linux/fs/f2fs/inode.c
Chao Yu 18dd6470c2 f2fs: fix to do sanity check with i_extra_isize
If inode.i_extra_isize was fuzzed to an abnormal value, when
calculating inline data size, the result will overflow, result
in accessing invalid memory area when operating inline data.

Let's do sanity check with i_extra_isize during inode loading
for fixing.

https://bugzilla.kernel.org/show_bug.cgi?id=200421

- Reproduce

- POC (poc.c)
    #define _GNU_SOURCE
    #include <sys/types.h>
    #include <sys/mount.h>
    #include <sys/mman.h>
    #include <sys/stat.h>
    #include <sys/xattr.h>

    #include <dirent.h>
    #include <errno.h>
    #include <error.h>
    #include <fcntl.h>
    #include <stdio.h>
    #include <stdlib.h>
    #include <string.h>
    #include <unistd.h>

    #include <linux/falloc.h>
    #include <linux/loop.h>

    static void activity(char *mpoint) {

      char *foo_bar_baz;
      char *foo_baz;
      char *xattr;
      int err;

      err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint);
      err = asprintf(&foo_baz, "%s/foo/baz", mpoint);
      err = asprintf(&xattr, "%s/foo/bar/xattr", mpoint);

      rename(foo_bar_baz, foo_baz);

      char buf2[113];
      memset(buf2, 0, sizeof(buf2));
      listxattr(xattr, buf2, sizeof(buf2));
      removexattr(xattr, "user.mime_type");

    }

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

- Kernel message
Umount the image will leave the following message
[ 2910.995489] F2FS-fs (loop0): Mounted with checkpoint version = 2
[ 2918.416465] ==================================================================
[ 2918.416807] BUG: KASAN: slab-out-of-bounds in f2fs_iget+0xcb9/0x1a80
[ 2918.417009] Read of size 4 at addr ffff88018efc2068 by task a.out/1229

[ 2918.417311] CPU: 1 PID: 1229 Comm: a.out Not tainted 4.17.0+ #1
[ 2918.417314] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
[ 2918.417323] Call Trace:
[ 2918.417366]  dump_stack+0x71/0xab
[ 2918.417401]  print_address_description+0x6b/0x290
[ 2918.417407]  kasan_report+0x28e/0x390
[ 2918.417411]  ? f2fs_iget+0xcb9/0x1a80
[ 2918.417415]  f2fs_iget+0xcb9/0x1a80
[ 2918.417422]  ? f2fs_lookup+0x2e7/0x580
[ 2918.417425]  f2fs_lookup+0x2e7/0x580
[ 2918.417433]  ? __recover_dot_dentries+0x400/0x400
[ 2918.417447]  ? legitimize_path.isra.29+0x5a/0xa0
[ 2918.417453]  __lookup_slow+0x11c/0x220
[ 2918.417457]  ? may_delete+0x2a0/0x2a0
[ 2918.417475]  ? deref_stack_reg+0xe0/0xe0
[ 2918.417479]  ? __lookup_hash+0xb0/0xb0
[ 2918.417483]  lookup_slow+0x3e/0x60
[ 2918.417488]  walk_component+0x3ac/0x990
[ 2918.417492]  ? generic_permission+0x51/0x1e0
[ 2918.417495]  ? inode_permission+0x51/0x1d0
[ 2918.417499]  ? pick_link+0x3e0/0x3e0
[ 2918.417502]  ? link_path_walk+0x4b1/0x770
[ 2918.417513]  ? _raw_spin_lock_irqsave+0x25/0x50
[ 2918.417518]  ? walk_component+0x990/0x990
[ 2918.417522]  ? path_init+0x2e6/0x580
[ 2918.417526]  path_lookupat+0x13f/0x430
[ 2918.417531]  ? trailing_symlink+0x3a0/0x3a0
[ 2918.417534]  ? do_renameat2+0x270/0x7b0
[ 2918.417538]  ? __kasan_slab_free+0x14c/0x190
[ 2918.417541]  ? do_renameat2+0x270/0x7b0
[ 2918.417553]  ? kmem_cache_free+0x85/0x1e0
[ 2918.417558]  ? do_renameat2+0x270/0x7b0
[ 2918.417563]  filename_lookup+0x13c/0x280
[ 2918.417567]  ? filename_parentat+0x2b0/0x2b0
[ 2918.417572]  ? kasan_unpoison_shadow+0x31/0x40
[ 2918.417575]  ? kasan_kmalloc+0xa6/0xd0
[ 2918.417593]  ? strncpy_from_user+0xaa/0x1c0
[ 2918.417598]  ? getname_flags+0x101/0x2b0
[ 2918.417614]  ? path_listxattr+0x87/0x110
[ 2918.417619]  path_listxattr+0x87/0x110
[ 2918.417623]  ? listxattr+0xc0/0xc0
[ 2918.417637]  ? mm_fault_error+0x1b0/0x1b0
[ 2918.417654]  do_syscall_64+0x73/0x160
[ 2918.417660]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 2918.417676] RIP: 0033:0x7f2f3a3480d7
[ 2918.417677] Code: f0 ff ff 73 01 c3 48 8b 0d be dd 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 b8 c2 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 91 dd 2b 00 f7 d8 64 89 01 48
[ 2918.417732] RSP: 002b:00007fff4095b7d8 EFLAGS: 00000206 ORIG_RAX: 00000000000000c2
[ 2918.417744] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f2f3a3480d7
[ 2918.417746] RDX: 0000000000000071 RSI: 00007fff4095b810 RDI: 000000000126a0c0
[ 2918.417749] RBP: 00007fff4095b890 R08: 000000000126a010 R09: 0000000000000000
[ 2918.417751] R10: 00000000000001ab R11: 0000000000000206 R12: 00000000004005e0
[ 2918.417753] R13: 00007fff4095b990 R14: 0000000000000000 R15: 0000000000000000

[ 2918.417853] Allocated by task 329:
[ 2918.418002]  kasan_kmalloc+0xa6/0xd0
[ 2918.418007]  kmem_cache_alloc+0xc8/0x1e0
[ 2918.418023]  mempool_init_node+0x194/0x230
[ 2918.418027]  mempool_init+0x12/0x20
[ 2918.418042]  bioset_init+0x2bd/0x380
[ 2918.418052]  blk_alloc_queue_node+0xe9/0x540
[ 2918.418075]  dm_create+0x2c0/0x800
[ 2918.418080]  dev_create+0xd2/0x530
[ 2918.418083]  ctl_ioctl+0x2a3/0x5b0
[ 2918.418087]  dm_ctl_ioctl+0xa/0x10
[ 2918.418092]  do_vfs_ioctl+0x13e/0x8c0
[ 2918.418095]  ksys_ioctl+0x66/0x70
[ 2918.418098]  __x64_sys_ioctl+0x3d/0x50
[ 2918.418102]  do_syscall_64+0x73/0x160
[ 2918.418106]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

[ 2918.418204] Freed by task 0:
[ 2918.418301] (stack is not available)

[ 2918.418521] The buggy address belongs to the object at ffff88018efc0000
                which belongs to the cache biovec-max of size 8192
[ 2918.418894] The buggy address is located 104 bytes to the right of
                8192-byte region [ffff88018efc0000, ffff88018efc2000)
[ 2918.419257] The buggy address belongs to the page:
[ 2918.419431] page:ffffea00063bf000 count:1 mapcount:0 mapping:ffff8801f2242540 index:0x0 compound_mapcount: 0
[ 2918.419702] flags: 0x17fff8000008100(slab|head)
[ 2918.419879] raw: 017fff8000008100 dead000000000100 dead000000000200 ffff8801f2242540
[ 2918.420101] raw: 0000000000000000 0000000000030003 00000001ffffffff 0000000000000000
[ 2918.420322] page dumped because: kasan: bad access detected

[ 2918.420599] Memory state around the buggy address:
[ 2918.420764]  ffff88018efc1f00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 2918.420975]  ffff88018efc1f80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 2918.421194] >ffff88018efc2000: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 2918.421406]                                                           ^
[ 2918.421627]  ffff88018efc2080: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 2918.421838]  ffff88018efc2100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 2918.422046] ==================================================================
[ 2918.422264] Disabling lock debugging due to kernel taint
[ 2923.901641] BUG: unable to handle kernel paging request at ffff88018f0db000
[ 2923.901884] PGD 22226a067 P4D 22226a067 PUD 222273067 PMD 18e642063 PTE 800000018f0db061
[ 2923.902120] Oops: 0003 [#1] SMP KASAN PTI
[ 2923.902274] CPU: 1 PID: 1231 Comm: umount Tainted: G    B             4.17.0+ #1
[ 2923.902490] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
[ 2923.902761] RIP: 0010:__memset+0x24/0x30
[ 2923.902906] Code: 90 90 90 90 90 90 66 66 90 66 90 49 89 f9 48 89 d1 83 e2 07 48 c1 e9 03 40 0f b6 f6 48 b8 01 01 01 01 01 01 01 01 48 0f af c6 <f3> 48 ab 89 d1 f3 aa 4c 89 c8 c3 90 49 89 f9 40 88 f0 48 89 d1 f3
[ 2923.903446] RSP: 0018:ffff88018ddf7ae0 EFLAGS: 00010206
[ 2923.903622] RAX: 0000000000000000 RBX: ffff8801d549d888 RCX: 1ffffffffffdaffb
[ 2923.903833] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88018f0daffc
[ 2923.904062] RBP: ffff88018efc206c R08: 1ffff10031df840d R09: ffff88018efc206c
[ 2923.904273] R10: ffffffffffffe1ee R11: ffffed0031df65fa R12: 0000000000000000
[ 2923.904485] R13: ffff8801d549dc98 R14: 00000000ffffc3db R15: ffffea00063bec80
[ 2923.904693] FS:  00007fa8b2f8a840(0000) GS:ffff8801f3b00000(0000) knlGS:0000000000000000
[ 2923.904937] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2923.910080] CR2: ffff88018f0db000 CR3: 000000018f892000 CR4: 00000000000006e0
[ 2923.914930] Call Trace:
[ 2923.919724]  f2fs_truncate_inline_inode+0x114/0x170
[ 2923.924487]  f2fs_truncate_blocks+0x11b/0x7c0
[ 2923.929178]  ? f2fs_truncate_data_blocks+0x10/0x10
[ 2923.933834]  ? dqget+0x670/0x670
[ 2923.938437]  ? f2fs_destroy_extent_tree+0xd6/0x270
[ 2923.943107]  ? __radix_tree_lookup+0x2f/0x150
[ 2923.947772]  f2fs_truncate+0xd4/0x1a0
[ 2923.952491]  f2fs_evict_inode+0x5ab/0x610
[ 2923.957204]  evict+0x15f/0x280
[ 2923.961898]  __dentry_kill+0x161/0x250
[ 2923.966634]  shrink_dentry_list+0xf3/0x250
[ 2923.971897]  shrink_dcache_parent+0xa9/0x100
[ 2923.976561]  ? shrink_dcache_sb+0x1f0/0x1f0
[ 2923.981177]  ? wait_for_completion+0x8a/0x210
[ 2923.985781]  ? migrate_swap_stop+0x2d0/0x2d0
[ 2923.990332]  do_one_tree+0xe/0x40
[ 2923.994735]  shrink_dcache_for_umount+0x3a/0xa0
[ 2923.999077]  generic_shutdown_super+0x3e/0x1c0
[ 2924.003350]  kill_block_super+0x4b/0x70
[ 2924.007619]  deactivate_locked_super+0x65/0x90
[ 2924.011812]  cleanup_mnt+0x5c/0xa0
[ 2924.015995]  task_work_run+0xce/0xf0
[ 2924.020174]  exit_to_usermode_loop+0x115/0x120
[ 2924.024293]  do_syscall_64+0x12f/0x160
[ 2924.028479]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 2924.032709] RIP: 0033:0x7fa8b2868487
[ 2924.036888] Code: 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 31 f6 e9 09 00 00 00 66 0f 1f 84 00 00 00 00 00 b8 a6 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d e1 c9 2b 00 f7 d8 64 89 01 48
[ 2924.045750] RSP: 002b:00007ffc39824d58 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6
[ 2924.050190] RAX: 0000000000000000 RBX: 00000000008ea030 RCX: 00007fa8b2868487
[ 2924.054604] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 00000000008f4360
[ 2924.058940] RBP: 00000000008f4360 R08: 0000000000000000 R09: 0000000000000014
[ 2924.063186] R10: 00000000000006b2 R11: 0000000000000246 R12: 00007fa8b2d7183c
[ 2924.067418] R13: 0000000000000000 R14: 00000000008ea210 R15: 00007ffc39824fe0
[ 2924.071534] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_timer joydev input_leds serio_raw snd soundcore mac_hid i2c_piix4 ib_iser rdma_cm iw_cm ib_cm ib_core configfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi btrfs zstd_decompress zstd_compress xxhash raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear 8139too qxl ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel psmouse aes_x86_64 8139cp crypto_simd cryptd mii glue_helper pata_acpi floppy
[ 2924.098044] CR2: ffff88018f0db000
[ 2924.102520] ---[ end trace a8e0d899985faf31 ]---
[ 2924.107012] RIP: 0010:__memset+0x24/0x30
[ 2924.111448] Code: 90 90 90 90 90 90 66 66 90 66 90 49 89 f9 48 89 d1 83 e2 07 48 c1 e9 03 40 0f b6 f6 48 b8 01 01 01 01 01 01 01 01 48 0f af c6 <f3> 48 ab 89 d1 f3 aa 4c 89 c8 c3 90 49 89 f9 40 88 f0 48 89 d1 f3
[ 2924.120724] RSP: 0018:ffff88018ddf7ae0 EFLAGS: 00010206
[ 2924.125312] RAX: 0000000000000000 RBX: ffff8801d549d888 RCX: 1ffffffffffdaffb
[ 2924.129931] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88018f0daffc
[ 2924.134537] RBP: ffff88018efc206c R08: 1ffff10031df840d R09: ffff88018efc206c
[ 2924.139175] R10: ffffffffffffe1ee R11: ffffed0031df65fa R12: 0000000000000000
[ 2924.143825] R13: ffff8801d549dc98 R14: 00000000ffffc3db R15: ffffea00063bec80
[ 2924.148500] FS:  00007fa8b2f8a840(0000) GS:ffff8801f3b00000(0000) knlGS:0000000000000000
[ 2924.153247] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2924.158003] CR2: ffff88018f0db000 CR3: 000000018f892000 CR4: 00000000000006e0
[ 2924.164641] BUG: Bad rss-counter state mm:00000000fa04621e idx:0 val:4
[ 2924.170007] BUG: Bad rss-counter
tate mm:00000000fa04621e idx:1 val:2

- Location
https://elixir.bootlin.com/linux/v4.18-rc3/source/fs/f2fs/inline.c#L78
	memset(addr + from, 0, MAX_INLINE_DATA(inode) - from);
Here the length can be negative.

Reported-by Wen Xu <wen.xu@gatech.edu>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 11:52:36 -07:00

745 lines
20 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 (!IS_INODE(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 page *node_page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned long long iblocks;
iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks);
if (!iblocks) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, "
"run fsck to fix.",
__func__, inode->i_ino, iblocks);
return false;
}
if (ino_of_node(node_page) != nid_of_node(node_page)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: corrupted inode footer i_ino=%lx, ino,nid: "
"[%u, %u] run fsck to fix.",
__func__, inode->i_ino,
ino_of_node(node_page), nid_of_node(node_page));
return false;
}
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;
}
if (fi->i_extra_isize > F2FS_TOTAL_EXTRA_ATTR_SIZE ||
fi->i_extra_isize % sizeof(__le32)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: inode (ino=%lx) has corrupted i_extra_isize: %d, "
"max: %zu",
__func__, inode->i_ino, fi->i_extra_isize,
F2FS_TOTAL_EXTRA_ATTR_SIZE);
return false;
}
if (F2FS_I(inode)->extent_tree) {
struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest;
if (ei->len &&
(!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC) ||
!f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
DATA_GENERIC))) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: inode (ino=%lx) extent info [%u, %u, %u] "
"is incorrect, run fsck to fix",
__func__, inode->i_ino,
ei->blk, ei->fofs, ei->len);
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);
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;
}
if (!sanity_check_inode(inode, node_page)) {
f2fs_put_page(node_page, 1);
return -EINVAL;
}
/* 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);
}