linux/fs/btrfs/tree-checker.c

1913 lines
57 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) Qu Wenruo 2017. All rights reserved.
*/
/*
* The module is used to catch unexpected/corrupted tree block data.
* Such behavior can be caused either by a fuzzed image or bugs.
*
* The objective is to do leaf/node validation checks when tree block is read
* from disk, and check *every* possible member, so other code won't
* need to checking them again.
*
* Due to the potential and unwanted damage, every checker needs to be
* carefully reviewed otherwise so it does not prevent mount of valid images.
*/
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/error-injection.h>
#include "ctree.h"
#include "tree-checker.h"
#include "disk-io.h"
#include "compression.h"
#include "volumes.h"
#include "misc.h"
btrfs: add ro compat flags to inodes Currently, inode flags are fully backwards incompatible in btrfs. If we introduce a new inode flag, then tree-checker will detect it and fail. This can even cause us to fail to mount entirely. To make it possible to introduce new flags which can be read-only compatible, like VERITY, we add new ro flags to btrfs without treating them quite so harshly in tree-checker. A read-only file system can survive an unexpected flag, and can be mounted. As for the implementation, it unfortunately gets a little complicated. The on-disk representation of the inode, btrfs_inode_item, has an __le64 for flags but the in-memory representation, btrfs_inode, uses a u32. David Sterba had the nice idea that we could reclaim those wasted 32 bits on disk and use them for the new ro_compat flags. It turns out that the tree-checker code which checks for unknown flags is broken, and ignores the upper 32 bits we are hoping to use. The issue is that the flags use the literal 1 rather than 1ULL, so the flags are signed ints, and one of them is specifically (1 << 31). As a result, the mask which ORs the flags is a negative integer on machines where int is 32 bit twos complement. When tree-checker evaluates the expression: btrfs_inode_flags(leaf, iitem) & ~BTRFS_INODE_FLAG_MASK) The mask is something like 0x80000abc, which gets promoted to u64 with sign extension to 0xffffffff80000abc. Negating that 64 bit mask leaves all the upper bits zeroed, and we can't detect unexpected flags. This suggests that we can't use those bits after all. Luckily, we have good reason to believe that they are zero anyway. Inode flags are metadata, which is always checksummed, so any bit flips that would introduce 1s would cause a checksum failure anyway (excluding the improbable case of the checksum getting corrupted exactly badly). Further, unless the 1 << 31 flag is used, the cast to u64 of the 32 bit inode flag should preserve its value and not add leading zeroes (at least for twos complement). The only place that flag (BTRFS_INODE_ROOT_ITEM_INIT) is used is in a special inode embedded in the root item, and indeed for that inode we see 0xffffffff80000000 as the flags on disk. However, that inode is never seen by tree checker, nor is it used in a context where verity might be meaningful. Theoretically, a future ro flag might cause trouble on that inode, so we should proactively clean up that mess before it does. With the introduction of the new ro flags, keep two separate unsigned masks and check them against the appropriate u32. Since we no longer run afoul of sign extension, this also stops writing out 0xffffffff80000000 in root_item inodes going forward. Signed-off-by: Boris Burkov <boris@bur.io> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-01 04:01:48 +08:00
#include "btrfs_inode.h"
/*
* Error message should follow the following format:
* corrupt <type>: <identifier>, <reason>[, <bad_value>]
*
* @type: leaf or node
* @identifier: the necessary info to locate the leaf/node.
* It's recommended to decode key.objecitd/offset if it's
* meaningful.
* @reason: describe the error
* @bad_value: optional, it's recommended to output bad value and its
* expected value (range).
*
* Since comma is used to separate the components, only space is allowed
* inside each component.
*/
/*
* Append generic "corrupt leaf/node root=%llu block=%llu slot=%d: " to @fmt.
* Allows callers to customize the output.
*/
__printf(3, 4)
__cold
static void generic_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = eb->fs_info;
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(fs_info,
"corrupt %s: root=%llu block=%llu slot=%d, %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot, &vaf);
va_end(args);
}
/*
* Customized reporter for extent data item, since its key objectid and
* offset has its own meaning.
*/
__printf(3, 4)
__cold
static void file_extent_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_key key;
struct va_format vaf;
va_list args;
btrfs_item_key_to_cpu(eb, &key, slot);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(fs_info,
"corrupt %s: root=%llu block=%llu slot=%d ino=%llu file_offset=%llu, %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
key.objectid, key.offset, &vaf);
va_end(args);
}
/*
* Return 0 if the btrfs_file_extent_##name is aligned to @alignment
* Else return 1
*/
#define CHECK_FE_ALIGNED(leaf, slot, fi, name, alignment) \
({ \
if (unlikely(!IS_ALIGNED(btrfs_file_extent_##name((leaf), (fi)), \
(alignment)))) \
file_extent_err((leaf), (slot), \
"invalid %s for file extent, have %llu, should be aligned to %u", \
(#name), btrfs_file_extent_##name((leaf), (fi)), \
(alignment)); \
(!IS_ALIGNED(btrfs_file_extent_##name((leaf), (fi)), (alignment))); \
})
static u64 file_extent_end(struct extent_buffer *leaf,
struct btrfs_key *key,
struct btrfs_file_extent_item *extent)
{
u64 end;
u64 len;
if (btrfs_file_extent_type(leaf, extent) == BTRFS_FILE_EXTENT_INLINE) {
len = btrfs_file_extent_ram_bytes(leaf, extent);
end = ALIGN(key->offset + len, leaf->fs_info->sectorsize);
} else {
len = btrfs_file_extent_num_bytes(leaf, extent);
end = key->offset + len;
}
return end;
}
/*
* Customized report for dir_item, the only new important information is
* key->objectid, which represents inode number
*/
__printf(3, 4)
__cold
static void dir_item_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_key key;
struct va_format vaf;
va_list args;
btrfs_item_key_to_cpu(eb, &key, slot);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(fs_info,
"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
key.objectid, &vaf);
va_end(args);
}
/*
* This functions checks prev_key->objectid, to ensure current key and prev_key
* share the same objectid as inode number.
*
* This is to detect missing INODE_ITEM in subvolume trees.
*
* Return true if everything is OK or we don't need to check.
* Return false if anything is wrong.
*/
static bool check_prev_ino(struct extent_buffer *leaf,
struct btrfs_key *key, int slot,
struct btrfs_key *prev_key)
{
/* No prev key, skip check */
if (slot == 0)
return true;
/* Only these key->types needs to be checked */
ASSERT(key->type == BTRFS_XATTR_ITEM_KEY ||
key->type == BTRFS_INODE_REF_KEY ||
key->type == BTRFS_DIR_INDEX_KEY ||
key->type == BTRFS_DIR_ITEM_KEY ||
key->type == BTRFS_EXTENT_DATA_KEY);
/*
* Only subvolume trees along with their reloc trees need this check.
* Things like log tree doesn't follow this ino requirement.
*/
if (!is_fstree(btrfs_header_owner(leaf)))
return true;
if (key->objectid == prev_key->objectid)
return true;
/* Error found */
dir_item_err(leaf, slot,
"invalid previous key objectid, have %llu expect %llu",
prev_key->objectid, key->objectid);
return false;
}
static int check_extent_data_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot,
struct btrfs_key *prev_key)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_file_extent_item *fi;
u32 sectorsize = fs_info->sectorsize;
u32 item_size = btrfs_item_size(leaf, slot);
u64 extent_end;
if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) {
file_extent_err(leaf, slot,
"unaligned file_offset for file extent, have %llu should be aligned to %u",
key->offset, sectorsize);
return -EUCLEAN;
}
/*
* Previous key must have the same key->objectid (ino).
* It can be XATTR_ITEM, INODE_ITEM or just another EXTENT_DATA.
* But if objectids mismatch, it means we have a missing
* INODE_ITEM.
*/
if (unlikely(!check_prev_ino(leaf, key, slot, prev_key)))
return -EUCLEAN;
fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
/*
* Make sure the item contains at least inline header, so the file
* extent type is not some garbage.
*/
if (unlikely(item_size < BTRFS_FILE_EXTENT_INLINE_DATA_START)) {
file_extent_err(leaf, slot,
"invalid item size, have %u expect [%zu, %u)",
item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START,
SZ_4K);
return -EUCLEAN;
}
if (unlikely(btrfs_file_extent_type(leaf, fi) >=
BTRFS_NR_FILE_EXTENT_TYPES)) {
file_extent_err(leaf, slot,
"invalid type for file extent, have %u expect range [0, %u]",
btrfs_file_extent_type(leaf, fi),
BTRFS_NR_FILE_EXTENT_TYPES - 1);
return -EUCLEAN;
}
/*
* Support for new compression/encryption must introduce incompat flag,
* and must be caught in open_ctree().
*/
if (unlikely(btrfs_file_extent_compression(leaf, fi) >=
BTRFS_NR_COMPRESS_TYPES)) {
file_extent_err(leaf, slot,
"invalid compression for file extent, have %u expect range [0, %u]",
btrfs_file_extent_compression(leaf, fi),
BTRFS_NR_COMPRESS_TYPES - 1);
return -EUCLEAN;
}
if (unlikely(btrfs_file_extent_encryption(leaf, fi))) {
file_extent_err(leaf, slot,
"invalid encryption for file extent, have %u expect 0",
btrfs_file_extent_encryption(leaf, fi));
return -EUCLEAN;
}
if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) {
/* Inline extent must have 0 as key offset */
if (unlikely(key->offset)) {
file_extent_err(leaf, slot,
"invalid file_offset for inline file extent, have %llu expect 0",
key->offset);
return -EUCLEAN;
}
/* Compressed inline extent has no on-disk size, skip it */
if (btrfs_file_extent_compression(leaf, fi) !=
BTRFS_COMPRESS_NONE)
return 0;
/* Uncompressed inline extent size must match item size */
if (unlikely(item_size != BTRFS_FILE_EXTENT_INLINE_DATA_START +
btrfs_file_extent_ram_bytes(leaf, fi))) {
file_extent_err(leaf, slot,
"invalid ram_bytes for uncompressed inline extent, have %u expect %llu",
item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START +
btrfs_file_extent_ram_bytes(leaf, fi));
return -EUCLEAN;
}
return 0;
}
/* Regular or preallocated extent has fixed item size */
if (unlikely(item_size != sizeof(*fi))) {
file_extent_err(leaf, slot,
"invalid item size for reg/prealloc file extent, have %u expect %zu",
item_size, sizeof(*fi));
return -EUCLEAN;
}
if (unlikely(CHECK_FE_ALIGNED(leaf, slot, fi, ram_bytes, sectorsize) ||
CHECK_FE_ALIGNED(leaf, slot, fi, disk_bytenr, sectorsize) ||
CHECK_FE_ALIGNED(leaf, slot, fi, disk_num_bytes, sectorsize) ||
CHECK_FE_ALIGNED(leaf, slot, fi, offset, sectorsize) ||
CHECK_FE_ALIGNED(leaf, slot, fi, num_bytes, sectorsize)))
return -EUCLEAN;
/* Catch extent end overflow */
if (unlikely(check_add_overflow(btrfs_file_extent_num_bytes(leaf, fi),
key->offset, &extent_end))) {
file_extent_err(leaf, slot,
"extent end overflow, have file offset %llu extent num bytes %llu",
key->offset,
btrfs_file_extent_num_bytes(leaf, fi));
return -EUCLEAN;
}
/*
* Check that no two consecutive file extent items, in the same leaf,
* present ranges that overlap each other.
*/
if (slot > 0 &&
prev_key->objectid == key->objectid &&
prev_key->type == BTRFS_EXTENT_DATA_KEY) {
struct btrfs_file_extent_item *prev_fi;
u64 prev_end;
prev_fi = btrfs_item_ptr(leaf, slot - 1,
struct btrfs_file_extent_item);
prev_end = file_extent_end(leaf, prev_key, prev_fi);
if (unlikely(prev_end > key->offset)) {
file_extent_err(leaf, slot - 1,
"file extent end range (%llu) goes beyond start offset (%llu) of the next file extent",
prev_end, key->offset);
return -EUCLEAN;
}
}
return 0;
}
static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key,
int slot, struct btrfs_key *prev_key)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
u32 sectorsize = fs_info->sectorsize;
const u32 csumsize = fs_info->csum_size;
if (unlikely(key->objectid != BTRFS_EXTENT_CSUM_OBJECTID)) {
generic_err(leaf, slot,
"invalid key objectid for csum item, have %llu expect %llu",
key->objectid, BTRFS_EXTENT_CSUM_OBJECTID);
return -EUCLEAN;
}
if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) {
generic_err(leaf, slot,
"unaligned key offset for csum item, have %llu should be aligned to %u",
key->offset, sectorsize);
return -EUCLEAN;
}
if (unlikely(!IS_ALIGNED(btrfs_item_size(leaf, slot), csumsize))) {
generic_err(leaf, slot,
"unaligned item size for csum item, have %u should be aligned to %u",
btrfs_item_size(leaf, slot), csumsize);
return -EUCLEAN;
}
if (slot > 0 && prev_key->type == BTRFS_EXTENT_CSUM_KEY) {
u64 prev_csum_end;
u32 prev_item_size;
prev_item_size = btrfs_item_size(leaf, slot - 1);
prev_csum_end = (prev_item_size / csumsize) * sectorsize;
prev_csum_end += prev_key->offset;
if (unlikely(prev_csum_end > key->offset)) {
generic_err(leaf, slot - 1,
"csum end range (%llu) goes beyond the start range (%llu) of the next csum item",
prev_csum_end, key->offset);
return -EUCLEAN;
}
}
return 0;
}
/* Inode item error output has the same format as dir_item_err() */
#define inode_item_err(eb, slot, fmt, ...) \
dir_item_err(eb, slot, fmt, __VA_ARGS__)
static int check_inode_key(struct extent_buffer *leaf, struct btrfs_key *key,
int slot)
{
struct btrfs_key item_key;
bool is_inode_item;
btrfs_item_key_to_cpu(leaf, &item_key, slot);
is_inode_item = (item_key.type == BTRFS_INODE_ITEM_KEY);
/* For XATTR_ITEM, location key should be all 0 */
if (item_key.type == BTRFS_XATTR_ITEM_KEY) {
if (unlikely(key->objectid != 0 || key->type != 0 ||
key->offset != 0))
return -EUCLEAN;
return 0;
}
if (unlikely((key->objectid < BTRFS_FIRST_FREE_OBJECTID ||
key->objectid > BTRFS_LAST_FREE_OBJECTID) &&
key->objectid != BTRFS_ROOT_TREE_DIR_OBJECTID &&
key->objectid != BTRFS_FREE_INO_OBJECTID)) {
if (is_inode_item) {
generic_err(leaf, slot,
"invalid key objectid: has %llu expect %llu or [%llu, %llu] or %llu",
key->objectid, BTRFS_ROOT_TREE_DIR_OBJECTID,
BTRFS_FIRST_FREE_OBJECTID,
BTRFS_LAST_FREE_OBJECTID,
BTRFS_FREE_INO_OBJECTID);
} else {
dir_item_err(leaf, slot,
"invalid location key objectid: has %llu expect %llu or [%llu, %llu] or %llu",
key->objectid, BTRFS_ROOT_TREE_DIR_OBJECTID,
BTRFS_FIRST_FREE_OBJECTID,
BTRFS_LAST_FREE_OBJECTID,
BTRFS_FREE_INO_OBJECTID);
}
return -EUCLEAN;
}
if (unlikely(key->offset != 0)) {
if (is_inode_item)
inode_item_err(leaf, slot,
"invalid key offset: has %llu expect 0",
key->offset);
else
dir_item_err(leaf, slot,
"invalid location key offset:has %llu expect 0",
key->offset);
return -EUCLEAN;
}
return 0;
}
static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key,
int slot)
{
struct btrfs_key item_key;
bool is_root_item;
btrfs_item_key_to_cpu(leaf, &item_key, slot);
is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY);
/* No such tree id */
if (unlikely(key->objectid == 0)) {
if (is_root_item)
generic_err(leaf, slot, "invalid root id 0");
else
dir_item_err(leaf, slot,
"invalid location key root id 0");
return -EUCLEAN;
}
/* DIR_ITEM/INDEX/INODE_REF is not allowed to point to non-fs trees */
if (unlikely(!is_fstree(key->objectid) && !is_root_item)) {
dir_item_err(leaf, slot,
"invalid location key objectid, have %llu expect [%llu, %llu]",
key->objectid, BTRFS_FIRST_FREE_OBJECTID,
BTRFS_LAST_FREE_OBJECTID);
return -EUCLEAN;
}
/*
* ROOT_ITEM with non-zero offset means this is a snapshot, created at
* @offset transid.
* Furthermore, for location key in DIR_ITEM, its offset is always -1.
*
* So here we only check offset for reloc tree whose key->offset must
* be a valid tree.
*/
if (unlikely(key->objectid == BTRFS_TREE_RELOC_OBJECTID &&
key->offset == 0)) {
generic_err(leaf, slot, "invalid root id 0 for reloc tree");
return -EUCLEAN;
}
return 0;
}
static int check_dir_item(struct extent_buffer *leaf,
struct btrfs_key *key, struct btrfs_key *prev_key,
int slot)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_dir_item *di;
u32 item_size = btrfs_item_size(leaf, slot);
u32 cur = 0;
if (unlikely(!check_prev_ino(leaf, key, slot, prev_key)))
return -EUCLEAN;
di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
while (cur < item_size) {
struct btrfs_key location_key;
u32 name_len;
u32 data_len;
u32 max_name_len;
u32 total_size;
u32 name_hash;
u8 dir_type;
int ret;
/* header itself should not cross item boundary */
if (unlikely(cur + sizeof(*di) > item_size)) {
dir_item_err(leaf, slot,
"dir item header crosses item boundary, have %zu boundary %u",
cur + sizeof(*di), item_size);
return -EUCLEAN;
}
/* Location key check */
btrfs_dir_item_key_to_cpu(leaf, di, &location_key);
if (location_key.type == BTRFS_ROOT_ITEM_KEY) {
ret = check_root_key(leaf, &location_key, slot);
if (unlikely(ret < 0))
return ret;
} else if (location_key.type == BTRFS_INODE_ITEM_KEY ||
location_key.type == 0) {
ret = check_inode_key(leaf, &location_key, slot);
if (unlikely(ret < 0))
return ret;
} else {
dir_item_err(leaf, slot,
"invalid location key type, have %u, expect %u or %u",
location_key.type, BTRFS_ROOT_ITEM_KEY,
BTRFS_INODE_ITEM_KEY);
return -EUCLEAN;
}
/* dir type check */
dir_type = btrfs_dir_type(leaf, di);
if (unlikely(dir_type >= BTRFS_FT_MAX)) {
dir_item_err(leaf, slot,
"invalid dir item type, have %u expect [0, %u)",
dir_type, BTRFS_FT_MAX);
return -EUCLEAN;
}
if (unlikely(key->type == BTRFS_XATTR_ITEM_KEY &&
dir_type != BTRFS_FT_XATTR)) {
dir_item_err(leaf, slot,
"invalid dir item type for XATTR key, have %u expect %u",
dir_type, BTRFS_FT_XATTR);
return -EUCLEAN;
}
if (unlikely(dir_type == BTRFS_FT_XATTR &&
key->type != BTRFS_XATTR_ITEM_KEY)) {
dir_item_err(leaf, slot,
"xattr dir type found for non-XATTR key");
return -EUCLEAN;
}
if (dir_type == BTRFS_FT_XATTR)
max_name_len = XATTR_NAME_MAX;
else
max_name_len = BTRFS_NAME_LEN;
/* Name/data length check */
name_len = btrfs_dir_name_len(leaf, di);
data_len = btrfs_dir_data_len(leaf, di);
if (unlikely(name_len > max_name_len)) {
dir_item_err(leaf, slot,
"dir item name len too long, have %u max %u",
name_len, max_name_len);
return -EUCLEAN;
}
if (unlikely(name_len + data_len > BTRFS_MAX_XATTR_SIZE(fs_info))) {
dir_item_err(leaf, slot,
"dir item name and data len too long, have %u max %u",
name_len + data_len,
BTRFS_MAX_XATTR_SIZE(fs_info));
return -EUCLEAN;
}
if (unlikely(data_len && dir_type != BTRFS_FT_XATTR)) {
dir_item_err(leaf, slot,
"dir item with invalid data len, have %u expect 0",
data_len);
return -EUCLEAN;
}
total_size = sizeof(*di) + name_len + data_len;
/* header and name/data should not cross item boundary */
if (unlikely(cur + total_size > item_size)) {
dir_item_err(leaf, slot,
"dir item data crosses item boundary, have %u boundary %u",
cur + total_size, item_size);
return -EUCLEAN;
}
/*
* Special check for XATTR/DIR_ITEM, as key->offset is name
* hash, should match its name
*/
if (key->type == BTRFS_DIR_ITEM_KEY ||
key->type == BTRFS_XATTR_ITEM_KEY) {
char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
read_extent_buffer(leaf, namebuf,
(unsigned long)(di + 1), name_len);
name_hash = btrfs_name_hash(namebuf, name_len);
if (unlikely(key->offset != name_hash)) {
dir_item_err(leaf, slot,
"name hash mismatch with key, have 0x%016x expect 0x%016llx",
name_hash, key->offset);
return -EUCLEAN;
}
}
cur += total_size;
di = (struct btrfs_dir_item *)((void *)di + total_size);
}
return 0;
}
__printf(3, 4)
__cold
static void block_group_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_key key;
struct va_format vaf;
va_list args;
btrfs_item_key_to_cpu(eb, &key, slot);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(fs_info,
"corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
key.objectid, key.offset, &vaf);
va_end(args);
}
static int check_block_group_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_block_group_item bgi;
u32 item_size = btrfs_item_size(leaf, slot);
u64 chunk_objectid;
u64 flags;
u64 type;
/*
* Here we don't really care about alignment since extent allocator can
btrfs: tree-checker: Don't check max block group size as current max chunk size limit is unreliable [BUG] A completely valid btrfs will refuse to mount, with error message like: BTRFS critical (device sdb2): corrupt leaf: root=2 block=239681536 slot=172 \ bg_start=12018974720 bg_len=10888413184, invalid block group size, \ have 10888413184 expect (0, 10737418240] This has been reported several times as the 4.19 kernel is now being used. The filesystem refuses to mount, but is otherwise ok and booting 4.18 is a workaround. Btrfs check returns no error, and all kernels used on this fs is later than 2011, which should all have the 10G size limit commit. [CAUSE] For a 12 devices btrfs, we could allocate a chunk larger than 10G due to stripe stripe bump up. __btrfs_alloc_chunk() |- max_stripe_size = 1G |- max_chunk_size = 10G |- data_stripe = 11 |- if (1G * 11 > 10G) { stripe_size = 976128930; stripe_size = round_up(976128930, SZ_16M) = 989855744 However the final stripe_size (989855744) * 11 = 10888413184, which is still larger than 10G. [FIX] For the comprehensive check, we need to do the full check at chunk read time, and rely on bg <-> chunk mapping to do the check. We could just skip the length check for now. Fixes: fce466eab7ac ("btrfs: tree-checker: Verify block_group_item") Cc: stable@vger.kernel.org # v4.19+ Reported-by: Wang Yugui <wangyugui@e16-tech.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2018-11-23 09:06:36 +08:00
* handle it. We care more about the size.
*/
if (unlikely(key->offset == 0)) {
block_group_err(leaf, slot,
btrfs: tree-checker: Don't check max block group size as current max chunk size limit is unreliable [BUG] A completely valid btrfs will refuse to mount, with error message like: BTRFS critical (device sdb2): corrupt leaf: root=2 block=239681536 slot=172 \ bg_start=12018974720 bg_len=10888413184, invalid block group size, \ have 10888413184 expect (0, 10737418240] This has been reported several times as the 4.19 kernel is now being used. The filesystem refuses to mount, but is otherwise ok and booting 4.18 is a workaround. Btrfs check returns no error, and all kernels used on this fs is later than 2011, which should all have the 10G size limit commit. [CAUSE] For a 12 devices btrfs, we could allocate a chunk larger than 10G due to stripe stripe bump up. __btrfs_alloc_chunk() |- max_stripe_size = 1G |- max_chunk_size = 10G |- data_stripe = 11 |- if (1G * 11 > 10G) { stripe_size = 976128930; stripe_size = round_up(976128930, SZ_16M) = 989855744 However the final stripe_size (989855744) * 11 = 10888413184, which is still larger than 10G. [FIX] For the comprehensive check, we need to do the full check at chunk read time, and rely on bg <-> chunk mapping to do the check. We could just skip the length check for now. Fixes: fce466eab7ac ("btrfs: tree-checker: Verify block_group_item") Cc: stable@vger.kernel.org # v4.19+ Reported-by: Wang Yugui <wangyugui@e16-tech.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2018-11-23 09:06:36 +08:00
"invalid block group size 0");
return -EUCLEAN;
}
if (unlikely(item_size != sizeof(bgi))) {
block_group_err(leaf, slot,
"invalid item size, have %u expect %zu",
item_size, sizeof(bgi));
return -EUCLEAN;
}
read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
sizeof(bgi));
chunk_objectid = btrfs_stack_block_group_chunk_objectid(&bgi);
if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) {
/*
* We don't init the nr_global_roots until we load the global
* roots, so this could be 0 at mount time. If it's 0 we'll
* just assume we're fine, and later we'll check against our
* actual value.
*/
if (unlikely(fs_info->nr_global_roots &&
chunk_objectid >= fs_info->nr_global_roots)) {
block_group_err(leaf, slot,
"invalid block group global root id, have %llu, needs to be <= %llu",
chunk_objectid,
fs_info->nr_global_roots);
return -EUCLEAN;
}
} else if (unlikely(chunk_objectid != BTRFS_FIRST_CHUNK_TREE_OBJECTID)) {
block_group_err(leaf, slot,
"invalid block group chunk objectid, have %llu expect %llu",
btrfs_stack_block_group_chunk_objectid(&bgi),
BTRFS_FIRST_CHUNK_TREE_OBJECTID);
return -EUCLEAN;
}
if (unlikely(btrfs_stack_block_group_used(&bgi) > key->offset)) {
block_group_err(leaf, slot,
"invalid block group used, have %llu expect [0, %llu)",
btrfs_stack_block_group_used(&bgi), key->offset);
return -EUCLEAN;
}
flags = btrfs_stack_block_group_flags(&bgi);
if (unlikely(hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1)) {
block_group_err(leaf, slot,
"invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
flags & BTRFS_BLOCK_GROUP_PROFILE_MASK,
hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK));
return -EUCLEAN;
}
type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
if (unlikely(type != BTRFS_BLOCK_GROUP_DATA &&
type != BTRFS_BLOCK_GROUP_METADATA &&
type != BTRFS_BLOCK_GROUP_SYSTEM &&
type != (BTRFS_BLOCK_GROUP_METADATA |
BTRFS_BLOCK_GROUP_DATA))) {
block_group_err(leaf, slot,
"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx",
type, hweight64(type),
BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA,
BTRFS_BLOCK_GROUP_SYSTEM,
BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA);
return -EUCLEAN;
}
return 0;
}
__printf(4, 5)
__cold
static void chunk_err(const struct extent_buffer *leaf,
const struct btrfs_chunk *chunk, u64 logical,
const char *fmt, ...)
{
const struct btrfs_fs_info *fs_info = leaf->fs_info;
bool is_sb;
struct va_format vaf;
va_list args;
int i;
int slot = -1;
/* Only superblock eb is able to have such small offset */
is_sb = (leaf->start == BTRFS_SUPER_INFO_OFFSET);
if (!is_sb) {
/*
* Get the slot number by iterating through all slots, this
* would provide better readability.
*/
for (i = 0; i < btrfs_header_nritems(leaf); i++) {
if (btrfs_item_ptr_offset(leaf, i) ==
(unsigned long)chunk) {
slot = i;
break;
}
}
}
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (is_sb)
btrfs_crit(fs_info,
"corrupt superblock syschunk array: chunk_start=%llu, %pV",
logical, &vaf);
else
btrfs_crit(fs_info,
"corrupt leaf: root=%llu block=%llu slot=%d chunk_start=%llu, %pV",
BTRFS_CHUNK_TREE_OBJECTID, leaf->start, slot,
logical, &vaf);
va_end(args);
}
/*
* The common chunk check which could also work on super block sys chunk array.
*
* Return -EUCLEAN if anything is corrupted.
* Return 0 if everything is OK.
*/
int btrfs_check_chunk_valid(struct extent_buffer *leaf,
struct btrfs_chunk *chunk, u64 logical)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
u64 length;
btrfs: tree-checker: check if chunk item end overflows While mounting a crafted image provided by user, kernel panics due to the invalid chunk item whose end is less than start. [66.387422] loop: module loaded [66.389773] loop0: detected capacity change from 262144 to 0 [66.427708] BTRFS: device fsid a62e00e8-e94e-4200-8217-12444de93c2e devid 1 transid 12 /dev/loop0 scanned by mount (613) [66.431061] BTRFS info (device loop0): disk space caching is enabled [66.431078] BTRFS info (device loop0): has skinny extents [66.437101] BTRFS error: insert state: end < start 29360127 37748736 [66.437136] ------------[ cut here ]------------ [66.437140] WARNING: CPU: 16 PID: 613 at fs/btrfs/extent_io.c:557 insert_state.cold+0x1a/0x46 [btrfs] [66.437369] CPU: 16 PID: 613 Comm: mount Tainted: G O 5.11.0-rc1-custom #45 [66.437374] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ArchLinux 1.14.0-1 04/01/2014 [66.437378] RIP: 0010:insert_state.cold+0x1a/0x46 [btrfs] [66.437420] RSP: 0018:ffff93e5414c3908 EFLAGS: 00010286 [66.437427] RAX: 0000000000000000 RBX: 0000000001bfffff RCX: 0000000000000000 [66.437431] RDX: 0000000000000000 RSI: ffffffffb90d4660 RDI: 00000000ffffffff [66.437434] RBP: ffff93e5414c3938 R08: 0000000000000001 R09: 0000000000000001 [66.437438] R10: ffff93e5414c3658 R11: 0000000000000000 R12: ffff8ec782d72aa0 [66.437441] R13: ffff8ec78bc71628 R14: 0000000000000000 R15: 0000000002400000 [66.437447] FS: 00007f01386a8580(0000) GS:ffff8ec809000000(0000) knlGS:0000000000000000 [66.437451] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [66.437455] CR2: 00007f01382fa000 CR3: 0000000109a34000 CR4: 0000000000750ee0 [66.437460] PKRU: 55555554 [66.437464] Call Trace: [66.437475] set_extent_bit+0x652/0x740 [btrfs] [66.437539] set_extent_bits_nowait+0x1d/0x20 [btrfs] [66.437576] add_extent_mapping+0x1e0/0x2f0 [btrfs] [66.437621] read_one_chunk+0x33c/0x420 [btrfs] [66.437674] btrfs_read_chunk_tree+0x6a4/0x870 [btrfs] [66.437708] ? kvm_sched_clock_read+0x18/0x40 [66.437739] open_ctree+0xb32/0x1734 [btrfs] [66.437781] ? bdi_register_va+0x1b/0x20 [66.437788] ? super_setup_bdi_name+0x79/0xd0 [66.437810] btrfs_mount_root.cold+0x12/0xeb [btrfs] [66.437854] ? __kmalloc_track_caller+0x217/0x3b0 [66.437873] legacy_get_tree+0x34/0x60 [66.437880] vfs_get_tree+0x2d/0xc0 [66.437888] vfs_kern_mount.part.0+0x78/0xc0 [66.437897] vfs_kern_mount+0x13/0x20 [66.437902] btrfs_mount+0x11f/0x3c0 [btrfs] [66.437940] ? kfree+0x5ff/0x670 [66.437944] ? __kmalloc_track_caller+0x217/0x3b0 [66.437962] legacy_get_tree+0x34/0x60 [66.437974] vfs_get_tree+0x2d/0xc0 [66.437983] path_mount+0x48c/0xd30 [66.437998] __x64_sys_mount+0x108/0x140 [66.438011] do_syscall_64+0x38/0x50 [66.438018] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [66.438023] RIP: 0033:0x7f0138827f6e [66.438033] RSP: 002b:00007ffecd79edf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 [66.438040] RAX: ffffffffffffffda RBX: 00007f013894c264 RCX: 00007f0138827f6e [66.438044] RDX: 00005593a4a41360 RSI: 00005593a4a33690 RDI: 00005593a4a3a6c0 [66.438047] RBP: 00005593a4a33440 R08: 0000000000000000 R09: 0000000000000001 [66.438050] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [66.438054] R13: 00005593a4a3a6c0 R14: 00005593a4a41360 R15: 00005593a4a33440 [66.438078] irq event stamp: 18169 [66.438082] hardirqs last enabled at (18175): [<ffffffffb81154bf>] console_unlock+0x4ff/0x5f0 [66.438088] hardirqs last disabled at (18180): [<ffffffffb8115427>] console_unlock+0x467/0x5f0 [66.438092] softirqs last enabled at (16910): [<ffffffffb8a00fe2>] asm_call_irq_on_stack+0x12/0x20 [66.438097] softirqs last disabled at (16905): [<ffffffffb8a00fe2>] asm_call_irq_on_stack+0x12/0x20 [66.438103] ---[ end trace e114b111db64298b ]--- [66.438107] BTRFS error: found node 12582912 29360127 on insert of 37748736 29360127 [66.438127] BTRFS critical: panic in extent_io_tree_panic:679: locking error: extent tree was modified by another thread while locked (errno=-17 Object already exists) [66.441069] ------------[ cut here ]------------ [66.441072] kernel BUG at fs/btrfs/extent_io.c:679! [66.442064] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI [66.443018] CPU: 16 PID: 613 Comm: mount Tainted: G W O 5.11.0-rc1-custom #45 [66.444538] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ArchLinux 1.14.0-1 04/01/2014 [66.446223] RIP: 0010:extent_io_tree_panic.isra.0+0x23/0x25 [btrfs] [66.450878] RSP: 0018:ffff93e5414c3948 EFLAGS: 00010246 [66.451840] RAX: 0000000000000000 RBX: 0000000001bfffff RCX: 0000000000000000 [66.453141] RDX: 0000000000000000 RSI: ffffffffb90d4660 RDI: 00000000ffffffff [66.454445] RBP: ffff93e5414c3948 R08: 0000000000000001 R09: 0000000000000001 [66.455743] R10: ffff93e5414c3658 R11: 0000000000000000 R12: ffff8ec782d728c0 [66.457055] R13: ffff8ec78bc71628 R14: ffff8ec782d72aa0 R15: 0000000002400000 [66.458356] FS: 00007f01386a8580(0000) GS:ffff8ec809000000(0000) knlGS:0000000000000000 [66.459841] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [66.460895] CR2: 00007f01382fa000 CR3: 0000000109a34000 CR4: 0000000000750ee0 [66.462196] PKRU: 55555554 [66.462692] Call Trace: [66.463139] set_extent_bit.cold+0x30/0x98 [btrfs] [66.464049] set_extent_bits_nowait+0x1d/0x20 [btrfs] [66.490466] add_extent_mapping+0x1e0/0x2f0 [btrfs] [66.514097] read_one_chunk+0x33c/0x420 [btrfs] [66.534976] btrfs_read_chunk_tree+0x6a4/0x870 [btrfs] [66.555718] ? kvm_sched_clock_read+0x18/0x40 [66.575758] open_ctree+0xb32/0x1734 [btrfs] [66.595272] ? bdi_register_va+0x1b/0x20 [66.614638] ? super_setup_bdi_name+0x79/0xd0 [66.633809] btrfs_mount_root.cold+0x12/0xeb [btrfs] [66.652938] ? __kmalloc_track_caller+0x217/0x3b0 [66.671925] legacy_get_tree+0x34/0x60 [66.690300] vfs_get_tree+0x2d/0xc0 [66.708221] vfs_kern_mount.part.0+0x78/0xc0 [66.725808] vfs_kern_mount+0x13/0x20 [66.742730] btrfs_mount+0x11f/0x3c0 [btrfs] [66.759350] ? kfree+0x5ff/0x670 [66.775441] ? __kmalloc_track_caller+0x217/0x3b0 [66.791750] legacy_get_tree+0x34/0x60 [66.807494] vfs_get_tree+0x2d/0xc0 [66.823349] path_mount+0x48c/0xd30 [66.838753] __x64_sys_mount+0x108/0x140 [66.854412] do_syscall_64+0x38/0x50 [66.869673] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [66.885093] RIP: 0033:0x7f0138827f6e [66.945613] RSP: 002b:00007ffecd79edf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 [66.977214] RAX: ffffffffffffffda RBX: 00007f013894c264 RCX: 00007f0138827f6e [66.994266] RDX: 00005593a4a41360 RSI: 00005593a4a33690 RDI: 00005593a4a3a6c0 [67.011544] RBP: 00005593a4a33440 R08: 0000000000000000 R09: 0000000000000001 [67.028836] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [67.045812] R13: 00005593a4a3a6c0 R14: 00005593a4a41360 R15: 00005593a4a33440 [67.216138] ---[ end trace e114b111db64298c ]--- [67.237089] RIP: 0010:extent_io_tree_panic.isra.0+0x23/0x25 [btrfs] [67.325317] RSP: 0018:ffff93e5414c3948 EFLAGS: 00010246 [67.347946] RAX: 0000000000000000 RBX: 0000000001bfffff RCX: 0000000000000000 [67.371343] RDX: 0000000000000000 RSI: ffffffffb90d4660 RDI: 00000000ffffffff [67.394757] RBP: ffff93e5414c3948 R08: 0000000000000001 R09: 0000000000000001 [67.418409] R10: ffff93e5414c3658 R11: 0000000000000000 R12: ffff8ec782d728c0 [67.441906] R13: ffff8ec78bc71628 R14: ffff8ec782d72aa0 R15: 0000000002400000 [67.465436] FS: 00007f01386a8580(0000) GS:ffff8ec809000000(0000) knlGS:0000000000000000 [67.511660] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [67.535047] CR2: 00007f01382fa000 CR3: 0000000109a34000 CR4: 0000000000750ee0 [67.558449] PKRU: 55555554 [67.581146] note: mount[613] exited with preempt_count 2 The image has a chunk item which has a logical start 37748736 and length 18446744073701163008 (-8M). The calculated end 29360127 overflows. EEXIST was caught by insert_state() because of the duplicate end and extent_io_tree_panic() was called. Add overflow check of chunk item end to tree checker so it can be detected early at mount time. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=208929 CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-03 17:28:04 +08:00
u64 chunk_end;
u64 stripe_len;
u16 num_stripes;
u16 sub_stripes;
u64 type;
u64 features;
bool mixed = false;
int raid_index;
int nparity;
int ncopies;
length = btrfs_chunk_length(leaf, chunk);
stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
type = btrfs_chunk_type(leaf, chunk);
raid_index = btrfs_bg_flags_to_raid_index(type);
ncopies = btrfs_raid_array[raid_index].ncopies;
nparity = btrfs_raid_array[raid_index].nparity;
if (unlikely(!num_stripes)) {
chunk_err(leaf, chunk, logical,
"invalid chunk num_stripes, have %u", num_stripes);
return -EUCLEAN;
}
if (unlikely(num_stripes < ncopies)) {
chunk_err(leaf, chunk, logical,
"invalid chunk num_stripes < ncopies, have %u < %d",
num_stripes, ncopies);
return -EUCLEAN;
}
if (unlikely(nparity && num_stripes == nparity)) {
chunk_err(leaf, chunk, logical,
"invalid chunk num_stripes == nparity, have %u == %d",
num_stripes, nparity);
return -EUCLEAN;
}
if (unlikely(!IS_ALIGNED(logical, fs_info->sectorsize))) {
chunk_err(leaf, chunk, logical,
"invalid chunk logical, have %llu should aligned to %u",
logical, fs_info->sectorsize);
return -EUCLEAN;
}
if (unlikely(btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize)) {
chunk_err(leaf, chunk, logical,
"invalid chunk sectorsize, have %u expect %u",
btrfs_chunk_sector_size(leaf, chunk),
fs_info->sectorsize);
return -EUCLEAN;
}
if (unlikely(!length || !IS_ALIGNED(length, fs_info->sectorsize))) {
chunk_err(leaf, chunk, logical,
"invalid chunk length, have %llu", length);
return -EUCLEAN;
}
btrfs: tree-checker: check if chunk item end overflows While mounting a crafted image provided by user, kernel panics due to the invalid chunk item whose end is less than start. [66.387422] loop: module loaded [66.389773] loop0: detected capacity change from 262144 to 0 [66.427708] BTRFS: device fsid a62e00e8-e94e-4200-8217-12444de93c2e devid 1 transid 12 /dev/loop0 scanned by mount (613) [66.431061] BTRFS info (device loop0): disk space caching is enabled [66.431078] BTRFS info (device loop0): has skinny extents [66.437101] BTRFS error: insert state: end < start 29360127 37748736 [66.437136] ------------[ cut here ]------------ [66.437140] WARNING: CPU: 16 PID: 613 at fs/btrfs/extent_io.c:557 insert_state.cold+0x1a/0x46 [btrfs] [66.437369] CPU: 16 PID: 613 Comm: mount Tainted: G O 5.11.0-rc1-custom #45 [66.437374] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ArchLinux 1.14.0-1 04/01/2014 [66.437378] RIP: 0010:insert_state.cold+0x1a/0x46 [btrfs] [66.437420] RSP: 0018:ffff93e5414c3908 EFLAGS: 00010286 [66.437427] RAX: 0000000000000000 RBX: 0000000001bfffff RCX: 0000000000000000 [66.437431] RDX: 0000000000000000 RSI: ffffffffb90d4660 RDI: 00000000ffffffff [66.437434] RBP: ffff93e5414c3938 R08: 0000000000000001 R09: 0000000000000001 [66.437438] R10: ffff93e5414c3658 R11: 0000000000000000 R12: ffff8ec782d72aa0 [66.437441] R13: ffff8ec78bc71628 R14: 0000000000000000 R15: 0000000002400000 [66.437447] FS: 00007f01386a8580(0000) GS:ffff8ec809000000(0000) knlGS:0000000000000000 [66.437451] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [66.437455] CR2: 00007f01382fa000 CR3: 0000000109a34000 CR4: 0000000000750ee0 [66.437460] PKRU: 55555554 [66.437464] Call Trace: [66.437475] set_extent_bit+0x652/0x740 [btrfs] [66.437539] set_extent_bits_nowait+0x1d/0x20 [btrfs] [66.437576] add_extent_mapping+0x1e0/0x2f0 [btrfs] [66.437621] read_one_chunk+0x33c/0x420 [btrfs] [66.437674] btrfs_read_chunk_tree+0x6a4/0x870 [btrfs] [66.437708] ? kvm_sched_clock_read+0x18/0x40 [66.437739] open_ctree+0xb32/0x1734 [btrfs] [66.437781] ? bdi_register_va+0x1b/0x20 [66.437788] ? super_setup_bdi_name+0x79/0xd0 [66.437810] btrfs_mount_root.cold+0x12/0xeb [btrfs] [66.437854] ? __kmalloc_track_caller+0x217/0x3b0 [66.437873] legacy_get_tree+0x34/0x60 [66.437880] vfs_get_tree+0x2d/0xc0 [66.437888] vfs_kern_mount.part.0+0x78/0xc0 [66.437897] vfs_kern_mount+0x13/0x20 [66.437902] btrfs_mount+0x11f/0x3c0 [btrfs] [66.437940] ? kfree+0x5ff/0x670 [66.437944] ? __kmalloc_track_caller+0x217/0x3b0 [66.437962] legacy_get_tree+0x34/0x60 [66.437974] vfs_get_tree+0x2d/0xc0 [66.437983] path_mount+0x48c/0xd30 [66.437998] __x64_sys_mount+0x108/0x140 [66.438011] do_syscall_64+0x38/0x50 [66.438018] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [66.438023] RIP: 0033:0x7f0138827f6e [66.438033] RSP: 002b:00007ffecd79edf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 [66.438040] RAX: ffffffffffffffda RBX: 00007f013894c264 RCX: 00007f0138827f6e [66.438044] RDX: 00005593a4a41360 RSI: 00005593a4a33690 RDI: 00005593a4a3a6c0 [66.438047] RBP: 00005593a4a33440 R08: 0000000000000000 R09: 0000000000000001 [66.438050] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [66.438054] R13: 00005593a4a3a6c0 R14: 00005593a4a41360 R15: 00005593a4a33440 [66.438078] irq event stamp: 18169 [66.438082] hardirqs last enabled at (18175): [<ffffffffb81154bf>] console_unlock+0x4ff/0x5f0 [66.438088] hardirqs last disabled at (18180): [<ffffffffb8115427>] console_unlock+0x467/0x5f0 [66.438092] softirqs last enabled at (16910): [<ffffffffb8a00fe2>] asm_call_irq_on_stack+0x12/0x20 [66.438097] softirqs last disabled at (16905): [<ffffffffb8a00fe2>] asm_call_irq_on_stack+0x12/0x20 [66.438103] ---[ end trace e114b111db64298b ]--- [66.438107] BTRFS error: found node 12582912 29360127 on insert of 37748736 29360127 [66.438127] BTRFS critical: panic in extent_io_tree_panic:679: locking error: extent tree was modified by another thread while locked (errno=-17 Object already exists) [66.441069] ------------[ cut here ]------------ [66.441072] kernel BUG at fs/btrfs/extent_io.c:679! [66.442064] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI [66.443018] CPU: 16 PID: 613 Comm: mount Tainted: G W O 5.11.0-rc1-custom #45 [66.444538] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ArchLinux 1.14.0-1 04/01/2014 [66.446223] RIP: 0010:extent_io_tree_panic.isra.0+0x23/0x25 [btrfs] [66.450878] RSP: 0018:ffff93e5414c3948 EFLAGS: 00010246 [66.451840] RAX: 0000000000000000 RBX: 0000000001bfffff RCX: 0000000000000000 [66.453141] RDX: 0000000000000000 RSI: ffffffffb90d4660 RDI: 00000000ffffffff [66.454445] RBP: ffff93e5414c3948 R08: 0000000000000001 R09: 0000000000000001 [66.455743] R10: ffff93e5414c3658 R11: 0000000000000000 R12: ffff8ec782d728c0 [66.457055] R13: ffff8ec78bc71628 R14: ffff8ec782d72aa0 R15: 0000000002400000 [66.458356] FS: 00007f01386a8580(0000) GS:ffff8ec809000000(0000) knlGS:0000000000000000 [66.459841] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [66.460895] CR2: 00007f01382fa000 CR3: 0000000109a34000 CR4: 0000000000750ee0 [66.462196] PKRU: 55555554 [66.462692] Call Trace: [66.463139] set_extent_bit.cold+0x30/0x98 [btrfs] [66.464049] set_extent_bits_nowait+0x1d/0x20 [btrfs] [66.490466] add_extent_mapping+0x1e0/0x2f0 [btrfs] [66.514097] read_one_chunk+0x33c/0x420 [btrfs] [66.534976] btrfs_read_chunk_tree+0x6a4/0x870 [btrfs] [66.555718] ? kvm_sched_clock_read+0x18/0x40 [66.575758] open_ctree+0xb32/0x1734 [btrfs] [66.595272] ? bdi_register_va+0x1b/0x20 [66.614638] ? super_setup_bdi_name+0x79/0xd0 [66.633809] btrfs_mount_root.cold+0x12/0xeb [btrfs] [66.652938] ? __kmalloc_track_caller+0x217/0x3b0 [66.671925] legacy_get_tree+0x34/0x60 [66.690300] vfs_get_tree+0x2d/0xc0 [66.708221] vfs_kern_mount.part.0+0x78/0xc0 [66.725808] vfs_kern_mount+0x13/0x20 [66.742730] btrfs_mount+0x11f/0x3c0 [btrfs] [66.759350] ? kfree+0x5ff/0x670 [66.775441] ? __kmalloc_track_caller+0x217/0x3b0 [66.791750] legacy_get_tree+0x34/0x60 [66.807494] vfs_get_tree+0x2d/0xc0 [66.823349] path_mount+0x48c/0xd30 [66.838753] __x64_sys_mount+0x108/0x140 [66.854412] do_syscall_64+0x38/0x50 [66.869673] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [66.885093] RIP: 0033:0x7f0138827f6e [66.945613] RSP: 002b:00007ffecd79edf8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 [66.977214] RAX: ffffffffffffffda RBX: 00007f013894c264 RCX: 00007f0138827f6e [66.994266] RDX: 00005593a4a41360 RSI: 00005593a4a33690 RDI: 00005593a4a3a6c0 [67.011544] RBP: 00005593a4a33440 R08: 0000000000000000 R09: 0000000000000001 [67.028836] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [67.045812] R13: 00005593a4a3a6c0 R14: 00005593a4a41360 R15: 00005593a4a33440 [67.216138] ---[ end trace e114b111db64298c ]--- [67.237089] RIP: 0010:extent_io_tree_panic.isra.0+0x23/0x25 [btrfs] [67.325317] RSP: 0018:ffff93e5414c3948 EFLAGS: 00010246 [67.347946] RAX: 0000000000000000 RBX: 0000000001bfffff RCX: 0000000000000000 [67.371343] RDX: 0000000000000000 RSI: ffffffffb90d4660 RDI: 00000000ffffffff [67.394757] RBP: ffff93e5414c3948 R08: 0000000000000001 R09: 0000000000000001 [67.418409] R10: ffff93e5414c3658 R11: 0000000000000000 R12: ffff8ec782d728c0 [67.441906] R13: ffff8ec78bc71628 R14: ffff8ec782d72aa0 R15: 0000000002400000 [67.465436] FS: 00007f01386a8580(0000) GS:ffff8ec809000000(0000) knlGS:0000000000000000 [67.511660] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [67.535047] CR2: 00007f01382fa000 CR3: 0000000109a34000 CR4: 0000000000750ee0 [67.558449] PKRU: 55555554 [67.581146] note: mount[613] exited with preempt_count 2 The image has a chunk item which has a logical start 37748736 and length 18446744073701163008 (-8M). The calculated end 29360127 overflows. EEXIST was caught by insert_state() because of the duplicate end and extent_io_tree_panic() was called. Add overflow check of chunk item end to tree checker so it can be detected early at mount time. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=208929 CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Anand Jain <anand.jain@oracle.com> Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-01-03 17:28:04 +08:00
if (unlikely(check_add_overflow(logical, length, &chunk_end))) {
chunk_err(leaf, chunk, logical,
"invalid chunk logical start and length, have logical start %llu length %llu",
logical, length);
return -EUCLEAN;
}
if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) {
chunk_err(leaf, chunk, logical,
"invalid chunk stripe length: %llu",
stripe_len);
return -EUCLEAN;
}
if (unlikely(type & ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
BTRFS_BLOCK_GROUP_PROFILE_MASK))) {
chunk_err(leaf, chunk, logical,
"unrecognized chunk type: 0x%llx",
~(BTRFS_BLOCK_GROUP_TYPE_MASK |
BTRFS_BLOCK_GROUP_PROFILE_MASK) &
btrfs_chunk_type(leaf, chunk));
return -EUCLEAN;
}
if (unlikely(!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) &&
(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0)) {
chunk_err(leaf, chunk, logical,
"invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set",
type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
return -EUCLEAN;
}
if (unlikely((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0)) {
chunk_err(leaf, chunk, logical,
"missing chunk type flag, have 0x%llx one bit must be set in 0x%llx",
type, BTRFS_BLOCK_GROUP_TYPE_MASK);
return -EUCLEAN;
}
if (unlikely((type & BTRFS_BLOCK_GROUP_SYSTEM) &&
(type & (BTRFS_BLOCK_GROUP_METADATA |
BTRFS_BLOCK_GROUP_DATA)))) {
chunk_err(leaf, chunk, logical,
"system chunk with data or metadata type: 0x%llx",
type);
return -EUCLEAN;
}
features = btrfs_super_incompat_flags(fs_info->super_copy);
if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
mixed = true;
if (!mixed) {
if (unlikely((type & BTRFS_BLOCK_GROUP_METADATA) &&
(type & BTRFS_BLOCK_GROUP_DATA))) {
chunk_err(leaf, chunk, logical,
"mixed chunk type in non-mixed mode: 0x%llx", type);
return -EUCLEAN;
}
}
if (unlikely((type & BTRFS_BLOCK_GROUP_RAID10 &&
sub_stripes != btrfs_raid_array[BTRFS_RAID_RAID10].sub_stripes) ||
(type & BTRFS_BLOCK_GROUP_RAID1 &&
num_stripes != btrfs_raid_array[BTRFS_RAID_RAID1].devs_min) ||
(type & BTRFS_BLOCK_GROUP_RAID1C3 &&
num_stripes != btrfs_raid_array[BTRFS_RAID_RAID1C3].devs_min) ||
(type & BTRFS_BLOCK_GROUP_RAID1C4 &&
num_stripes != btrfs_raid_array[BTRFS_RAID_RAID1C4].devs_min) ||
(type & BTRFS_BLOCK_GROUP_RAID5 &&
num_stripes < btrfs_raid_array[BTRFS_RAID_RAID5].devs_min) ||
(type & BTRFS_BLOCK_GROUP_RAID6 &&
num_stripes < btrfs_raid_array[BTRFS_RAID_RAID6].devs_min) ||
(type & BTRFS_BLOCK_GROUP_DUP &&
num_stripes != btrfs_raid_array[BTRFS_RAID_DUP].dev_stripes) ||
((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 &&
num_stripes != btrfs_raid_array[BTRFS_RAID_SINGLE].dev_stripes))) {
chunk_err(leaf, chunk, logical,
"invalid num_stripes:sub_stripes %u:%u for profile %llu",
num_stripes, sub_stripes,
type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
return -EUCLEAN;
}
return 0;
}
/*
* Enhanced version of chunk item checker.
*
* The common btrfs_check_chunk_valid() doesn't check item size since it needs
* to work on super block sys_chunk_array which doesn't have full item ptr.
*/
static int check_leaf_chunk_item(struct extent_buffer *leaf,
struct btrfs_chunk *chunk,
struct btrfs_key *key, int slot)
{
int num_stripes;
if (unlikely(btrfs_item_size(leaf, slot) < sizeof(struct btrfs_chunk))) {
chunk_err(leaf, chunk, key->offset,
"invalid chunk item size: have %u expect [%zu, %u)",
btrfs_item_size(leaf, slot),
sizeof(struct btrfs_chunk),
BTRFS_LEAF_DATA_SIZE(leaf->fs_info));
return -EUCLEAN;
}
num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
/* Let btrfs_check_chunk_valid() handle this error type */
if (num_stripes == 0)
goto out;
if (unlikely(btrfs_chunk_item_size(num_stripes) !=
btrfs_item_size(leaf, slot))) {
chunk_err(leaf, chunk, key->offset,
"invalid chunk item size: have %u expect %lu",
btrfs_item_size(leaf, slot),
btrfs_chunk_item_size(num_stripes));
return -EUCLEAN;
}
out:
return btrfs_check_chunk_valid(leaf, chunk, key->offset);
}
__printf(3, 4)
__cold
static void dev_item_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
struct btrfs_key key;
struct va_format vaf;
va_list args;
btrfs_item_key_to_cpu(eb, &key, slot);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(eb->fs_info,
"corrupt %s: root=%llu block=%llu slot=%d devid=%llu %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
key.objectid, &vaf);
va_end(args);
}
static int check_dev_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
struct btrfs_dev_item *ditem;
const u32 item_size = btrfs_item_size(leaf, slot);
if (unlikely(key->objectid != BTRFS_DEV_ITEMS_OBJECTID)) {
dev_item_err(leaf, slot,
"invalid objectid: has=%llu expect=%llu",
key->objectid, BTRFS_DEV_ITEMS_OBJECTID);
return -EUCLEAN;
}
if (unlikely(item_size != sizeof(*ditem))) {
dev_item_err(leaf, slot, "invalid item size: has %u expect %zu",
item_size, sizeof(*ditem));
return -EUCLEAN;
}
ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item);
if (unlikely(btrfs_device_id(leaf, ditem) != key->offset)) {
dev_item_err(leaf, slot,
"devid mismatch: key has=%llu item has=%llu",
key->offset, btrfs_device_id(leaf, ditem));
return -EUCLEAN;
}
/*
* For device total_bytes, we don't have reliable way to check it, as
* it can be 0 for device removal. Device size check can only be done
* by dev extents check.
*/
if (unlikely(btrfs_device_bytes_used(leaf, ditem) >
btrfs_device_total_bytes(leaf, ditem))) {
dev_item_err(leaf, slot,
"invalid bytes used: have %llu expect [0, %llu]",
btrfs_device_bytes_used(leaf, ditem),
btrfs_device_total_bytes(leaf, ditem));
return -EUCLEAN;
}
/*
* Remaining members like io_align/type/gen/dev_group aren't really
* utilized. Skip them to make later usage of them easier.
*/
return 0;
}
static int check_inode_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_inode_item *iitem;
u64 super_gen = btrfs_super_generation(fs_info->super_copy);
u32 valid_mask = (S_IFMT | S_ISUID | S_ISGID | S_ISVTX | 0777);
btrfs: tree-checker: check item_size for inode_item while mounting the crafted image, out-of-bounds access happens: [350.429619] UBSAN: array-index-out-of-bounds in fs/btrfs/struct-funcs.c:161:1 [350.429636] index 1048096 is out of range for type 'page *[16]' [350.429650] CPU: 0 PID: 9 Comm: kworker/u8:1 Not tainted 5.16.0-rc4 #1 [350.429652] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [350.429653] Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs] [350.429772] Call Trace: [350.429774] <TASK> [350.429776] dump_stack_lvl+0x47/0x5c [350.429780] ubsan_epilogue+0x5/0x50 [350.429786] __ubsan_handle_out_of_bounds+0x66/0x70 [350.429791] btrfs_get_16+0xfd/0x120 [btrfs] [350.429832] check_leaf+0x754/0x1a40 [btrfs] [350.429874] ? filemap_read+0x34a/0x390 [350.429878] ? load_balance+0x175/0xfc0 [350.429881] validate_extent_buffer+0x244/0x310 [btrfs] [350.429911] btrfs_validate_metadata_buffer+0xf8/0x100 [btrfs] [350.429935] end_bio_extent_readpage+0x3af/0x850 [btrfs] [350.429969] ? newidle_balance+0x259/0x480 [350.429972] end_workqueue_fn+0x29/0x40 [btrfs] [350.429995] btrfs_work_helper+0x71/0x330 [btrfs] [350.430030] ? __schedule+0x2fb/0xa40 [350.430033] process_one_work+0x1f6/0x400 [350.430035] ? process_one_work+0x400/0x400 [350.430036] worker_thread+0x2d/0x3d0 [350.430037] ? process_one_work+0x400/0x400 [350.430038] kthread+0x165/0x190 [350.430041] ? set_kthread_struct+0x40/0x40 [350.430043] ret_from_fork+0x1f/0x30 [350.430047] </TASK> [350.430077] BTRFS warning (device loop0): bad eb member start: ptr 0xffe20f4e start 20975616 member offset 4293005178 size 2 check_leaf() is checking the leaf: corrupt leaf: root=4 block=29396992 slot=1, bad key order, prev (16140901064495857664 1 0) current (1 204 12582912) leaf 29396992 items 6 free space 3565 generation 6 owner DEV_TREE leaf 29396992 flags 0x1(WRITTEN) backref revision 1 fs uuid a62e00e8-e94e-4200-8217-12444de93c2e chunk uuid cecbd0f7-9ca0-441e-ae9f-f782f9732bd8 item 0 key (16140901064495857664 INODE_ITEM 0) itemoff 3955 itemsize 40 generation 0 transid 0 size 0 nbytes 17592186044416 block group 0 mode 52667 links 33 uid 0 gid 2104132511 rdev 94223634821136 sequence 100305 flags 0x2409000(none) atime 0.0 (1970-01-01 08:00:00) ctime 2973280098083405823.4294967295 (-269783007-01-01 21:37:03) mtime 18446744071572723616.4026825121 (1902-04-16 12:40:00) otime 9249929404488876031.4294967295 (622322949-04-16 04:25:58) item 1 key (1 DEV_EXTENT 12582912) itemoff 3907 itemsize 48 dev extent chunk_tree 3 chunk_objectid 256 chunk_offset 12582912 length 8388608 chunk_tree_uuid cecbd0f7-9ca0-441e-ae9f-f782f9732bd8 The corrupted leaf of device tree has an inode item. The leaf passed checksum and others checks in validate_extent_buffer until check_leaf_item(). Because of the key type BTRFS_INODE_ITEM, check_inode_item() is called even we are in the device tree. Since the item offset + sizeof(struct btrfs_inode_item) > eb->len, out-of-bounds access is triggered. The item end vs leaf boundary check has been done before check_leaf_item(), so fix it by checking item size in check_inode_item() before access of the inode item in extent buffer. Other check functions except check_dev_item() in check_leaf_item() have their item size checks. The commit for check_dev_item() is followed. No regression observed during running fstests. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215299 CC: stable@vger.kernel.org # 5.10+ CC: Wenqing Liu <wenqingliu0120@gmail.com> Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-21 17:33:34 +08:00
const u32 item_size = btrfs_item_size(leaf, slot);
u32 mode;
int ret;
btrfs: add ro compat flags to inodes Currently, inode flags are fully backwards incompatible in btrfs. If we introduce a new inode flag, then tree-checker will detect it and fail. This can even cause us to fail to mount entirely. To make it possible to introduce new flags which can be read-only compatible, like VERITY, we add new ro flags to btrfs without treating them quite so harshly in tree-checker. A read-only file system can survive an unexpected flag, and can be mounted. As for the implementation, it unfortunately gets a little complicated. The on-disk representation of the inode, btrfs_inode_item, has an __le64 for flags but the in-memory representation, btrfs_inode, uses a u32. David Sterba had the nice idea that we could reclaim those wasted 32 bits on disk and use them for the new ro_compat flags. It turns out that the tree-checker code which checks for unknown flags is broken, and ignores the upper 32 bits we are hoping to use. The issue is that the flags use the literal 1 rather than 1ULL, so the flags are signed ints, and one of them is specifically (1 << 31). As a result, the mask which ORs the flags is a negative integer on machines where int is 32 bit twos complement. When tree-checker evaluates the expression: btrfs_inode_flags(leaf, iitem) & ~BTRFS_INODE_FLAG_MASK) The mask is something like 0x80000abc, which gets promoted to u64 with sign extension to 0xffffffff80000abc. Negating that 64 bit mask leaves all the upper bits zeroed, and we can't detect unexpected flags. This suggests that we can't use those bits after all. Luckily, we have good reason to believe that they are zero anyway. Inode flags are metadata, which is always checksummed, so any bit flips that would introduce 1s would cause a checksum failure anyway (excluding the improbable case of the checksum getting corrupted exactly badly). Further, unless the 1 << 31 flag is used, the cast to u64 of the 32 bit inode flag should preserve its value and not add leading zeroes (at least for twos complement). The only place that flag (BTRFS_INODE_ROOT_ITEM_INIT) is used is in a special inode embedded in the root item, and indeed for that inode we see 0xffffffff80000000 as the flags on disk. However, that inode is never seen by tree checker, nor is it used in a context where verity might be meaningful. Theoretically, a future ro flag might cause trouble on that inode, so we should proactively clean up that mess before it does. With the introduction of the new ro flags, keep two separate unsigned masks and check them against the appropriate u32. Since we no longer run afoul of sign extension, this also stops writing out 0xffffffff80000000 in root_item inodes going forward. Signed-off-by: Boris Burkov <boris@bur.io> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-01 04:01:48 +08:00
u32 flags;
u32 ro_flags;
ret = check_inode_key(leaf, key, slot);
if (unlikely(ret < 0))
return ret;
btrfs: tree-checker: check item_size for inode_item while mounting the crafted image, out-of-bounds access happens: [350.429619] UBSAN: array-index-out-of-bounds in fs/btrfs/struct-funcs.c:161:1 [350.429636] index 1048096 is out of range for type 'page *[16]' [350.429650] CPU: 0 PID: 9 Comm: kworker/u8:1 Not tainted 5.16.0-rc4 #1 [350.429652] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [350.429653] Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs] [350.429772] Call Trace: [350.429774] <TASK> [350.429776] dump_stack_lvl+0x47/0x5c [350.429780] ubsan_epilogue+0x5/0x50 [350.429786] __ubsan_handle_out_of_bounds+0x66/0x70 [350.429791] btrfs_get_16+0xfd/0x120 [btrfs] [350.429832] check_leaf+0x754/0x1a40 [btrfs] [350.429874] ? filemap_read+0x34a/0x390 [350.429878] ? load_balance+0x175/0xfc0 [350.429881] validate_extent_buffer+0x244/0x310 [btrfs] [350.429911] btrfs_validate_metadata_buffer+0xf8/0x100 [btrfs] [350.429935] end_bio_extent_readpage+0x3af/0x850 [btrfs] [350.429969] ? newidle_balance+0x259/0x480 [350.429972] end_workqueue_fn+0x29/0x40 [btrfs] [350.429995] btrfs_work_helper+0x71/0x330 [btrfs] [350.430030] ? __schedule+0x2fb/0xa40 [350.430033] process_one_work+0x1f6/0x400 [350.430035] ? process_one_work+0x400/0x400 [350.430036] worker_thread+0x2d/0x3d0 [350.430037] ? process_one_work+0x400/0x400 [350.430038] kthread+0x165/0x190 [350.430041] ? set_kthread_struct+0x40/0x40 [350.430043] ret_from_fork+0x1f/0x30 [350.430047] </TASK> [350.430077] BTRFS warning (device loop0): bad eb member start: ptr 0xffe20f4e start 20975616 member offset 4293005178 size 2 check_leaf() is checking the leaf: corrupt leaf: root=4 block=29396992 slot=1, bad key order, prev (16140901064495857664 1 0) current (1 204 12582912) leaf 29396992 items 6 free space 3565 generation 6 owner DEV_TREE leaf 29396992 flags 0x1(WRITTEN) backref revision 1 fs uuid a62e00e8-e94e-4200-8217-12444de93c2e chunk uuid cecbd0f7-9ca0-441e-ae9f-f782f9732bd8 item 0 key (16140901064495857664 INODE_ITEM 0) itemoff 3955 itemsize 40 generation 0 transid 0 size 0 nbytes 17592186044416 block group 0 mode 52667 links 33 uid 0 gid 2104132511 rdev 94223634821136 sequence 100305 flags 0x2409000(none) atime 0.0 (1970-01-01 08:00:00) ctime 2973280098083405823.4294967295 (-269783007-01-01 21:37:03) mtime 18446744071572723616.4026825121 (1902-04-16 12:40:00) otime 9249929404488876031.4294967295 (622322949-04-16 04:25:58) item 1 key (1 DEV_EXTENT 12582912) itemoff 3907 itemsize 48 dev extent chunk_tree 3 chunk_objectid 256 chunk_offset 12582912 length 8388608 chunk_tree_uuid cecbd0f7-9ca0-441e-ae9f-f782f9732bd8 The corrupted leaf of device tree has an inode item. The leaf passed checksum and others checks in validate_extent_buffer until check_leaf_item(). Because of the key type BTRFS_INODE_ITEM, check_inode_item() is called even we are in the device tree. Since the item offset + sizeof(struct btrfs_inode_item) > eb->len, out-of-bounds access is triggered. The item end vs leaf boundary check has been done before check_leaf_item(), so fix it by checking item size in check_inode_item() before access of the inode item in extent buffer. Other check functions except check_dev_item() in check_leaf_item() have their item size checks. The commit for check_dev_item() is followed. No regression observed during running fstests. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215299 CC: stable@vger.kernel.org # 5.10+ CC: Wenqing Liu <wenqingliu0120@gmail.com> Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-01-21 17:33:34 +08:00
if (unlikely(item_size != sizeof(*iitem))) {
generic_err(leaf, slot, "invalid item size: has %u expect %zu",
item_size, sizeof(*iitem));
return -EUCLEAN;
}
iitem = btrfs_item_ptr(leaf, slot, struct btrfs_inode_item);
/* Here we use super block generation + 1 to handle log tree */
if (unlikely(btrfs_inode_generation(leaf, iitem) > super_gen + 1)) {
inode_item_err(leaf, slot,
"invalid inode generation: has %llu expect (0, %llu]",
btrfs_inode_generation(leaf, iitem),
super_gen + 1);
return -EUCLEAN;
}
/* Note for ROOT_TREE_DIR_ITEM, mkfs could set its transid 0 */
if (unlikely(btrfs_inode_transid(leaf, iitem) > super_gen + 1)) {
inode_item_err(leaf, slot,
"invalid inode transid: has %llu expect [0, %llu]",
btrfs_inode_transid(leaf, iitem), super_gen + 1);
return -EUCLEAN;
}
/*
* For size and nbytes it's better not to be too strict, as for dir
* item its size/nbytes can easily get wrong, but doesn't affect
* anything in the fs. So here we skip the check.
*/
mode = btrfs_inode_mode(leaf, iitem);
if (unlikely(mode & ~valid_mask)) {
inode_item_err(leaf, slot,
"unknown mode bit detected: 0x%x",
mode & ~valid_mask);
return -EUCLEAN;
}
/*
* S_IFMT is not bit mapped so we can't completely rely on
* is_power_of_2/has_single_bit_set, but it can save us from checking
* FIFO/CHR/DIR/REG. Only needs to check BLK, LNK and SOCKS
*/
if (!has_single_bit_set(mode & S_IFMT)) {
if (unlikely(!S_ISLNK(mode) && !S_ISBLK(mode) && !S_ISSOCK(mode))) {
inode_item_err(leaf, slot,
"invalid mode: has 0%o expect valid S_IF* bit(s)",
mode & S_IFMT);
return -EUCLEAN;
}
}
if (unlikely(S_ISDIR(mode) && btrfs_inode_nlink(leaf, iitem) > 1)) {
inode_item_err(leaf, slot,
"invalid nlink: has %u expect no more than 1 for dir",
btrfs_inode_nlink(leaf, iitem));
return -EUCLEAN;
}
btrfs: add ro compat flags to inodes Currently, inode flags are fully backwards incompatible in btrfs. If we introduce a new inode flag, then tree-checker will detect it and fail. This can even cause us to fail to mount entirely. To make it possible to introduce new flags which can be read-only compatible, like VERITY, we add new ro flags to btrfs without treating them quite so harshly in tree-checker. A read-only file system can survive an unexpected flag, and can be mounted. As for the implementation, it unfortunately gets a little complicated. The on-disk representation of the inode, btrfs_inode_item, has an __le64 for flags but the in-memory representation, btrfs_inode, uses a u32. David Sterba had the nice idea that we could reclaim those wasted 32 bits on disk and use them for the new ro_compat flags. It turns out that the tree-checker code which checks for unknown flags is broken, and ignores the upper 32 bits we are hoping to use. The issue is that the flags use the literal 1 rather than 1ULL, so the flags are signed ints, and one of them is specifically (1 << 31). As a result, the mask which ORs the flags is a negative integer on machines where int is 32 bit twos complement. When tree-checker evaluates the expression: btrfs_inode_flags(leaf, iitem) & ~BTRFS_INODE_FLAG_MASK) The mask is something like 0x80000abc, which gets promoted to u64 with sign extension to 0xffffffff80000abc. Negating that 64 bit mask leaves all the upper bits zeroed, and we can't detect unexpected flags. This suggests that we can't use those bits after all. Luckily, we have good reason to believe that they are zero anyway. Inode flags are metadata, which is always checksummed, so any bit flips that would introduce 1s would cause a checksum failure anyway (excluding the improbable case of the checksum getting corrupted exactly badly). Further, unless the 1 << 31 flag is used, the cast to u64 of the 32 bit inode flag should preserve its value and not add leading zeroes (at least for twos complement). The only place that flag (BTRFS_INODE_ROOT_ITEM_INIT) is used is in a special inode embedded in the root item, and indeed for that inode we see 0xffffffff80000000 as the flags on disk. However, that inode is never seen by tree checker, nor is it used in a context where verity might be meaningful. Theoretically, a future ro flag might cause trouble on that inode, so we should proactively clean up that mess before it does. With the introduction of the new ro flags, keep two separate unsigned masks and check them against the appropriate u32. Since we no longer run afoul of sign extension, this also stops writing out 0xffffffff80000000 in root_item inodes going forward. Signed-off-by: Boris Burkov <boris@bur.io> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-01 04:01:48 +08:00
btrfs_inode_split_flags(btrfs_inode_flags(leaf, iitem), &flags, &ro_flags);
if (unlikely(flags & ~BTRFS_INODE_FLAG_MASK)) {
inode_item_err(leaf, slot,
btrfs: add ro compat flags to inodes Currently, inode flags are fully backwards incompatible in btrfs. If we introduce a new inode flag, then tree-checker will detect it and fail. This can even cause us to fail to mount entirely. To make it possible to introduce new flags which can be read-only compatible, like VERITY, we add new ro flags to btrfs without treating them quite so harshly in tree-checker. A read-only file system can survive an unexpected flag, and can be mounted. As for the implementation, it unfortunately gets a little complicated. The on-disk representation of the inode, btrfs_inode_item, has an __le64 for flags but the in-memory representation, btrfs_inode, uses a u32. David Sterba had the nice idea that we could reclaim those wasted 32 bits on disk and use them for the new ro_compat flags. It turns out that the tree-checker code which checks for unknown flags is broken, and ignores the upper 32 bits we are hoping to use. The issue is that the flags use the literal 1 rather than 1ULL, so the flags are signed ints, and one of them is specifically (1 << 31). As a result, the mask which ORs the flags is a negative integer on machines where int is 32 bit twos complement. When tree-checker evaluates the expression: btrfs_inode_flags(leaf, iitem) & ~BTRFS_INODE_FLAG_MASK) The mask is something like 0x80000abc, which gets promoted to u64 with sign extension to 0xffffffff80000abc. Negating that 64 bit mask leaves all the upper bits zeroed, and we can't detect unexpected flags. This suggests that we can't use those bits after all. Luckily, we have good reason to believe that they are zero anyway. Inode flags are metadata, which is always checksummed, so any bit flips that would introduce 1s would cause a checksum failure anyway (excluding the improbable case of the checksum getting corrupted exactly badly). Further, unless the 1 << 31 flag is used, the cast to u64 of the 32 bit inode flag should preserve its value and not add leading zeroes (at least for twos complement). The only place that flag (BTRFS_INODE_ROOT_ITEM_INIT) is used is in a special inode embedded in the root item, and indeed for that inode we see 0xffffffff80000000 as the flags on disk. However, that inode is never seen by tree checker, nor is it used in a context where verity might be meaningful. Theoretically, a future ro flag might cause trouble on that inode, so we should proactively clean up that mess before it does. With the introduction of the new ro flags, keep two separate unsigned masks and check them against the appropriate u32. Since we no longer run afoul of sign extension, this also stops writing out 0xffffffff80000000 in root_item inodes going forward. Signed-off-by: Boris Burkov <boris@bur.io> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-07-01 04:01:48 +08:00
"unknown incompat flags detected: 0x%x", flags);
return -EUCLEAN;
}
if (unlikely(!sb_rdonly(fs_info->sb) &&
(ro_flags & ~BTRFS_INODE_RO_FLAG_MASK))) {
inode_item_err(leaf, slot,
"unknown ro-compat flags detected on writeable mount: 0x%x",
ro_flags);
return -EUCLEAN;
}
return 0;
}
static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key,
int slot)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_root_item ri = { 0 };
const u64 valid_root_flags = BTRFS_ROOT_SUBVOL_RDONLY |
BTRFS_ROOT_SUBVOL_DEAD;
int ret;
ret = check_root_key(leaf, key, slot);
if (unlikely(ret < 0))
return ret;
if (unlikely(btrfs_item_size(leaf, slot) != sizeof(ri) &&
btrfs_item_size(leaf, slot) !=
btrfs_legacy_root_item_size())) {
generic_err(leaf, slot,
"invalid root item size, have %u expect %zu or %u",
btrfs_item_size(leaf, slot), sizeof(ri),
btrfs_legacy_root_item_size());
return -EUCLEAN;
}
/*
* For legacy root item, the members starting at generation_v2 will be
* all filled with 0.
* And since we allow geneartion_v2 as 0, it will still pass the check.
*/
read_extent_buffer(leaf, &ri, btrfs_item_ptr_offset(leaf, slot),
btrfs_item_size(leaf, slot));
/* Generation related */
if (unlikely(btrfs_root_generation(&ri) >
btrfs_super_generation(fs_info->super_copy) + 1)) {
generic_err(leaf, slot,
"invalid root generation, have %llu expect (0, %llu]",
btrfs_root_generation(&ri),
btrfs_super_generation(fs_info->super_copy) + 1);
return -EUCLEAN;
}
if (unlikely(btrfs_root_generation_v2(&ri) >
btrfs_super_generation(fs_info->super_copy) + 1)) {
generic_err(leaf, slot,
"invalid root v2 generation, have %llu expect (0, %llu]",
btrfs_root_generation_v2(&ri),
btrfs_super_generation(fs_info->super_copy) + 1);
return -EUCLEAN;
}
if (unlikely(btrfs_root_last_snapshot(&ri) >
btrfs_super_generation(fs_info->super_copy) + 1)) {
generic_err(leaf, slot,
"invalid root last_snapshot, have %llu expect (0, %llu]",
btrfs_root_last_snapshot(&ri),
btrfs_super_generation(fs_info->super_copy) + 1);
return -EUCLEAN;
}
/* Alignment and level check */
if (unlikely(!IS_ALIGNED(btrfs_root_bytenr(&ri), fs_info->sectorsize))) {
generic_err(leaf, slot,
"invalid root bytenr, have %llu expect to be aligned to %u",
btrfs_root_bytenr(&ri), fs_info->sectorsize);
return -EUCLEAN;
}
if (unlikely(btrfs_root_level(&ri) >= BTRFS_MAX_LEVEL)) {
generic_err(leaf, slot,
"invalid root level, have %u expect [0, %u]",
btrfs_root_level(&ri), BTRFS_MAX_LEVEL - 1);
return -EUCLEAN;
}
if (unlikely(btrfs_root_drop_level(&ri) >= BTRFS_MAX_LEVEL)) {
generic_err(leaf, slot,
"invalid root level, have %u expect [0, %u]",
btrfs_root_drop_level(&ri), BTRFS_MAX_LEVEL - 1);
return -EUCLEAN;
}
/* Flags check */
if (unlikely(btrfs_root_flags(&ri) & ~valid_root_flags)) {
generic_err(leaf, slot,
"invalid root flags, have 0x%llx expect mask 0x%llx",
btrfs_root_flags(&ri), valid_root_flags);
return -EUCLEAN;
}
return 0;
}
__printf(3,4)
__cold
static void extent_err(const struct extent_buffer *eb, int slot,
const char *fmt, ...)
{
struct btrfs_key key;
struct va_format vaf;
va_list args;
u64 bytenr;
u64 len;
btrfs_item_key_to_cpu(eb, &key, slot);
bytenr = key.objectid;
if (key.type == BTRFS_METADATA_ITEM_KEY ||
key.type == BTRFS_TREE_BLOCK_REF_KEY ||
key.type == BTRFS_SHARED_BLOCK_REF_KEY)
len = eb->fs_info->nodesize;
else
len = key.offset;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
btrfs_crit(eb->fs_info,
"corrupt %s: block=%llu slot=%d extent bytenr=%llu len=%llu %pV",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
eb->start, slot, bytenr, len, &vaf);
va_end(args);
}
static int check_extent_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_extent_item *ei;
bool is_tree_block = false;
unsigned long ptr; /* Current pointer inside inline refs */
unsigned long end; /* Extent item end */
const u32 item_size = btrfs_item_size(leaf, slot);
u64 flags;
u64 generation;
u64 total_refs; /* Total refs in btrfs_extent_item */
u64 inline_refs = 0; /* found total inline refs */
if (unlikely(key->type == BTRFS_METADATA_ITEM_KEY &&
!btrfs_fs_incompat(fs_info, SKINNY_METADATA))) {
generic_err(leaf, slot,
"invalid key type, METADATA_ITEM type invalid when SKINNY_METADATA feature disabled");
return -EUCLEAN;
}
/* key->objectid is the bytenr for both key types */
if (unlikely(!IS_ALIGNED(key->objectid, fs_info->sectorsize))) {
generic_err(leaf, slot,
"invalid key objectid, have %llu expect to be aligned to %u",
key->objectid, fs_info->sectorsize);
return -EUCLEAN;
}
/* key->offset is tree level for METADATA_ITEM_KEY */
if (unlikely(key->type == BTRFS_METADATA_ITEM_KEY &&
key->offset >= BTRFS_MAX_LEVEL)) {
extent_err(leaf, slot,
"invalid tree level, have %llu expect [0, %u]",
key->offset, BTRFS_MAX_LEVEL - 1);
return -EUCLEAN;
}
/*
* EXTENT/METADATA_ITEM consists of:
* 1) One btrfs_extent_item
* Records the total refs, type and generation of the extent.
*
* 2) One btrfs_tree_block_info (for EXTENT_ITEM and tree backref only)
* Records the first key and level of the tree block.
*
* 2) Zero or more btrfs_extent_inline_ref(s)
* Each inline ref has one btrfs_extent_inline_ref shows:
* 2.1) The ref type, one of the 4
* TREE_BLOCK_REF Tree block only
* SHARED_BLOCK_REF Tree block only
* EXTENT_DATA_REF Data only
* SHARED_DATA_REF Data only
* 2.2) Ref type specific data
* Either using btrfs_extent_inline_ref::offset, or specific
* data structure.
*/
if (unlikely(item_size < sizeof(*ei))) {
extent_err(leaf, slot,
"invalid item size, have %u expect [%zu, %u)",
item_size, sizeof(*ei),
BTRFS_LEAF_DATA_SIZE(fs_info));
return -EUCLEAN;
}
end = item_size + btrfs_item_ptr_offset(leaf, slot);
/* Checks against extent_item */
ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
flags = btrfs_extent_flags(leaf, ei);
total_refs = btrfs_extent_refs(leaf, ei);
generation = btrfs_extent_generation(leaf, ei);
if (unlikely(generation >
btrfs_super_generation(fs_info->super_copy) + 1)) {
extent_err(leaf, slot,
"invalid generation, have %llu expect (0, %llu]",
generation,
btrfs_super_generation(fs_info->super_copy) + 1);
return -EUCLEAN;
}
if (unlikely(!has_single_bit_set(flags & (BTRFS_EXTENT_FLAG_DATA |
BTRFS_EXTENT_FLAG_TREE_BLOCK)))) {
extent_err(leaf, slot,
"invalid extent flag, have 0x%llx expect 1 bit set in 0x%llx",
flags, BTRFS_EXTENT_FLAG_DATA |
BTRFS_EXTENT_FLAG_TREE_BLOCK);
return -EUCLEAN;
}
is_tree_block = !!(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK);
if (is_tree_block) {
if (unlikely(key->type == BTRFS_EXTENT_ITEM_KEY &&
key->offset != fs_info->nodesize)) {
extent_err(leaf, slot,
"invalid extent length, have %llu expect %u",
key->offset, fs_info->nodesize);
return -EUCLEAN;
}
} else {
if (unlikely(key->type != BTRFS_EXTENT_ITEM_KEY)) {
extent_err(leaf, slot,
"invalid key type, have %u expect %u for data backref",
key->type, BTRFS_EXTENT_ITEM_KEY);
return -EUCLEAN;
}
if (unlikely(!IS_ALIGNED(key->offset, fs_info->sectorsize))) {
extent_err(leaf, slot,
"invalid extent length, have %llu expect aligned to %u",
key->offset, fs_info->sectorsize);
return -EUCLEAN;
}
if (unlikely(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) {
extent_err(leaf, slot,
"invalid extent flag, data has full backref set");
return -EUCLEAN;
}
}
ptr = (unsigned long)(struct btrfs_extent_item *)(ei + 1);
/* Check the special case of btrfs_tree_block_info */
if (is_tree_block && key->type != BTRFS_METADATA_ITEM_KEY) {
struct btrfs_tree_block_info *info;
info = (struct btrfs_tree_block_info *)ptr;
if (unlikely(btrfs_tree_block_level(leaf, info) >= BTRFS_MAX_LEVEL)) {
extent_err(leaf, slot,
"invalid tree block info level, have %u expect [0, %u]",
btrfs_tree_block_level(leaf, info),
BTRFS_MAX_LEVEL - 1);
return -EUCLEAN;
}
ptr = (unsigned long)(struct btrfs_tree_block_info *)(info + 1);
}
/* Check inline refs */
while (ptr < end) {
struct btrfs_extent_inline_ref *iref;
struct btrfs_extent_data_ref *dref;
struct btrfs_shared_data_ref *sref;
u64 dref_offset;
u64 inline_offset;
u8 inline_type;
if (unlikely(ptr + sizeof(*iref) > end)) {
extent_err(leaf, slot,
"inline ref item overflows extent item, ptr %lu iref size %zu end %lu",
ptr, sizeof(*iref), end);
return -EUCLEAN;
}
iref = (struct btrfs_extent_inline_ref *)ptr;
inline_type = btrfs_extent_inline_ref_type(leaf, iref);
inline_offset = btrfs_extent_inline_ref_offset(leaf, iref);
if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) {
extent_err(leaf, slot,
"inline ref item overflows extent item, ptr %lu iref size %u end %lu",
ptr, inline_type, end);
return -EUCLEAN;
}
switch (inline_type) {
/* inline_offset is subvolid of the owner, no need to check */
case BTRFS_TREE_BLOCK_REF_KEY:
inline_refs++;
break;
/* Contains parent bytenr */
case BTRFS_SHARED_BLOCK_REF_KEY:
if (unlikely(!IS_ALIGNED(inline_offset,
fs_info->sectorsize))) {
extent_err(leaf, slot,
"invalid tree parent bytenr, have %llu expect aligned to %u",
inline_offset, fs_info->sectorsize);
return -EUCLEAN;
}
inline_refs++;
break;
/*
* Contains owner subvolid, owner key objectid, adjusted offset.
* The only obvious corruption can happen in that offset.
*/
case BTRFS_EXTENT_DATA_REF_KEY:
dref = (struct btrfs_extent_data_ref *)(&iref->offset);
dref_offset = btrfs_extent_data_ref_offset(leaf, dref);
if (unlikely(!IS_ALIGNED(dref_offset,
fs_info->sectorsize))) {
extent_err(leaf, slot,
"invalid data ref offset, have %llu expect aligned to %u",
dref_offset, fs_info->sectorsize);
return -EUCLEAN;
}
inline_refs += btrfs_extent_data_ref_count(leaf, dref);
break;
/* Contains parent bytenr and ref count */
case BTRFS_SHARED_DATA_REF_KEY:
sref = (struct btrfs_shared_data_ref *)(iref + 1);
if (unlikely(!IS_ALIGNED(inline_offset,
fs_info->sectorsize))) {
extent_err(leaf, slot,
"invalid data parent bytenr, have %llu expect aligned to %u",
inline_offset, fs_info->sectorsize);
return -EUCLEAN;
}
inline_refs += btrfs_shared_data_ref_count(leaf, sref);
break;
default:
extent_err(leaf, slot, "unknown inline ref type: %u",
inline_type);
return -EUCLEAN;
}
ptr += btrfs_extent_inline_ref_size(inline_type);
}
/* No padding is allowed */
if (unlikely(ptr != end)) {
extent_err(leaf, slot,
"invalid extent item size, padding bytes found");
return -EUCLEAN;
}
/* Finally, check the inline refs against total refs */
if (unlikely(inline_refs > total_refs)) {
extent_err(leaf, slot,
"invalid extent refs, have %llu expect >= inline %llu",
total_refs, inline_refs);
return -EUCLEAN;
}
return 0;
}
static int check_simple_keyed_refs(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
u32 expect_item_size = 0;
if (key->type == BTRFS_SHARED_DATA_REF_KEY)
expect_item_size = sizeof(struct btrfs_shared_data_ref);
if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) {
generic_err(leaf, slot,
"invalid item size, have %u expect %u for key type %u",
btrfs_item_size(leaf, slot),
expect_item_size, key->type);
return -EUCLEAN;
}
if (unlikely(!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize))) {
generic_err(leaf, slot,
"invalid key objectid for shared block ref, have %llu expect aligned to %u",
key->objectid, leaf->fs_info->sectorsize);
return -EUCLEAN;
}
if (unlikely(key->type != BTRFS_TREE_BLOCK_REF_KEY &&
!IS_ALIGNED(key->offset, leaf->fs_info->sectorsize))) {
extent_err(leaf, slot,
"invalid tree parent bytenr, have %llu expect aligned to %u",
key->offset, leaf->fs_info->sectorsize);
return -EUCLEAN;
}
return 0;
}
static int check_extent_data_ref(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
struct btrfs_extent_data_ref *dref;
unsigned long ptr = btrfs_item_ptr_offset(leaf, slot);
const unsigned long end = ptr + btrfs_item_size(leaf, slot);
if (unlikely(btrfs_item_size(leaf, slot) % sizeof(*dref) != 0)) {
generic_err(leaf, slot,
"invalid item size, have %u expect aligned to %zu for key type %u",
btrfs_item_size(leaf, slot),
sizeof(*dref), key->type);
return -EUCLEAN;
}
if (unlikely(!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize))) {
generic_err(leaf, slot,
"invalid key objectid for shared block ref, have %llu expect aligned to %u",
key->objectid, leaf->fs_info->sectorsize);
return -EUCLEAN;
}
for (; ptr < end; ptr += sizeof(*dref)) {
u64 offset;
btrfs: tree-checker: do not error out if extent ref hash doesn't match The tree checker checks the extent ref hash at read and write time to make sure we do not corrupt the file system. Generally extent references go inline, but if we have enough of them we need to make an item, which looks like key.objectid = <bytenr> key.type = <BTRFS_EXTENT_DATA_REF_KEY|BTRFS_TREE_BLOCK_REF_KEY> key.offset = hash(tree, owner, offset) However if key.offset collide with an unrelated extent reference we'll simply key.offset++ until we get something that doesn't collide. Obviously this doesn't match at tree checker time, and thus we error while writing out the transaction. This is relatively easy to reproduce, simply do something like the following xfs_io -f -c "pwrite 0 1M" file offset=2 for i in {0..10000} do xfs_io -c "reflink file 0 ${offset}M 1M" file offset=$(( offset + 2 )) done xfs_io -c "reflink file 0 17999258914816 1M" file xfs_io -c "reflink file 0 35998517829632 1M" file xfs_io -c "reflink file 0 53752752058368 1M" file btrfs filesystem sync And the sync will error out because we'll abort the transaction. The magic values above are used because they generate hash collisions with the first file in the main subvol. The fix for this is to remove the hash value check from tree checker, as we have no idea which offset ours should belong to. Reported-by: Tuomas Lähdekorpi <tuomas.lahdekorpi@gmail.com> Fixes: 0785a9aacf9d ("btrfs: tree-checker: Add EXTENT_DATA_REF check") CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> [ add comment] Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-17 04:43:22 +08:00
/*
* We cannot check the extent_data_ref hash due to possible
* overflow from the leaf due to hash collisions.
*/
dref = (struct btrfs_extent_data_ref *)ptr;
offset = btrfs_extent_data_ref_offset(leaf, dref);
if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) {
extent_err(leaf, slot,
"invalid extent data backref offset, have %llu expect aligned to %u",
offset, leaf->fs_info->sectorsize);
return -EUCLEAN;
}
}
return 0;
}
#define inode_ref_err(eb, slot, fmt, args...) \
inode_item_err(eb, slot, fmt, ##args)
static int check_inode_ref(struct extent_buffer *leaf,
struct btrfs_key *key, struct btrfs_key *prev_key,
int slot)
{
struct btrfs_inode_ref *iref;
unsigned long ptr;
unsigned long end;
if (unlikely(!check_prev_ino(leaf, key, slot, prev_key)))
return -EUCLEAN;
/* namelen can't be 0, so item_size == sizeof() is also invalid */
if (unlikely(btrfs_item_size(leaf, slot) <= sizeof(*iref))) {
inode_ref_err(leaf, slot,
"invalid item size, have %u expect (%zu, %u)",
btrfs_item_size(leaf, slot),
sizeof(*iref), BTRFS_LEAF_DATA_SIZE(leaf->fs_info));
return -EUCLEAN;
}
ptr = btrfs_item_ptr_offset(leaf, slot);
end = ptr + btrfs_item_size(leaf, slot);
while (ptr < end) {
u16 namelen;
if (unlikely(ptr + sizeof(iref) > end)) {
inode_ref_err(leaf, slot,
"inode ref overflow, ptr %lu end %lu inode_ref_size %zu",
ptr, end, sizeof(iref));
return -EUCLEAN;
}
iref = (struct btrfs_inode_ref *)ptr;
namelen = btrfs_inode_ref_name_len(leaf, iref);
if (unlikely(ptr + sizeof(*iref) + namelen > end)) {
inode_ref_err(leaf, slot,
"inode ref overflow, ptr %lu end %lu namelen %u",
ptr, end, namelen);
return -EUCLEAN;
}
/*
* NOTE: In theory we should record all found index numbers
* to find any duplicated indexes, but that will be too time
* consuming for inodes with too many hard links.
*/
ptr += sizeof(*iref) + namelen;
}
return 0;
}
/*
* Common point to switch the item-specific validation.
*/
static int check_leaf_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot,
struct btrfs_key *prev_key)
{
int ret = 0;
struct btrfs_chunk *chunk;
switch (key->type) {
case BTRFS_EXTENT_DATA_KEY:
ret = check_extent_data_item(leaf, key, slot, prev_key);
break;
case BTRFS_EXTENT_CSUM_KEY:
ret = check_csum_item(leaf, key, slot, prev_key);
break;
case BTRFS_DIR_ITEM_KEY:
case BTRFS_DIR_INDEX_KEY:
case BTRFS_XATTR_ITEM_KEY:
ret = check_dir_item(leaf, key, prev_key, slot);
break;
case BTRFS_INODE_REF_KEY:
ret = check_inode_ref(leaf, key, prev_key, slot);
break;
case BTRFS_BLOCK_GROUP_ITEM_KEY:
ret = check_block_group_item(leaf, key, slot);
break;
case BTRFS_CHUNK_ITEM_KEY:
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
ret = check_leaf_chunk_item(leaf, chunk, key, slot);
break;
case BTRFS_DEV_ITEM_KEY:
ret = check_dev_item(leaf, key, slot);
break;
case BTRFS_INODE_ITEM_KEY:
ret = check_inode_item(leaf, key, slot);
break;
case BTRFS_ROOT_ITEM_KEY:
ret = check_root_item(leaf, key, slot);
break;
case BTRFS_EXTENT_ITEM_KEY:
case BTRFS_METADATA_ITEM_KEY:
ret = check_extent_item(leaf, key, slot);
break;
case BTRFS_TREE_BLOCK_REF_KEY:
case BTRFS_SHARED_DATA_REF_KEY:
case BTRFS_SHARED_BLOCK_REF_KEY:
ret = check_simple_keyed_refs(leaf, key, slot);
break;
case BTRFS_EXTENT_DATA_REF_KEY:
ret = check_extent_data_ref(leaf, key, slot);
break;
}
return ret;
}
static int check_leaf(struct extent_buffer *leaf, bool check_item_data)
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
/* No valid key type is 0, so all key should be larger than this key */
struct btrfs_key prev_key = {0, 0, 0};
struct btrfs_key key;
u32 nritems = btrfs_header_nritems(leaf);
int slot;
if (unlikely(btrfs_header_level(leaf) != 0)) {
generic_err(leaf, 0,
"invalid level for leaf, have %d expect 0",
btrfs_header_level(leaf));
return -EUCLEAN;
}
/*
* Extent buffers from a relocation tree have a owner field that
* corresponds to the subvolume tree they are based on. So just from an
* extent buffer alone we can not find out what is the id of the
* corresponding subvolume tree, so we can not figure out if the extent
* buffer corresponds to the root of the relocation tree or not. So
* skip this check for relocation trees.
*/
if (nritems == 0 && !btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_RELOC)) {
u64 owner = btrfs_header_owner(leaf);
/* These trees must never be empty */
if (unlikely(owner == BTRFS_ROOT_TREE_OBJECTID ||
owner == BTRFS_CHUNK_TREE_OBJECTID ||
owner == BTRFS_DEV_TREE_OBJECTID ||
owner == BTRFS_FS_TREE_OBJECTID ||
owner == BTRFS_DATA_RELOC_TREE_OBJECTID)) {
generic_err(leaf, 0,
"invalid root, root %llu must never be empty",
owner);
return -EUCLEAN;
}
btrfs: Detect unbalanced tree with empty leaf before crashing btree operations [BUG] With crafted image, btrfs will panic at btree operations: kernel BUG at fs/btrfs/ctree.c:3894! invalid opcode: 0000 [#1] SMP PTI CPU: 0 PID: 1138 Comm: btrfs-transacti Not tainted 5.0.0-rc8+ #9 RIP: 0010:__push_leaf_left+0x6b6/0x6e0 RSP: 0018:ffffc0bd4128b990 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffa0a4ab8f0e38 RCX: 0000000000000000 RDX: ffffa0a280000000 RSI: 0000000000000000 RDI: ffffa0a4b3814000 RBP: ffffc0bd4128ba38 R08: 0000000000001000 R09: ffffc0bd4128b948 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000240 R13: ffffa0a4b556fb60 R14: ffffa0a4ab8f0af0 R15: ffffa0a4ab8f0af0 FS: 0000000000000000(0000) GS:ffffa0a4b7a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2461c80020 CR3: 000000022b32a006 CR4: 00000000000206f0 Call Trace: ? _cond_resched+0x1a/0x50 push_leaf_left+0x179/0x190 btrfs_del_items+0x316/0x470 btrfs_del_csums+0x215/0x3a0 __btrfs_free_extent.isra.72+0x5a7/0xbe0 __btrfs_run_delayed_refs+0x539/0x1120 btrfs_run_delayed_refs+0xdb/0x1b0 btrfs_commit_transaction+0x52/0x950 ? start_transaction+0x94/0x450 transaction_kthread+0x163/0x190 kthread+0x105/0x140 ? btrfs_cleanup_transaction+0x560/0x560 ? kthread_destroy_worker+0x50/0x50 ret_from_fork+0x35/0x40 Modules linked in: ---[ end trace c2425e6e89b5558f ]--- [CAUSE] The offending csum tree looks like this: checksum tree key (CSUM_TREE ROOT_ITEM 0) node 29741056 level 1 items 14 free 107 generation 19 owner CSUM_TREE ... key (EXTENT_CSUM EXTENT_CSUM 85975040) block 29630464 gen 17 key (EXTENT_CSUM EXTENT_CSUM 89911296) block 29642752 gen 17 <<< key (EXTENT_CSUM EXTENT_CSUM 92274688) block 29646848 gen 17 ... leaf 29630464 items 6 free space 1 generation 17 owner CSUM_TREE item 0 key (EXTENT_CSUM EXTENT_CSUM 85975040) itemoff 3987 itemsize 8 range start 85975040 end 85983232 length 8192 ... leaf 29642752 items 0 free space 3995 generation 17 owner 0 ^ empty leaf invalid owner ^ leaf 29646848 items 1 free space 602 generation 17 owner CSUM_TREE item 0 key (EXTENT_CSUM EXTENT_CSUM 92274688) itemoff 627 itemsize 3368 range start 92274688 end 95723520 length 3448832 So we have a corrupted csum tree where one tree leaf is completely empty, causing unbalanced btree, thus leading to unexpected btree balance error. [FIX] For this particular case, we handle it in two directions to catch it: - Check if the tree block is empty through btrfs_verify_level_key() So that invalid tree blocks won't be read out through btrfs_search_slot() and its variants. - Check 0 tree owner in tree checker NO tree is using 0 as its tree owner, detect it and reject at tree block read time. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202821 Reviewed-by: Nikolay Borisov <nborisov@suse.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-08-22 10:14:15 +08:00
/* Unknown tree */
if (unlikely(owner == 0)) {
btrfs: Detect unbalanced tree with empty leaf before crashing btree operations [BUG] With crafted image, btrfs will panic at btree operations: kernel BUG at fs/btrfs/ctree.c:3894! invalid opcode: 0000 [#1] SMP PTI CPU: 0 PID: 1138 Comm: btrfs-transacti Not tainted 5.0.0-rc8+ #9 RIP: 0010:__push_leaf_left+0x6b6/0x6e0 RSP: 0018:ffffc0bd4128b990 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffa0a4ab8f0e38 RCX: 0000000000000000 RDX: ffffa0a280000000 RSI: 0000000000000000 RDI: ffffa0a4b3814000 RBP: ffffc0bd4128ba38 R08: 0000000000001000 R09: ffffc0bd4128b948 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000240 R13: ffffa0a4b556fb60 R14: ffffa0a4ab8f0af0 R15: ffffa0a4ab8f0af0 FS: 0000000000000000(0000) GS:ffffa0a4b7a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2461c80020 CR3: 000000022b32a006 CR4: 00000000000206f0 Call Trace: ? _cond_resched+0x1a/0x50 push_leaf_left+0x179/0x190 btrfs_del_items+0x316/0x470 btrfs_del_csums+0x215/0x3a0 __btrfs_free_extent.isra.72+0x5a7/0xbe0 __btrfs_run_delayed_refs+0x539/0x1120 btrfs_run_delayed_refs+0xdb/0x1b0 btrfs_commit_transaction+0x52/0x950 ? start_transaction+0x94/0x450 transaction_kthread+0x163/0x190 kthread+0x105/0x140 ? btrfs_cleanup_transaction+0x560/0x560 ? kthread_destroy_worker+0x50/0x50 ret_from_fork+0x35/0x40 Modules linked in: ---[ end trace c2425e6e89b5558f ]--- [CAUSE] The offending csum tree looks like this: checksum tree key (CSUM_TREE ROOT_ITEM 0) node 29741056 level 1 items 14 free 107 generation 19 owner CSUM_TREE ... key (EXTENT_CSUM EXTENT_CSUM 85975040) block 29630464 gen 17 key (EXTENT_CSUM EXTENT_CSUM 89911296) block 29642752 gen 17 <<< key (EXTENT_CSUM EXTENT_CSUM 92274688) block 29646848 gen 17 ... leaf 29630464 items 6 free space 1 generation 17 owner CSUM_TREE item 0 key (EXTENT_CSUM EXTENT_CSUM 85975040) itemoff 3987 itemsize 8 range start 85975040 end 85983232 length 8192 ... leaf 29642752 items 0 free space 3995 generation 17 owner 0 ^ empty leaf invalid owner ^ leaf 29646848 items 1 free space 602 generation 17 owner CSUM_TREE item 0 key (EXTENT_CSUM EXTENT_CSUM 92274688) itemoff 627 itemsize 3368 range start 92274688 end 95723520 length 3448832 So we have a corrupted csum tree where one tree leaf is completely empty, causing unbalanced btree, thus leading to unexpected btree balance error. [FIX] For this particular case, we handle it in two directions to catch it: - Check if the tree block is empty through btrfs_verify_level_key() So that invalid tree blocks won't be read out through btrfs_search_slot() and its variants. - Check 0 tree owner in tree checker NO tree is using 0 as its tree owner, detect it and reject at tree block read time. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202821 Reviewed-by: Nikolay Borisov <nborisov@suse.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-08-22 10:14:15 +08:00
generic_err(leaf, 0,
"invalid owner, root 0 is not defined");
return -EUCLEAN;
}
/* EXTENT_TREE_V2 can have empty extent trees. */
if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
return 0;
if (unlikely(owner == BTRFS_EXTENT_TREE_OBJECTID)) {
generic_err(leaf, 0,
"invalid root, root %llu must never be empty",
owner);
return -EUCLEAN;
}
return 0;
}
if (unlikely(nritems == 0))
return 0;
/*
* Check the following things to make sure this is a good leaf, and
* leaf users won't need to bother with similar sanity checks:
*
* 1) key ordering
* 2) item offset and size
* No overlap, no hole, all inside the leaf.
* 3) item content
* If possible, do comprehensive sanity check.
* NOTE: All checks must only rely on the item data itself.
*/
for (slot = 0; slot < nritems; slot++) {
u32 item_end_expected;
btrfs: tree-checker: use u64 for item data end to avoid overflow User reported there is an array-index-out-of-bounds access while mounting the crafted image: [350.411942 ] loop0: detected capacity change from 0 to 262144 [350.427058 ] BTRFS: device fsid a62e00e8-e94e-4200-8217-12444de93c2e devid 1 transid 8 /dev/loop0 scanned by systemd-udevd (1044) [350.428564 ] BTRFS info (device loop0): disk space caching is enabled [350.428568 ] BTRFS info (device loop0): has skinny extents [350.429589 ] [350.429619 ] UBSAN: array-index-out-of-bounds in fs/btrfs/struct-funcs.c:161:1 [350.429636 ] index 1048096 is out of range for type 'page *[16]' [350.429650 ] CPU: 0 PID: 9 Comm: kworker/u8:1 Not tainted 5.16.0-rc4 [350.429652 ] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [350.429653 ] Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs] [350.429772 ] Call Trace: [350.429774 ] <TASK> [350.429776 ] dump_stack_lvl+0x47/0x5c [350.429780 ] ubsan_epilogue+0x5/0x50 [350.429786 ] __ubsan_handle_out_of_bounds+0x66/0x70 [350.429791 ] btrfs_get_16+0xfd/0x120 [btrfs] [350.429832 ] check_leaf+0x754/0x1a40 [btrfs] [350.429874 ] ? filemap_read+0x34a/0x390 [350.429878 ] ? load_balance+0x175/0xfc0 [350.429881 ] validate_extent_buffer+0x244/0x310 [btrfs] [350.429911 ] btrfs_validate_metadata_buffer+0xf8/0x100 [btrfs] [350.429935 ] end_bio_extent_readpage+0x3af/0x850 [btrfs] [350.429969 ] ? newidle_balance+0x259/0x480 [350.429972 ] end_workqueue_fn+0x29/0x40 [btrfs] [350.429995 ] btrfs_work_helper+0x71/0x330 [btrfs] [350.430030 ] ? __schedule+0x2fb/0xa40 [350.430033 ] process_one_work+0x1f6/0x400 [350.430035 ] ? process_one_work+0x400/0x400 [350.430036 ] worker_thread+0x2d/0x3d0 [350.430037 ] ? process_one_work+0x400/0x400 [350.430038 ] kthread+0x165/0x190 [350.430041 ] ? set_kthread_struct+0x40/0x40 [350.430043 ] ret_from_fork+0x1f/0x30 [350.430047 ] </TASK> [350.430047 ] [350.430077 ] BTRFS warning (device loop0): bad eb member start: ptr 0xffe20f4e start 20975616 member offset 4293005178 size 2 btrfs check reports: corrupt leaf: root=3 block=20975616 physical=20975616 slot=1, unexpected item end, have 4294971193 expect 3897 The first slot item offset is 4293005033 and the size is 1966160. In check_leaf, we use btrfs_item_end() to check item boundary versus extent_buffer data size. However, return type of btrfs_item_end() is u32. (u32)(4293005033 + 1966160) == 3897, overflow happens and the result 3897 equals to leaf data size reasonably. Fix it by use u64 variable to store item data end in check_leaf() to avoid u32 overflow. This commit does solve the invalid memory access showed by the stack trace. However, its metadata profile is DUP and another copy of the leaf is fine. So the image can be mounted successfully. But when umount is called, the ASSERT btrfs_mark_buffer_dirty() will be triggered because the only node in extent tree has 0 item and invalid owner. It's solved by another commit "btrfs: check extent buffer owner against the owner rootid". Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215299 Reported-by: Wenqing Liu <wenqingliu0120@gmail.com> CC: stable@vger.kernel.org # 4.19+ Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-22 16:42:07 +08:00
u64 item_data_end;
int ret;
btrfs_item_key_to_cpu(leaf, &key, slot);
/* Make sure the keys are in the right order */
if (unlikely(btrfs_comp_cpu_keys(&prev_key, &key) >= 0)) {
generic_err(leaf, slot,
"bad key order, prev (%llu %u %llu) current (%llu %u %llu)",
prev_key.objectid, prev_key.type,
prev_key.offset, key.objectid, key.type,
key.offset);
return -EUCLEAN;
}
btrfs: tree-checker: use u64 for item data end to avoid overflow User reported there is an array-index-out-of-bounds access while mounting the crafted image: [350.411942 ] loop0: detected capacity change from 0 to 262144 [350.427058 ] BTRFS: device fsid a62e00e8-e94e-4200-8217-12444de93c2e devid 1 transid 8 /dev/loop0 scanned by systemd-udevd (1044) [350.428564 ] BTRFS info (device loop0): disk space caching is enabled [350.428568 ] BTRFS info (device loop0): has skinny extents [350.429589 ] [350.429619 ] UBSAN: array-index-out-of-bounds in fs/btrfs/struct-funcs.c:161:1 [350.429636 ] index 1048096 is out of range for type 'page *[16]' [350.429650 ] CPU: 0 PID: 9 Comm: kworker/u8:1 Not tainted 5.16.0-rc4 [350.429652 ] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [350.429653 ] Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs] [350.429772 ] Call Trace: [350.429774 ] <TASK> [350.429776 ] dump_stack_lvl+0x47/0x5c [350.429780 ] ubsan_epilogue+0x5/0x50 [350.429786 ] __ubsan_handle_out_of_bounds+0x66/0x70 [350.429791 ] btrfs_get_16+0xfd/0x120 [btrfs] [350.429832 ] check_leaf+0x754/0x1a40 [btrfs] [350.429874 ] ? filemap_read+0x34a/0x390 [350.429878 ] ? load_balance+0x175/0xfc0 [350.429881 ] validate_extent_buffer+0x244/0x310 [btrfs] [350.429911 ] btrfs_validate_metadata_buffer+0xf8/0x100 [btrfs] [350.429935 ] end_bio_extent_readpage+0x3af/0x850 [btrfs] [350.429969 ] ? newidle_balance+0x259/0x480 [350.429972 ] end_workqueue_fn+0x29/0x40 [btrfs] [350.429995 ] btrfs_work_helper+0x71/0x330 [btrfs] [350.430030 ] ? __schedule+0x2fb/0xa40 [350.430033 ] process_one_work+0x1f6/0x400 [350.430035 ] ? process_one_work+0x400/0x400 [350.430036 ] worker_thread+0x2d/0x3d0 [350.430037 ] ? process_one_work+0x400/0x400 [350.430038 ] kthread+0x165/0x190 [350.430041 ] ? set_kthread_struct+0x40/0x40 [350.430043 ] ret_from_fork+0x1f/0x30 [350.430047 ] </TASK> [350.430047 ] [350.430077 ] BTRFS warning (device loop0): bad eb member start: ptr 0xffe20f4e start 20975616 member offset 4293005178 size 2 btrfs check reports: corrupt leaf: root=3 block=20975616 physical=20975616 slot=1, unexpected item end, have 4294971193 expect 3897 The first slot item offset is 4293005033 and the size is 1966160. In check_leaf, we use btrfs_item_end() to check item boundary versus extent_buffer data size. However, return type of btrfs_item_end() is u32. (u32)(4293005033 + 1966160) == 3897, overflow happens and the result 3897 equals to leaf data size reasonably. Fix it by use u64 variable to store item data end in check_leaf() to avoid u32 overflow. This commit does solve the invalid memory access showed by the stack trace. However, its metadata profile is DUP and another copy of the leaf is fine. So the image can be mounted successfully. But when umount is called, the ASSERT btrfs_mark_buffer_dirty() will be triggered because the only node in extent tree has 0 item and invalid owner. It's solved by another commit "btrfs: check extent buffer owner against the owner rootid". Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215299 Reported-by: Wenqing Liu <wenqingliu0120@gmail.com> CC: stable@vger.kernel.org # 4.19+ Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-22 16:42:07 +08:00
item_data_end = (u64)btrfs_item_offset(leaf, slot) +
btrfs_item_size(leaf, slot);
/*
* Make sure the offset and ends are right, remember that the
* item data starts at the end of the leaf and grows towards the
* front.
*/
if (slot == 0)
item_end_expected = BTRFS_LEAF_DATA_SIZE(fs_info);
else
item_end_expected = btrfs_item_offset(leaf,
slot - 1);
btrfs: tree-checker: use u64 for item data end to avoid overflow User reported there is an array-index-out-of-bounds access while mounting the crafted image: [350.411942 ] loop0: detected capacity change from 0 to 262144 [350.427058 ] BTRFS: device fsid a62e00e8-e94e-4200-8217-12444de93c2e devid 1 transid 8 /dev/loop0 scanned by systemd-udevd (1044) [350.428564 ] BTRFS info (device loop0): disk space caching is enabled [350.428568 ] BTRFS info (device loop0): has skinny extents [350.429589 ] [350.429619 ] UBSAN: array-index-out-of-bounds in fs/btrfs/struct-funcs.c:161:1 [350.429636 ] index 1048096 is out of range for type 'page *[16]' [350.429650 ] CPU: 0 PID: 9 Comm: kworker/u8:1 Not tainted 5.16.0-rc4 [350.429652 ] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [350.429653 ] Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs] [350.429772 ] Call Trace: [350.429774 ] <TASK> [350.429776 ] dump_stack_lvl+0x47/0x5c [350.429780 ] ubsan_epilogue+0x5/0x50 [350.429786 ] __ubsan_handle_out_of_bounds+0x66/0x70 [350.429791 ] btrfs_get_16+0xfd/0x120 [btrfs] [350.429832 ] check_leaf+0x754/0x1a40 [btrfs] [350.429874 ] ? filemap_read+0x34a/0x390 [350.429878 ] ? load_balance+0x175/0xfc0 [350.429881 ] validate_extent_buffer+0x244/0x310 [btrfs] [350.429911 ] btrfs_validate_metadata_buffer+0xf8/0x100 [btrfs] [350.429935 ] end_bio_extent_readpage+0x3af/0x850 [btrfs] [350.429969 ] ? newidle_balance+0x259/0x480 [350.429972 ] end_workqueue_fn+0x29/0x40 [btrfs] [350.429995 ] btrfs_work_helper+0x71/0x330 [btrfs] [350.430030 ] ? __schedule+0x2fb/0xa40 [350.430033 ] process_one_work+0x1f6/0x400 [350.430035 ] ? process_one_work+0x400/0x400 [350.430036 ] worker_thread+0x2d/0x3d0 [350.430037 ] ? process_one_work+0x400/0x400 [350.430038 ] kthread+0x165/0x190 [350.430041 ] ? set_kthread_struct+0x40/0x40 [350.430043 ] ret_from_fork+0x1f/0x30 [350.430047 ] </TASK> [350.430047 ] [350.430077 ] BTRFS warning (device loop0): bad eb member start: ptr 0xffe20f4e start 20975616 member offset 4293005178 size 2 btrfs check reports: corrupt leaf: root=3 block=20975616 physical=20975616 slot=1, unexpected item end, have 4294971193 expect 3897 The first slot item offset is 4293005033 and the size is 1966160. In check_leaf, we use btrfs_item_end() to check item boundary versus extent_buffer data size. However, return type of btrfs_item_end() is u32. (u32)(4293005033 + 1966160) == 3897, overflow happens and the result 3897 equals to leaf data size reasonably. Fix it by use u64 variable to store item data end in check_leaf() to avoid u32 overflow. This commit does solve the invalid memory access showed by the stack trace. However, its metadata profile is DUP and another copy of the leaf is fine. So the image can be mounted successfully. But when umount is called, the ASSERT btrfs_mark_buffer_dirty() will be triggered because the only node in extent tree has 0 item and invalid owner. It's solved by another commit "btrfs: check extent buffer owner against the owner rootid". Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215299 Reported-by: Wenqing Liu <wenqingliu0120@gmail.com> CC: stable@vger.kernel.org # 4.19+ Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-22 16:42:07 +08:00
if (unlikely(item_data_end != item_end_expected)) {
generic_err(leaf, slot,
btrfs: tree-checker: use u64 for item data end to avoid overflow User reported there is an array-index-out-of-bounds access while mounting the crafted image: [350.411942 ] loop0: detected capacity change from 0 to 262144 [350.427058 ] BTRFS: device fsid a62e00e8-e94e-4200-8217-12444de93c2e devid 1 transid 8 /dev/loop0 scanned by systemd-udevd (1044) [350.428564 ] BTRFS info (device loop0): disk space caching is enabled [350.428568 ] BTRFS info (device loop0): has skinny extents [350.429589 ] [350.429619 ] UBSAN: array-index-out-of-bounds in fs/btrfs/struct-funcs.c:161:1 [350.429636 ] index 1048096 is out of range for type 'page *[16]' [350.429650 ] CPU: 0 PID: 9 Comm: kworker/u8:1 Not tainted 5.16.0-rc4 [350.429652 ] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [350.429653 ] Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs] [350.429772 ] Call Trace: [350.429774 ] <TASK> [350.429776 ] dump_stack_lvl+0x47/0x5c [350.429780 ] ubsan_epilogue+0x5/0x50 [350.429786 ] __ubsan_handle_out_of_bounds+0x66/0x70 [350.429791 ] btrfs_get_16+0xfd/0x120 [btrfs] [350.429832 ] check_leaf+0x754/0x1a40 [btrfs] [350.429874 ] ? filemap_read+0x34a/0x390 [350.429878 ] ? load_balance+0x175/0xfc0 [350.429881 ] validate_extent_buffer+0x244/0x310 [btrfs] [350.429911 ] btrfs_validate_metadata_buffer+0xf8/0x100 [btrfs] [350.429935 ] end_bio_extent_readpage+0x3af/0x850 [btrfs] [350.429969 ] ? newidle_balance+0x259/0x480 [350.429972 ] end_workqueue_fn+0x29/0x40 [btrfs] [350.429995 ] btrfs_work_helper+0x71/0x330 [btrfs] [350.430030 ] ? __schedule+0x2fb/0xa40 [350.430033 ] process_one_work+0x1f6/0x400 [350.430035 ] ? process_one_work+0x400/0x400 [350.430036 ] worker_thread+0x2d/0x3d0 [350.430037 ] ? process_one_work+0x400/0x400 [350.430038 ] kthread+0x165/0x190 [350.430041 ] ? set_kthread_struct+0x40/0x40 [350.430043 ] ret_from_fork+0x1f/0x30 [350.430047 ] </TASK> [350.430047 ] [350.430077 ] BTRFS warning (device loop0): bad eb member start: ptr 0xffe20f4e start 20975616 member offset 4293005178 size 2 btrfs check reports: corrupt leaf: root=3 block=20975616 physical=20975616 slot=1, unexpected item end, have 4294971193 expect 3897 The first slot item offset is 4293005033 and the size is 1966160. In check_leaf, we use btrfs_item_end() to check item boundary versus extent_buffer data size. However, return type of btrfs_item_end() is u32. (u32)(4293005033 + 1966160) == 3897, overflow happens and the result 3897 equals to leaf data size reasonably. Fix it by use u64 variable to store item data end in check_leaf() to avoid u32 overflow. This commit does solve the invalid memory access showed by the stack trace. However, its metadata profile is DUP and another copy of the leaf is fine. So the image can be mounted successfully. But when umount is called, the ASSERT btrfs_mark_buffer_dirty() will be triggered because the only node in extent tree has 0 item and invalid owner. It's solved by another commit "btrfs: check extent buffer owner against the owner rootid". Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215299 Reported-by: Wenqing Liu <wenqingliu0120@gmail.com> CC: stable@vger.kernel.org # 4.19+ Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-22 16:42:07 +08:00
"unexpected item end, have %llu expect %u",
item_data_end, item_end_expected);
return -EUCLEAN;
}
/*
* Check to make sure that we don't point outside of the leaf,
* just in case all the items are consistent to each other, but
* all point outside of the leaf.
*/
btrfs: tree-checker: use u64 for item data end to avoid overflow User reported there is an array-index-out-of-bounds access while mounting the crafted image: [350.411942 ] loop0: detected capacity change from 0 to 262144 [350.427058 ] BTRFS: device fsid a62e00e8-e94e-4200-8217-12444de93c2e devid 1 transid 8 /dev/loop0 scanned by systemd-udevd (1044) [350.428564 ] BTRFS info (device loop0): disk space caching is enabled [350.428568 ] BTRFS info (device loop0): has skinny extents [350.429589 ] [350.429619 ] UBSAN: array-index-out-of-bounds in fs/btrfs/struct-funcs.c:161:1 [350.429636 ] index 1048096 is out of range for type 'page *[16]' [350.429650 ] CPU: 0 PID: 9 Comm: kworker/u8:1 Not tainted 5.16.0-rc4 [350.429652 ] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [350.429653 ] Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs] [350.429772 ] Call Trace: [350.429774 ] <TASK> [350.429776 ] dump_stack_lvl+0x47/0x5c [350.429780 ] ubsan_epilogue+0x5/0x50 [350.429786 ] __ubsan_handle_out_of_bounds+0x66/0x70 [350.429791 ] btrfs_get_16+0xfd/0x120 [btrfs] [350.429832 ] check_leaf+0x754/0x1a40 [btrfs] [350.429874 ] ? filemap_read+0x34a/0x390 [350.429878 ] ? load_balance+0x175/0xfc0 [350.429881 ] validate_extent_buffer+0x244/0x310 [btrfs] [350.429911 ] btrfs_validate_metadata_buffer+0xf8/0x100 [btrfs] [350.429935 ] end_bio_extent_readpage+0x3af/0x850 [btrfs] [350.429969 ] ? newidle_balance+0x259/0x480 [350.429972 ] end_workqueue_fn+0x29/0x40 [btrfs] [350.429995 ] btrfs_work_helper+0x71/0x330 [btrfs] [350.430030 ] ? __schedule+0x2fb/0xa40 [350.430033 ] process_one_work+0x1f6/0x400 [350.430035 ] ? process_one_work+0x400/0x400 [350.430036 ] worker_thread+0x2d/0x3d0 [350.430037 ] ? process_one_work+0x400/0x400 [350.430038 ] kthread+0x165/0x190 [350.430041 ] ? set_kthread_struct+0x40/0x40 [350.430043 ] ret_from_fork+0x1f/0x30 [350.430047 ] </TASK> [350.430047 ] [350.430077 ] BTRFS warning (device loop0): bad eb member start: ptr 0xffe20f4e start 20975616 member offset 4293005178 size 2 btrfs check reports: corrupt leaf: root=3 block=20975616 physical=20975616 slot=1, unexpected item end, have 4294971193 expect 3897 The first slot item offset is 4293005033 and the size is 1966160. In check_leaf, we use btrfs_item_end() to check item boundary versus extent_buffer data size. However, return type of btrfs_item_end() is u32. (u32)(4293005033 + 1966160) == 3897, overflow happens and the result 3897 equals to leaf data size reasonably. Fix it by use u64 variable to store item data end in check_leaf() to avoid u32 overflow. This commit does solve the invalid memory access showed by the stack trace. However, its metadata profile is DUP and another copy of the leaf is fine. So the image can be mounted successfully. But when umount is called, the ASSERT btrfs_mark_buffer_dirty() will be triggered because the only node in extent tree has 0 item and invalid owner. It's solved by another commit "btrfs: check extent buffer owner against the owner rootid". Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215299 Reported-by: Wenqing Liu <wenqingliu0120@gmail.com> CC: stable@vger.kernel.org # 4.19+ Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-22 16:42:07 +08:00
if (unlikely(item_data_end > BTRFS_LEAF_DATA_SIZE(fs_info))) {
generic_err(leaf, slot,
btrfs: tree-checker: use u64 for item data end to avoid overflow User reported there is an array-index-out-of-bounds access while mounting the crafted image: [350.411942 ] loop0: detected capacity change from 0 to 262144 [350.427058 ] BTRFS: device fsid a62e00e8-e94e-4200-8217-12444de93c2e devid 1 transid 8 /dev/loop0 scanned by systemd-udevd (1044) [350.428564 ] BTRFS info (device loop0): disk space caching is enabled [350.428568 ] BTRFS info (device loop0): has skinny extents [350.429589 ] [350.429619 ] UBSAN: array-index-out-of-bounds in fs/btrfs/struct-funcs.c:161:1 [350.429636 ] index 1048096 is out of range for type 'page *[16]' [350.429650 ] CPU: 0 PID: 9 Comm: kworker/u8:1 Not tainted 5.16.0-rc4 [350.429652 ] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [350.429653 ] Workqueue: btrfs-endio-meta btrfs_work_helper [btrfs] [350.429772 ] Call Trace: [350.429774 ] <TASK> [350.429776 ] dump_stack_lvl+0x47/0x5c [350.429780 ] ubsan_epilogue+0x5/0x50 [350.429786 ] __ubsan_handle_out_of_bounds+0x66/0x70 [350.429791 ] btrfs_get_16+0xfd/0x120 [btrfs] [350.429832 ] check_leaf+0x754/0x1a40 [btrfs] [350.429874 ] ? filemap_read+0x34a/0x390 [350.429878 ] ? load_balance+0x175/0xfc0 [350.429881 ] validate_extent_buffer+0x244/0x310 [btrfs] [350.429911 ] btrfs_validate_metadata_buffer+0xf8/0x100 [btrfs] [350.429935 ] end_bio_extent_readpage+0x3af/0x850 [btrfs] [350.429969 ] ? newidle_balance+0x259/0x480 [350.429972 ] end_workqueue_fn+0x29/0x40 [btrfs] [350.429995 ] btrfs_work_helper+0x71/0x330 [btrfs] [350.430030 ] ? __schedule+0x2fb/0xa40 [350.430033 ] process_one_work+0x1f6/0x400 [350.430035 ] ? process_one_work+0x400/0x400 [350.430036 ] worker_thread+0x2d/0x3d0 [350.430037 ] ? process_one_work+0x400/0x400 [350.430038 ] kthread+0x165/0x190 [350.430041 ] ? set_kthread_struct+0x40/0x40 [350.430043 ] ret_from_fork+0x1f/0x30 [350.430047 ] </TASK> [350.430047 ] [350.430077 ] BTRFS warning (device loop0): bad eb member start: ptr 0xffe20f4e start 20975616 member offset 4293005178 size 2 btrfs check reports: corrupt leaf: root=3 block=20975616 physical=20975616 slot=1, unexpected item end, have 4294971193 expect 3897 The first slot item offset is 4293005033 and the size is 1966160. In check_leaf, we use btrfs_item_end() to check item boundary versus extent_buffer data size. However, return type of btrfs_item_end() is u32. (u32)(4293005033 + 1966160) == 3897, overflow happens and the result 3897 equals to leaf data size reasonably. Fix it by use u64 variable to store item data end in check_leaf() to avoid u32 overflow. This commit does solve the invalid memory access showed by the stack trace. However, its metadata profile is DUP and another copy of the leaf is fine. So the image can be mounted successfully. But when umount is called, the ASSERT btrfs_mark_buffer_dirty() will be triggered because the only node in extent tree has 0 item and invalid owner. It's solved by another commit "btrfs: check extent buffer owner against the owner rootid". Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215299 Reported-by: Wenqing Liu <wenqingliu0120@gmail.com> CC: stable@vger.kernel.org # 4.19+ Signed-off-by: Su Yue <l@damenly.su> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-02-22 16:42:07 +08:00
"slot end outside of leaf, have %llu expect range [0, %u]",
item_data_end, BTRFS_LEAF_DATA_SIZE(fs_info));
return -EUCLEAN;
}
/* Also check if the item pointer overlaps with btrfs item. */
if (unlikely(btrfs_item_ptr_offset(leaf, slot) <
btrfs_item_nr_offset(slot) + sizeof(struct btrfs_item))) {
generic_err(leaf, slot,
"slot overlaps with its data, item end %lu data start %lu",
btrfs_item_nr_offset(slot) +
sizeof(struct btrfs_item),
btrfs_item_ptr_offset(leaf, slot));
return -EUCLEAN;
}
if (check_item_data) {
/*
* Check if the item size and content meet other
* criteria
*/
ret = check_leaf_item(leaf, &key, slot, &prev_key);
if (unlikely(ret < 0))
return ret;
}
prev_key.objectid = key.objectid;
prev_key.type = key.type;
prev_key.offset = key.offset;
}
return 0;
}
int btrfs_check_leaf_full(struct extent_buffer *leaf)
{
return check_leaf(leaf, true);
}
ALLOW_ERROR_INJECTION(btrfs_check_leaf_full, ERRNO);
int btrfs_check_leaf_relaxed(struct extent_buffer *leaf)
{
return check_leaf(leaf, false);
}
int btrfs_check_node(struct extent_buffer *node)
{
struct btrfs_fs_info *fs_info = node->fs_info;
unsigned long nr = btrfs_header_nritems(node);
struct btrfs_key key, next_key;
int slot;
int level = btrfs_header_level(node);
u64 bytenr;
int ret = 0;
if (unlikely(level <= 0 || level >= BTRFS_MAX_LEVEL)) {
generic_err(node, 0,
"invalid level for node, have %d expect [1, %d]",
level, BTRFS_MAX_LEVEL - 1);
return -EUCLEAN;
}
if (unlikely(nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(fs_info))) {
btrfs_crit(fs_info,
"corrupt node: root=%llu block=%llu, nritems too %s, have %lu expect range [1,%u]",
btrfs_header_owner(node), node->start,
nr == 0 ? "small" : "large", nr,
BTRFS_NODEPTRS_PER_BLOCK(fs_info));
return -EUCLEAN;
}
for (slot = 0; slot < nr - 1; slot++) {
bytenr = btrfs_node_blockptr(node, slot);
btrfs_node_key_to_cpu(node, &key, slot);
btrfs_node_key_to_cpu(node, &next_key, slot + 1);
if (unlikely(!bytenr)) {
generic_err(node, slot,
"invalid NULL node pointer");
ret = -EUCLEAN;
goto out;
}
if (unlikely(!IS_ALIGNED(bytenr, fs_info->sectorsize))) {
generic_err(node, slot,
"unaligned pointer, have %llu should be aligned to %u",
bytenr, fs_info->sectorsize);
ret = -EUCLEAN;
goto out;
}
if (unlikely(btrfs_comp_cpu_keys(&key, &next_key) >= 0)) {
generic_err(node, slot,
"bad key order, current (%llu %u %llu) next (%llu %u %llu)",
key.objectid, key.type, key.offset,
next_key.objectid, next_key.type,
next_key.offset);
ret = -EUCLEAN;
goto out;
}
}
out:
return ret;
}
ALLOW_ERROR_INJECTION(btrfs_check_node, ERRNO);
btrfs: tree-checker: check extent buffer owner against owner rootid Btrfs doesn't check whether the tree block respects the root owner. This means, if a tree block referred by a parent in extent tree, but has owner of 5, btrfs can still continue reading the tree block, as long as it doesn't trigger other sanity checks. Normally this is fine, but combined with the empty tree check in check_leaf(), if we hit an empty extent tree, but the root node has csum tree owner, we can let such extent buffer to sneak in. Shrink the hole by: - Do extra eb owner check at tree read time - Make sure the root owner extent buffer exactly matches the root id. Unfortunately we can't yet completely patch the hole, there are several call sites can't pass all info we need: - For reloc/log trees Their owner is key::offset, not key::objectid. We need the full root key to do that accurate check. For now, we just skip the ownership check for those trees. - For add_data_references() of relocation That call site doesn't have any parent/ownership info, as all the bytenrs are all from btrfs_find_all_leafs(). - For direct backref items walk Direct backref items records the parent bytenr directly, thus unlike indirect backref item, we don't do a full tree search. Thus in that case, we don't have full parent owner to check. For the later two cases, they all pass 0 as @owner_root, thus we can skip those cases if @owner_root is 0. Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2022-03-16 08:05:58 +08:00
int btrfs_check_eb_owner(const struct extent_buffer *eb, u64 root_owner)
{
const bool is_subvol = is_fstree(root_owner);
const u64 eb_owner = btrfs_header_owner(eb);
/*
* Skip dummy fs, as selftests don't create unique ebs for each dummy
* root.
*/
if (test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &eb->fs_info->fs_state))
return 0;
/*
* There are several call sites (backref walking, qgroup, and data
* reloc) passing 0 as @root_owner, as they are not holding the
* tree root. In that case, we can not do a reliable ownership check,
* so just exit.
*/
if (root_owner == 0)
return 0;
/*
* These trees use key.offset as their owner, our callers don't have
* the extra capacity to pass key.offset here. So we just skip them.
*/
if (root_owner == BTRFS_TREE_LOG_OBJECTID ||
root_owner == BTRFS_TREE_RELOC_OBJECTID)
return 0;
if (!is_subvol) {
/* For non-subvolume trees, the eb owner should match root owner */
if (unlikely(root_owner != eb_owner)) {
btrfs_crit(eb->fs_info,
"corrupted %s, root=%llu block=%llu owner mismatch, have %llu expect %llu",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
root_owner, btrfs_header_bytenr(eb), eb_owner,
root_owner);
return -EUCLEAN;
}
return 0;
}
/*
* For subvolume trees, owners can mismatch, but they should all belong
* to subvolume trees.
*/
if (unlikely(is_subvol != is_fstree(eb_owner))) {
btrfs_crit(eb->fs_info,
"corrupted %s, root=%llu block=%llu owner mismatch, have %llu expect [%llu, %llu]",
btrfs_header_level(eb) == 0 ? "leaf" : "node",
root_owner, btrfs_header_bytenr(eb), eb_owner,
BTRFS_FIRST_FREE_OBJECTID, BTRFS_LAST_FREE_OBJECTID);
return -EUCLEAN;
}
return 0;
}