abort, sizeof(abort), "/sys/fs/fuse/connections/%s/abort",
               ent->d_name);
      int fd = open(abort, O_WRONLY);
      if (fd == -1) {
        continue;
      }
      if (write(fd, abort, 1) < 0) {
      }
      close(fd);
    }
    closedir(dir);
  } else {
  }
  while (waitpid(-1, status, __WALL) != pid) {
  }
}

static void setup_test()
{
  prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
  setpgrp();
  write_file("/proc/self/oom_score_adj", "1000");
}

static void close_fds()
{
  for (int fd = 3; fd < MAX_FDS; fd++)
    close(fd);
}

static void execute_one(void);

#define WAIT_FLAGS __WALL

static void loop(void)
{
  int iter = 0;
  for (;; iter++) {
    int pid = fork();
    if (pid < 0)
      exit(1);
    if (pid == 0) {
      setup_test();
      execute_one();
      close_fds();
      exit(0);
    }
    int status = 0;
    uint64_t start = current_time_ms();
    for (;;) {
      sleep_ms(10);
      if (waitpid(-1, &status, WNOHANG | WAIT_FLAGS) == pid)
        break;
      if (current_time_ms() - start < 5000)
        continue;
      kill_and_wait(pid, &status);
      break;
    }
  }
}

uint64_t r[1] = {0xffffffffffffffff};

void execute_one(void)
{
  intptr_t res = 0;
  if (write(1, "executing program\n", sizeof("executing program\n") - 1)) {
  }
  memcpy((void*)0x20000300, "/selinux/load\000", 14);
  res = syscall(__NR_openat, /*fd=*/0xffffffffffffff9cul, /*file=*/0x20000300ul,
                /*flags=*/2ul, /*mode=*/0ul);
  if (res != -1)
    r[0] = res;
  syscall(__NR_write, /*fd=*/r[0], /*buf=*/0ul, /*count=*/0ul);
}
int main(void)
{
  syscall(__NR_mmap, /*addr=*/0x1ffff000ul, /*len=*/0x1000ul, /*prot=*/0ul,
          /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
          /*offset=*/0ul);
  syscall(__NR_mmap, /*addr=*/0x20000000ul, /*len=*/0x1000000ul,
          /*prot=PROT_WRITE|PROT_READ|PROT_EXEC*/ 7ul,
          /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
          /*offset=*/0ul);
  syscall(__NR_mmap, /*addr=*/0x21000000ul, /*len=*/0x1000ul, /*prot=*/0ul,
          /*flags=MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE*/ 0x32ul, /*fd=*/-1,
          /*offset=*/0ul);
  const char* reason;
  (void)reason;
  do_sandbox_none();
  return 0;
}

Re: WARNING: zero-size vmalloc in sel_write_load

[Paul Moore]

On Sun, Jul 28, 2024 at 11:15 PM Ubisectech Sirius
<bugreport@valiantsec.com> wrote:
>
> Hello.
> We are Ubisectech Sirius Team, the vulnerability lab of China ValiantSec. Recently, our team has discovered a issue in Linux kernel 6.8. Attached to the email were a PoC file of the issue.
>
> Stack dump:
>
> ------------[ cut here ]------------
> WARNING: CPU: 1 PID: 13730 at mm/vmalloc.c:3247 __vmalloc_node_range+0x10a4/0x1490 mm/vmalloc.c:3247
> Modules linked in:
> CPU: 1 PID: 13730 Comm: syz.2.627 Not tainted 6.8.0 #1
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
> RIP: 0010:__vmalloc_node_range+0x10a4/0x1490 mm/vmalloc.c:3247
> Code: 25 28 00 00 00 0f 85 9f 02 00 00 48 81 c4 70 01 00 00 4c 89 e0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc e8 ad e2 b4 ff 90 <0f> 0b 90 45 31 e4 eb 9d e8 9f e2 b4 ff 48 8b 4c 24 40 31 f6 45 31
> RSP: 0018:ffffc90001847978 EFLAGS: 00010212
> RAX: 00000000000018a9 RBX: dffffc0000000000 RCX: ffffc9000bb89000
> RDX: 0000000000040000 RSI: ffffffff81d5ca03 RDI: 0000000000000007
> RBP: 0000000000000000 R08: 0000000000000007 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000001 R12: ffff888000deeb48
> R13: dffffc0000000000 R14: 0000000000000000 R15: 1ffff92000308faf
> FS:  00007f7457ffb640(0000) GS:ffff88807ec00000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 0000000000000000 CR3: 000000001ef56000 CR4: 0000000000750ef0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> PKRU: 55555554
> Call Trace:
>  <TASK>
>  __vmalloc_node mm/vmalloc.c:3385 [inline]
>  vmalloc+0x6b/0x90 mm/vmalloc.c:3418
>  sel_write_load+0x286/0x1b60 security/selinux/selinuxfs.c:592
>  vfs_write+0x2b2/0x1090 fs/read_write.c:588
>  ksys_write+0x122/0x250 fs/read_write.c:643
>  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
>  do_syscall_64+0xd5/0x270 arch/x86/entry/common.c:83
>  entry_SYSCALL_64_after_hwframe+0x6f/0x77
> RIP: 0033:0x7f74571958cd
> Code: 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
> RSP: 002b:00007f7457ffafa8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
> RAX: ffffffffffffffda RBX: 00007f7457333f60 RCX: 00007f74571958cd
> RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
> RBP: 00007f745721bb06 R08: 0000000000000000 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
> R13: 000000000000000b R14: 00007f7457333f60 R15: 00007f7457fdb000
>  </TASK>
>
> Thank you for taking the time to read this email and we look forward to working with you further.

Similar to your other report, this warning/panic appears to be the
result of attempting to load a bogus SELinux policy with panic_on_warn
enabled, and similar to the other report I would expect the system to
gracefully fail to load the bogus/empty policy in those cases where
panic_on_warn is disabled.  Have you noticed any unexpected behavior
with panic_on_warn disabled?

-- 
paul-moore.com