2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 05:04:00 +08:00
linux-next/fs/f2fs/inode.c
Chao Yu 76d56d4ab4 f2fs: fix to do sanity check with extra_attr feature
If FI_EXTRA_ATTR is set in inode by fuzzing, inode.i_addr[0] will be
parsed as inode.i_extra_isize, then in __recover_inline_status, inline
data address will beyond boundary of page, result in accessing invalid
memory.

So in this condition, during reading inode page, let's do sanity check
with EXTRA_ATTR feature of fs and extra_attr bit of inode, if they're
inconsistent, deny to load this inode.

- Overview
Out-of-bound access in f2fs_iget() when mounting a corrupted f2fs image

- Reproduce

The following message will be got in KASAN build of 4.18 upstream kernel.
[  819.392227] ==================================================================
[  819.393901] BUG: KASAN: slab-out-of-bounds in f2fs_iget+0x736/0x1530
[  819.395329] Read of size 4 at addr ffff8801f099c968 by task mount/1292

[  819.397079] CPU: 1 PID: 1292 Comm: mount Not tainted 4.18.0-rc1+ #4
[  819.397082] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
[  819.397088] Call Trace:
[  819.397124]  dump_stack+0x7b/0xb5
[  819.397154]  print_address_description+0x70/0x290
[  819.397159]  kasan_report+0x291/0x390
[  819.397163]  ? f2fs_iget+0x736/0x1530
[  819.397176]  check_memory_region+0x139/0x190
[  819.397182]  __asan_loadN+0xf/0x20
[  819.397185]  f2fs_iget+0x736/0x1530
[  819.397197]  f2fs_fill_super+0x1b4f/0x2b40
[  819.397202]  ? f2fs_fill_super+0x1b4f/0x2b40
[  819.397208]  ? f2fs_commit_super+0x1b0/0x1b0
[  819.397227]  ? set_blocksize+0x90/0x140
[  819.397241]  mount_bdev+0x1c5/0x210
[  819.397245]  ? f2fs_commit_super+0x1b0/0x1b0
[  819.397252]  f2fs_mount+0x15/0x20
[  819.397256]  mount_fs+0x60/0x1a0
[  819.397267]  ? alloc_vfsmnt+0x309/0x360
[  819.397272]  vfs_kern_mount+0x6b/0x1a0
[  819.397282]  do_mount+0x34a/0x18c0
[  819.397300]  ? lockref_put_or_lock+0xcf/0x160
[  819.397306]  ? copy_mount_string+0x20/0x20
[  819.397318]  ? memcg_kmem_put_cache+0x1b/0xa0
[  819.397324]  ? kasan_check_write+0x14/0x20
[  819.397334]  ? _copy_from_user+0x6a/0x90
[  819.397353]  ? memdup_user+0x42/0x60
[  819.397359]  ksys_mount+0x83/0xd0
[  819.397365]  __x64_sys_mount+0x67/0x80
[  819.397388]  do_syscall_64+0x78/0x170
[  819.397403]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  819.397422] RIP: 0033:0x7f54c667cb9a
[  819.397424] Code: 48 8b 0d 01 c3 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ce c2 2b 00 f7 d8 64 89 01 48
[  819.397483] RSP: 002b:00007ffd8f46cd08 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5
[  819.397496] RAX: ffffffffffffffda RBX: 0000000000dfa030 RCX: 00007f54c667cb9a
[  819.397498] RDX: 0000000000dfa210 RSI: 0000000000dfbf30 RDI: 0000000000e02ec0
[  819.397501] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000013
[  819.397503] R10: 00000000c0ed0000 R11: 0000000000000202 R12: 0000000000e02ec0
[  819.397505] R13: 0000000000dfa210 R14: 0000000000000000 R15: 0000000000000003

[  819.397866] Allocated by task 139:
[  819.398702]  save_stack+0x46/0xd0
[  819.398705]  kasan_kmalloc+0xad/0xe0
[  819.398709]  kasan_slab_alloc+0x11/0x20
[  819.398713]  kmem_cache_alloc+0xd1/0x1e0
[  819.398717]  dup_fd+0x50/0x4c0
[  819.398740]  copy_process.part.37+0xbed/0x32e0
[  819.398744]  _do_fork+0x16e/0x590
[  819.398748]  __x64_sys_clone+0x69/0x80
[  819.398752]  do_syscall_64+0x78/0x170
[  819.398756]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

[  819.399097] Freed by task 159:
[  819.399743]  save_stack+0x46/0xd0
[  819.399747]  __kasan_slab_free+0x13c/0x1a0
[  819.399750]  kasan_slab_free+0xe/0x10
[  819.399754]  kmem_cache_free+0x89/0x1e0
[  819.399757]  put_files_struct+0x132/0x150
[  819.399761]  exit_files+0x62/0x70
[  819.399766]  do_exit+0x47b/0x1390
[  819.399770]  do_group_exit+0x86/0x130
[  819.399774]  __x64_sys_exit_group+0x2c/0x30
[  819.399778]  do_syscall_64+0x78/0x170
[  819.399782]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

[  819.400115] The buggy address belongs to the object at ffff8801f099c680
                which belongs to the cache files_cache of size 704
[  819.403234] The buggy address is located 40 bytes to the right of
                704-byte region [ffff8801f099c680, ffff8801f099c940)
[  819.405689] The buggy address belongs to the page:
[  819.406709] page:ffffea0007c26700 count:1 mapcount:0 mapping:ffff8801f69a3340 index:0xffff8801f099d380 compound_mapcount: 0
[  819.408984] flags: 0x2ffff0000008100(slab|head)
[  819.409932] raw: 02ffff0000008100 ffffea00077fb600 0000000200000002 ffff8801f69a3340
[  819.411514] raw: ffff8801f099d380 0000000080130000 00000001ffffffff 0000000000000000
[  819.413073] page dumped because: kasan: bad access detected

[  819.414539] Memory state around the buggy address:
[  819.415521]  ffff8801f099c800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  819.416981]  ffff8801f099c880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  819.418454] >ffff8801f099c900: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
[  819.419921]                                                           ^
[  819.421265]  ffff8801f099c980: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
[  819.422745]  ffff8801f099ca00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  819.424206] ==================================================================
[  819.425668] Disabling lock debugging due to kernel taint
[  819.457463] F2FS-fs (loop0): Mounted with checkpoint version = 3

The kernel still mounts the image. If you run the following program on the mounted folder mnt,

(poc.c)

static void activity(char *mpoint) {

  char *foo_bar_baz;
  int err;

  static int buf[8192];
  memset(buf, 0, sizeof(buf));

  err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint);
    int fd = open(foo_bar_baz, O_RDONLY, 0);
  if (fd >= 0) {
      read(fd, (char *)buf, 11);
      close(fd);
  }
}

int main(int argc, char *argv[]) {
  activity(argv[1]);
  return 0;
}

You can get kernel crash:
[  819.457463] F2FS-fs (loop0): Mounted with checkpoint version = 3
[  918.028501] BUG: unable to handle kernel paging request at ffffed0048000d82
[  918.044020] PGD 23ffee067 P4D 23ffee067 PUD 23fbef067 PMD 0
[  918.045207] Oops: 0000 [#1] SMP KASAN PTI
[  918.046048] CPU: 0 PID: 1309 Comm: poc Tainted: G    B             4.18.0-rc1+ #4
[  918.047573] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
[  918.049552] RIP: 0010:check_memory_region+0x5e/0x190
[  918.050565] Code: f8 49 c1 e8 03 49 89 db 49 c1 eb 03 4d 01 cb 4d 01 c1 4d 8d 63 01 4c 89 c8 4d 89 e2 4d 29 ca 49 83 fa 10 7f 3d 4d 85 d2 74 32 <41> 80 39 00 75 23 48 b8 01 00 00 00 00 fc ff df 4d 01 d1 49 01 c0
[  918.054322] RSP: 0018:ffff8801e3a1f258 EFLAGS: 00010202
[  918.055400] RAX: ffffed0048000d82 RBX: ffff880240006c11 RCX: ffffffffb8867d14
[  918.056832] RDX: 0000000000000000 RSI: 0000000000000002 RDI: ffff880240006c10
[  918.058253] RBP: ffff8801e3a1f268 R08: 1ffff10048000d82 R09: ffffed0048000d82
[  918.059717] R10: 0000000000000001 R11: ffffed0048000d82 R12: ffffed0048000d83
[  918.061159] R13: ffff8801e3a1f390 R14: 0000000000000000 R15: ffff880240006c08
[  918.062614] FS:  00007fac9732c700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000
[  918.064246] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  918.065412] CR2: ffffed0048000d82 CR3: 00000001df77a000 CR4: 00000000000006f0
[  918.066882] Call Trace:
[  918.067410]  __asan_loadN+0xf/0x20
[  918.068149]  f2fs_find_target_dentry+0xf4/0x270
[  918.069083]  ? __get_node_page+0x331/0x5b0
[  918.069925]  f2fs_find_in_inline_dir+0x24b/0x310
[  918.070881]  ? f2fs_recover_inline_data+0x4c0/0x4c0
[  918.071905]  ? unwind_next_frame.part.5+0x34f/0x490
[  918.072901]  ? unwind_dump+0x290/0x290
[  918.073695]  ? is_bpf_text_address+0xe/0x20
[  918.074566]  __f2fs_find_entry+0x599/0x670
[  918.075408]  ? kasan_unpoison_shadow+0x36/0x50
[  918.076315]  ? kasan_kmalloc+0xad/0xe0
[  918.077100]  ? memcg_kmem_put_cache+0x55/0xa0
[  918.077998]  ? f2fs_find_target_dentry+0x270/0x270
[  918.079006]  ? d_set_d_op+0x30/0x100
[  918.079749]  ? __d_lookup_rcu+0x69/0x2e0
[  918.080556]  ? __d_alloc+0x275/0x450
[  918.081297]  ? kasan_check_write+0x14/0x20
[  918.082135]  ? memset+0x31/0x40
[  918.082820]  ? fscrypt_setup_filename+0x1ec/0x4c0
[  918.083782]  ? d_alloc_parallel+0x5bb/0x8c0
[  918.084640]  f2fs_find_entry+0xe9/0x110
[  918.085432]  ? __f2fs_find_entry+0x670/0x670
[  918.086308]  ? kasan_check_write+0x14/0x20
[  918.087163]  f2fs_lookup+0x297/0x590
[  918.087902]  ? f2fs_link+0x2b0/0x2b0
[  918.088646]  ? legitimize_path.isra.29+0x61/0xa0
[  918.089589]  __lookup_slow+0x12e/0x240
[  918.090371]  ? may_delete+0x2b0/0x2b0
[  918.091123]  ? __nd_alloc_stack+0xa0/0xa0
[  918.091944]  lookup_slow+0x44/0x60
[  918.092642]  walk_component+0x3ee/0xa40
[  918.093428]  ? is_bpf_text_address+0xe/0x20
[  918.094283]  ? pick_link+0x3e0/0x3e0
[  918.095047]  ? in_group_p+0xa5/0xe0
[  918.095771]  ? generic_permission+0x53/0x1e0
[  918.096666]  ? security_inode_permission+0x1d/0x70
[  918.097646]  ? inode_permission+0x7a/0x1f0
[  918.098497]  link_path_walk+0x2a2/0x7b0
[  918.099298]  ? apparmor_capget+0x3d0/0x3d0
[  918.100140]  ? walk_component+0xa40/0xa40
[  918.100958]  ? path_init+0x2e6/0x580
[  918.101695]  path_openat+0x1bb/0x2160
[  918.102471]  ? __save_stack_trace+0x92/0x100
[  918.103352]  ? save_stack+0xb5/0xd0
[  918.104070]  ? vfs_unlink+0x250/0x250
[  918.104822]  ? save_stack+0x46/0xd0
[  918.105538]  ? kasan_slab_alloc+0x11/0x20
[  918.106370]  ? kmem_cache_alloc+0xd1/0x1e0
[  918.107213]  ? getname_flags+0x76/0x2c0
[  918.107997]  ? getname+0x12/0x20
[  918.108677]  ? do_sys_open+0x14b/0x2c0
[  918.109450]  ? __x64_sys_open+0x4c/0x60
[  918.110255]  ? do_syscall_64+0x78/0x170
[  918.111083]  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  918.112148]  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  918.113204]  ? f2fs_empty_inline_dir+0x1e0/0x1e0
[  918.114150]  ? timespec64_trunc+0x5c/0x90
[  918.114993]  ? wb_io_lists_depopulated+0x1a/0xc0
[  918.115937]  ? inode_io_list_move_locked+0x102/0x110
[  918.116949]  do_filp_open+0x12b/0x1d0
[  918.117709]  ? may_open_dev+0x50/0x50
[  918.118475]  ? kasan_kmalloc+0xad/0xe0
[  918.119246]  do_sys_open+0x17c/0x2c0
[  918.119983]  ? do_sys_open+0x17c/0x2c0
[  918.120751]  ? filp_open+0x60/0x60
[  918.121463]  ? task_work_run+0x4d/0xf0
[  918.122237]  __x64_sys_open+0x4c/0x60
[  918.123001]  do_syscall_64+0x78/0x170
[  918.123759]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  918.124802] RIP: 0033:0x7fac96e3e040
[  918.125537] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 09 27 2d 00 00 75 10 b8 02 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 7e e0 01 00 48 89 04 24
[  918.129341] RSP: 002b:00007fff1b37f848 EFLAGS: 00000246 ORIG_RAX: 0000000000000002
[  918.130870] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fac96e3e040
[  918.132295] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000122d080
[  918.133748] RBP: 00007fff1b37f9b0 R08: 00007fac9710bbd8 R09: 0000000000000001
[  918.135209] R10: 000000000000069d R11: 0000000000000246 R12: 0000000000400c20
[  918.136650] R13: 00007fff1b37fab0 R14: 0000000000000000 R15: 0000000000000000
[  918.138093] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy
[  918.147924] CR2: ffffed0048000d82
[  918.148619] ---[ end trace 4ce02f25ff7d3df5 ]---
[  918.149563] RIP: 0010:check_memory_region+0x5e/0x190
[  918.150576] Code: f8 49 c1 e8 03 49 89 db 49 c1 eb 03 4d 01 cb 4d 01 c1 4d 8d 63 01 4c 89 c8 4d 89 e2 4d 29 ca 49 83 fa 10 7f 3d 4d 85 d2 74 32 <41> 80 39 00 75 23 48 b8 01 00 00 00 00 fc ff df 4d 01 d1 49 01 c0
[  918.154360] RSP: 0018:ffff8801e3a1f258 EFLAGS: 00010202
[  918.155411] RAX: ffffed0048000d82 RBX: ffff880240006c11 RCX: ffffffffb8867d14
[  918.156833] RDX: 0000000000000000 RSI: 0000000000000002 RDI: ffff880240006c10
[  918.158257] RBP: ffff8801e3a1f268 R08: 1ffff10048000d82 R09: ffffed0048000d82
[  918.159722] R10: 0000000000000001 R11: ffffed0048000d82 R12: ffffed0048000d83
[  918.161149] R13: ffff8801e3a1f390 R14: 0000000000000000 R15: ffff880240006c08
[  918.162587] FS:  00007fac9732c700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000
[  918.164203] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  918.165356] CR2: ffffed0048000d82 CR3: 00000001df77a000 CR4: 00000000000006f0

Reported-by: Wen Xu <wen.xu@gatech.edu>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-07-27 18:03:59 +09:00

695 lines
19 KiB
C

/*
* fs/f2fs/inode.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/buffer_head.h>
#include <linux/backing-dev.h>
#include <linux/writeback.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include <trace/events/f2fs.h>
void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
{
if (is_inode_flag_set(inode, FI_NEW_INODE))
return;
if (f2fs_inode_dirtied(inode, sync))
return;
mark_inode_dirty_sync(inode);
}
void f2fs_set_inode_flags(struct inode *inode)
{
unsigned int flags = F2FS_I(inode)->i_flags;
unsigned int new_fl = 0;
if (flags & F2FS_SYNC_FL)
new_fl |= S_SYNC;
if (flags & F2FS_APPEND_FL)
new_fl |= S_APPEND;
if (flags & F2FS_IMMUTABLE_FL)
new_fl |= S_IMMUTABLE;
if (flags & F2FS_NOATIME_FL)
new_fl |= S_NOATIME;
if (flags & F2FS_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
if (f2fs_encrypted_inode(inode))
new_fl |= S_ENCRYPTED;
inode_set_flags(inode, new_fl,
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|
S_ENCRYPTED);
}
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
int extra_size = get_extra_isize(inode);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
if (ri->i_addr[extra_size])
inode->i_rdev = old_decode_dev(
le32_to_cpu(ri->i_addr[extra_size]));
else
inode->i_rdev = new_decode_dev(
le32_to_cpu(ri->i_addr[extra_size + 1]));
}
}
static bool __written_first_block(struct f2fs_sb_info *sbi,
struct f2fs_inode *ri)
{
block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]);
if (is_valid_data_blkaddr(sbi, addr))
return true;
return false;
}
static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
int extra_size = get_extra_isize(inode);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
if (old_valid_dev(inode->i_rdev)) {
ri->i_addr[extra_size] =
cpu_to_le32(old_encode_dev(inode->i_rdev));
ri->i_addr[extra_size + 1] = 0;
} else {
ri->i_addr[extra_size] = 0;
ri->i_addr[extra_size + 1] =
cpu_to_le32(new_encode_dev(inode->i_rdev));
ri->i_addr[extra_size + 2] = 0;
}
}
}
static void __recover_inline_status(struct inode *inode, struct page *ipage)
{
void *inline_data = inline_data_addr(inode, ipage);
__le32 *start = inline_data;
__le32 *end = start + MAX_INLINE_DATA(inode) / sizeof(__le32);
while (start < end) {
if (*start++) {
f2fs_wait_on_page_writeback(ipage, NODE, true);
set_inode_flag(inode, FI_DATA_EXIST);
set_raw_inline(inode, F2FS_INODE(ipage));
set_page_dirty(ipage);
return;
}
}
return;
}
static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_inode *ri = &F2FS_NODE(page)->i;
if (!f2fs_sb_has_inode_chksum(sbi->sb))
return false;
if (!RAW_IS_INODE(F2FS_NODE(page)) || !(ri->i_inline & F2FS_EXTRA_ATTR))
return false;
if (!F2FS_FITS_IN_INODE(ri, le16_to_cpu(ri->i_extra_isize),
i_inode_checksum))
return false;
return true;
}
static __u32 f2fs_inode_chksum(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_node *node = F2FS_NODE(page);
struct f2fs_inode *ri = &node->i;
__le32 ino = node->footer.ino;
__le32 gen = ri->i_generation;
__u32 chksum, chksum_seed;
__u32 dummy_cs = 0;
unsigned int offset = offsetof(struct f2fs_inode, i_inode_checksum);
unsigned int cs_size = sizeof(dummy_cs);
chksum = f2fs_chksum(sbi, sbi->s_chksum_seed, (__u8 *)&ino,
sizeof(ino));
chksum_seed = f2fs_chksum(sbi, chksum, (__u8 *)&gen, sizeof(gen));
chksum = f2fs_chksum(sbi, chksum_seed, (__u8 *)ri, offset);
chksum = f2fs_chksum(sbi, chksum, (__u8 *)&dummy_cs, cs_size);
offset += cs_size;
chksum = f2fs_chksum(sbi, chksum, (__u8 *)ri + offset,
F2FS_BLKSIZE - offset);
return chksum;
}
bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_inode *ri;
__u32 provided, calculated;
if (unlikely(is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)))
return true;
#ifdef CONFIG_F2FS_CHECK_FS
if (!f2fs_enable_inode_chksum(sbi, page))
#else
if (!f2fs_enable_inode_chksum(sbi, page) ||
PageDirty(page) || PageWriteback(page))
#endif
return true;
ri = &F2FS_NODE(page)->i;
provided = le32_to_cpu(ri->i_inode_checksum);
calculated = f2fs_inode_chksum(sbi, page);
if (provided != calculated)
f2fs_msg(sbi->sb, KERN_WARNING,
"checksum invalid, ino = %x, %x vs. %x",
ino_of_node(page), provided, calculated);
return provided == calculated;
}
void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_inode *ri = &F2FS_NODE(page)->i;
if (!f2fs_enable_inode_chksum(sbi, page))
return;
ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page));
}
static bool sanity_check_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)
&& !f2fs_has_extra_attr(inode)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: corrupted inode ino=%lx, run fsck to fix.",
__func__, inode->i_ino);
return false;
}
if (f2fs_has_extra_attr(inode) &&
!f2fs_sb_has_extra_attr(sbi->sb)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: inode (ino=%lx) is with extra_attr, "
"but extra_attr feature is off",
__func__, inode->i_ino);
return false;
}
return true;
}
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_inode *ri;
projid_t i_projid;
/* Check if ino is within scope */
if (f2fs_check_nid_range(sbi, inode->i_ino))
return -EINVAL;
node_page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
ri = F2FS_INODE(node_page);
inode->i_mode = le16_to_cpu(ri->i_mode);
i_uid_write(inode, le32_to_cpu(ri->i_uid));
i_gid_write(inode, le32_to_cpu(ri->i_gid));
set_nlink(inode, le32_to_cpu(ri->i_links));
inode->i_size = le64_to_cpu(ri->i_size);
inode->i_blocks = SECTOR_FROM_BLOCK(le64_to_cpu(ri->i_blocks) - 1);
inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime);
inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime);
inode->i_mtime.tv_sec = le64_to_cpu(ri->i_mtime);
inode->i_atime.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
inode->i_generation = le32_to_cpu(ri->i_generation);
if (S_ISDIR(inode->i_mode))
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
else if (S_ISREG(inode->i_mode))
fi->i_gc_failures[GC_FAILURE_PIN] =
le16_to_cpu(ri->i_gc_failures);
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
fi->i_flags = le32_to_cpu(ri->i_flags);
fi->flags = 0;
fi->i_advise = ri->i_advise;
fi->i_pino = le32_to_cpu(ri->i_pino);
fi->i_dir_level = ri->i_dir_level;
if (f2fs_init_extent_tree(inode, &ri->i_ext))
set_page_dirty(node_page);
get_inline_info(inode, ri);
if (!sanity_check_inode(inode)) {
f2fs_put_page(node_page, 1);
return -EINVAL;
}
fi->i_extra_isize = f2fs_has_extra_attr(inode) ?
le16_to_cpu(ri->i_extra_isize) : 0;
if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)) {
fi->i_inline_xattr_size = le16_to_cpu(ri->i_inline_xattr_size);
} else if (f2fs_has_inline_xattr(inode) ||
f2fs_has_inline_dentry(inode)) {
fi->i_inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
} else {
/*
* Previous inline data or directory always reserved 200 bytes
* in inode layout, even if inline_xattr is disabled. In order
* to keep inline_dentry's structure for backward compatibility,
* we get the space back only from inline_data.
*/
fi->i_inline_xattr_size = 0;
}
/* check data exist */
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
__recover_inline_status(inode, node_page);
/* get rdev by using inline_info */
__get_inode_rdev(inode, ri);
if (__written_first_block(sbi, ri))
set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
if (!f2fs_need_inode_block_update(sbi, inode->i_ino))
fi->last_disk_size = inode->i_size;
if (fi->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi->sb) &&
F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid))
i_projid = (projid_t)le32_to_cpu(ri->i_projid);
else
i_projid = F2FS_DEF_PROJID;
fi->i_projid = make_kprojid(&init_user_ns, i_projid);
if (f2fs_has_extra_attr(inode) && f2fs_sb_has_inode_crtime(sbi->sb) &&
F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) {
fi->i_crtime.tv_sec = le64_to_cpu(ri->i_crtime);
fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec);
}
F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
f2fs_put_page(node_page, 1);
stat_inc_inline_xattr(inode);
stat_inc_inline_inode(inode);
stat_inc_inline_dir(inode);
return 0;
}
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
int ret = 0;
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW)) {
trace_f2fs_iget(inode);
return inode;
}
if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
goto make_now;
ret = do_read_inode(inode);
if (ret)
goto bad_inode;
make_now:
if (ino == F2FS_NODE_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_node_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
} else if (ino == F2FS_META_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_meta_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
} else if (S_ISREG(inode->i_mode)) {
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
inode_nohighmem(inode);
} else if (S_ISLNK(inode->i_mode)) {
if (f2fs_encrypted_inode(inode))
inode->i_op = &f2fs_encrypted_symlink_inode_operations;
else
inode->i_op = &f2fs_symlink_inode_operations;
inode_nohighmem(inode);
inode->i_mapping->a_ops = &f2fs_dblock_aops;
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
inode->i_op = &f2fs_special_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
} else {
ret = -EIO;
goto bad_inode;
}
f2fs_set_inode_flags(inode);
unlock_new_inode(inode);
trace_f2fs_iget(inode);
return inode;
bad_inode:
iget_failed(inode);
trace_f2fs_iget_exit(inode, ret);
return ERR_PTR(ret);
}
struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino)
{
struct inode *inode;
retry:
inode = f2fs_iget(sb, ino);
if (IS_ERR(inode)) {
if (PTR_ERR(inode) == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry;
}
}
return inode;
}
void f2fs_update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_inode *ri;
struct extent_tree *et = F2FS_I(inode)->extent_tree;
f2fs_wait_on_page_writeback(node_page, NODE, true);
set_page_dirty(node_page);
f2fs_inode_synced(inode);
ri = F2FS_INODE(node_page);
ri->i_mode = cpu_to_le16(inode->i_mode);
ri->i_advise = F2FS_I(inode)->i_advise;
ri->i_uid = cpu_to_le32(i_uid_read(inode));
ri->i_gid = cpu_to_le32(i_gid_read(inode));
ri->i_links = cpu_to_le32(inode->i_nlink);
ri->i_size = cpu_to_le64(i_size_read(inode));
ri->i_blocks = cpu_to_le64(SECTOR_TO_BLOCK(inode->i_blocks) + 1);
if (et) {
read_lock(&et->lock);
set_raw_extent(&et->largest, &ri->i_ext);
read_unlock(&et->lock);
} else {
memset(&ri->i_ext, 0, sizeof(ri->i_ext));
}
set_raw_inline(inode, ri);
ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
ri->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
if (S_ISDIR(inode->i_mode))
ri->i_current_depth =
cpu_to_le32(F2FS_I(inode)->i_current_depth);
else if (S_ISREG(inode->i_mode))
ri->i_gc_failures =
cpu_to_le16(F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]);
ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
ri->i_generation = cpu_to_le32(inode->i_generation);
ri->i_dir_level = F2FS_I(inode)->i_dir_level;
if (f2fs_has_extra_attr(inode)) {
ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize);
if (f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(inode)->sb))
ri->i_inline_xattr_size =
cpu_to_le16(F2FS_I(inode)->i_inline_xattr_size);
if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)->sb) &&
F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
i_projid)) {
projid_t i_projid;
i_projid = from_kprojid(&init_user_ns,
F2FS_I(inode)->i_projid);
ri->i_projid = cpu_to_le32(i_projid);
}
if (f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)->sb) &&
F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
i_crtime)) {
ri->i_crtime =
cpu_to_le64(F2FS_I(inode)->i_crtime.tv_sec);
ri->i_crtime_nsec =
cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec);
}
}
__set_inode_rdev(inode, ri);
/* deleted inode */
if (inode->i_nlink == 0)
clear_inline_node(node_page);
F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
#ifdef CONFIG_F2FS_CHECK_FS
f2fs_inode_chksum_set(F2FS_I_SB(inode), node_page);
#endif
}
void f2fs_update_inode_page(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *node_page;
retry:
node_page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page)) {
int err = PTR_ERR(node_page);
if (err == -ENOMEM) {
cond_resched();
goto retry;
} else if (err != -ENOENT) {
f2fs_stop_checkpoint(sbi, false);
}
return;
}
f2fs_update_inode(inode, node_page);
f2fs_put_page(node_page, 1);
}
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
return 0;
if (!is_inode_flag_set(inode, FI_DIRTY_INODE))
return 0;
/*
* We need to balance fs here to prevent from producing dirty node pages
* during the urgent cleaning time when runing out of free sections.
*/
f2fs_update_inode_page(inode);
if (wbc && wbc->nr_to_write)
f2fs_balance_fs(sbi, true);
return 0;
}
/*
* Called at the last iput() if i_nlink is zero
*/
void f2fs_evict_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
int err = 0;
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
f2fs_drop_inmem_pages(inode);
trace_f2fs_evict_inode(inode);
truncate_inode_pages_final(&inode->i_data);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
goto out_clear;
f2fs_bug_on(sbi, get_dirty_pages(inode));
f2fs_remove_dirty_inode(inode);
f2fs_destroy_extent_tree(inode);
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
dquot_initialize(inode);
f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
f2fs_remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
sb_start_intwrite(inode->i_sb);
set_inode_flag(inode, FI_NO_ALLOC);
i_size_write(inode, 0);
retry:
if (F2FS_HAS_BLOCKS(inode))
err = f2fs_truncate(inode);
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
f2fs_show_injection_info(FAULT_EVICT_INODE);
err = -EIO;
}
#endif
if (!err) {
f2fs_lock_op(sbi);
err = f2fs_remove_inode_page(inode);
f2fs_unlock_op(sbi);
if (err == -ENOENT)
err = 0;
}
/* give more chances, if ENOMEM case */
if (err == -ENOMEM) {
err = 0;
goto retry;
}
if (err)
f2fs_update_inode_page(inode);
dquot_free_inode(inode);
sb_end_intwrite(inode->i_sb);
no_delete:
dquot_drop(inode);
stat_dec_inline_xattr(inode);
stat_dec_inline_dir(inode);
stat_dec_inline_inode(inode);
if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG)))
f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));
else
f2fs_inode_synced(inode);
/* ino == 0, if f2fs_new_inode() was failed t*/
if (inode->i_ino)
invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino,
inode->i_ino);
if (xnid)
invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
if (inode->i_nlink) {
if (is_inode_flag_set(inode, FI_APPEND_WRITE))
f2fs_add_ino_entry(sbi, inode->i_ino, APPEND_INO);
if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
f2fs_add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
}
if (is_inode_flag_set(inode, FI_FREE_NID)) {
f2fs_alloc_nid_failed(sbi, inode->i_ino);
clear_inode_flag(inode, FI_FREE_NID);
} else {
/*
* If xattr nid is corrupted, we can reach out error condition,
* err & !f2fs_exist_written_data(sbi, inode->i_ino, ORPHAN_INO)).
* In that case, f2fs_check_nid_range() is enough to give a clue.
*/
}
out_clear:
fscrypt_put_encryption_info(inode);
clear_inode(inode);
}
/* caller should call f2fs_lock_op() */
void f2fs_handle_failed_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct node_info ni;
/*
* clear nlink of inode in order to release resource of inode
* immediately.
*/
clear_nlink(inode);
/*
* we must call this to avoid inode being remained as dirty, resulting
* in a panic when flushing dirty inodes in gdirty_list.
*/
f2fs_update_inode_page(inode);
f2fs_inode_synced(inode);
/* don't make bad inode, since it becomes a regular file. */
unlock_new_inode(inode);
/*
* Note: we should add inode to orphan list before f2fs_unlock_op()
* so we can prevent losing this orphan when encoutering checkpoint
* and following suddenly power-off.
*/
f2fs_get_node_info(sbi, inode->i_ino, &ni);
if (ni.blk_addr != NULL_ADDR) {
int err = f2fs_acquire_orphan_inode(sbi);
if (err) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"Too many orphan inodes, run fsck to fix.");
} else {
f2fs_add_orphan_inode(inode);
}
f2fs_alloc_nid_done(sbi, inode->i_ino);
} else {
set_inode_flag(inode, FI_FREE_NID);
}
f2fs_unlock_op(sbi);
/* iput will drop the inode object */
iput(inode);
}