mirror of
https://github.com/torvalds/linux.git
synced 2026-09-26 01:52:03 +02:00
ext4: fix ABBA deadlock in ext4_xattr_inode_cache_find()
Syzbot/stress-ng reported an ABBA deadlock in ext4 when exercising
concurrent xattr workloads (using the ea_inode mount/format option).
The deadlock occurs between the running transaction and the eviction
thread:
- Task 1 (stress-ng): Holds a reference to a shared mbcache_entry (ce)
and calls ext4_xattr_inode_cache_find() -> ext4_iget() to retrieve
the corresponding EA inode. Since the EA inode is currently being
evicted, ext4_iget() blocks in __wait_on_freeing_inode() waiting for
eviction to complete.
- Task 2 (eviction thread): Currently evicting the same EA inode in
ext4_evict_ea_inode(). It calls mb_cache_entry_wait_unused(oe) which
blocks waiting for Task 1 to release the reference to the mbcache_entry.
To break this deadlock, implement a new ext4_iget() configuration flag
named EXT4_IGET_NOWAIT. When set, perform a non-blocking lookup of the
inode via VFS's find_inode_nowait() API.
If the inode is currently being evicted (marked with I_FREEING or
I_WILL_FREE) or created (I_CREATING), or if it is not present in the VFS
inode cache (cache miss), simply skip it (returning -ENOENT) rather than
waiting for eviction/creation to complete, breaking the ABBA cycle.
Since we return -ENOENT immediately on a cache miss, we never attempt to
allocate a new inode or call iget_locked(), completely eliminating any
TOCTOU race window.
If the returned inode is I_NEW, wait for its initialization to clear via
wait_on_new_inode(). If initialization fails and the inode is unhashed
during wait_on_new_inode() waking up (e.g., due to an I/O read error in
another thread), safely drop the reference and return -ENOENT. This
unhashed check is executed unconditionally on all cache-hit pathways to
properly handle concurrent initialization failures.
Finally, standard validation checks (including is_bad_inode,
EXT4_EA_INODE_FL, file_acl, and xattr flags) are executed as normal inside
check_igot_inode() to fully guarantee VFS-layer safety.
In ext4_xattr_inode_cache_find(), invoke ext4_iget() with the new
EXT4_IGET_NOWAIT flag to perform the non-blocking cache search.
Suggested-by: Jan Kara <jack@suse.cz>
Reported-by: Colin Ian King <colin.i.king@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219283
Fixes: 0a46ef2347 ("ext4: do not create EA inode under buffer lock")
Signed-off-by: Aditya Prakash Srivastava <aditya.ansh182@gmail.com>
Tested-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260626054821.1729-1-aditya.ansh182@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
This commit is contained in:
parent
2c0e4fb511
commit
03438084a7
|
|
@ -3144,7 +3144,8 @@ typedef enum {
|
|||
EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */
|
||||
EXT4_IGET_HANDLE = 0x0002, /* Inode # is from a handle */
|
||||
EXT4_IGET_BAD = 0x0004, /* Allow to iget a bad inode */
|
||||
EXT4_IGET_EA_INODE = 0x0008 /* Inode should contain an EA value */
|
||||
EXT4_IGET_EA_INODE = 0x0008, /* Inode should contain an EA value */
|
||||
EXT4_IGET_NOWAIT = 0x0010 /* Non-blocking lookup (skip if freeing) */
|
||||
} ext4_iget_flags;
|
||||
|
||||
extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
|
||||
|
|
|
|||
|
|
@ -5272,6 +5272,20 @@ void ext4_set_inode_mapping_order(struct inode *inode)
|
|||
mapping_set_folio_order_range(inode->i_mapping, min_order, max_order);
|
||||
}
|
||||
|
||||
static int ext4_iget_match(struct inode *inode, u64 ino, void *data)
|
||||
{
|
||||
if (inode->i_ino != ino)
|
||||
return 0;
|
||||
spin_lock(&inode->i_lock);
|
||||
if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_CREATING)) {
|
||||
spin_unlock(&inode->i_lock);
|
||||
return -1;
|
||||
}
|
||||
__iget(inode);
|
||||
spin_unlock(&inode->i_lock);
|
||||
return 1;
|
||||
}
|
||||
|
||||
struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
|
||||
ext4_iget_flags flags, const char *function,
|
||||
unsigned int line)
|
||||
|
|
@ -5300,9 +5314,24 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
|
|||
return ERR_PTR(-EFSCORRUPTED);
|
||||
}
|
||||
|
||||
inode = iget_locked(sb, ino);
|
||||
if (!inode)
|
||||
return ERR_PTR(-ENOMEM);
|
||||
if (flags & EXT4_IGET_NOWAIT) {
|
||||
inode = find_inode_nowait(sb, ino, ext4_iget_match, NULL);
|
||||
if (!inode)
|
||||
return ERR_PTR(-ENOENT);
|
||||
|
||||
if (inode_state_read_once(inode) & I_NEW)
|
||||
wait_on_new_inode(inode);
|
||||
|
||||
if (unlikely(inode_unhashed(inode))) {
|
||||
iput(inode);
|
||||
return ERR_PTR(-ENOENT);
|
||||
}
|
||||
} else {
|
||||
inode = iget_locked(sb, ino);
|
||||
if (!inode)
|
||||
return ERR_PTR(-ENOMEM);
|
||||
}
|
||||
|
||||
if (!(inode_state_read_once(inode) & I_NEW)) {
|
||||
ret = check_igot_inode(inode, flags, function, line);
|
||||
if (ret) {
|
||||
|
|
|
|||
|
|
@ -1550,7 +1550,7 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
|
|||
|
||||
while (ce) {
|
||||
ea_inode = ext4_iget(inode->i_sb, ce->e_value,
|
||||
EXT4_IGET_EA_INODE);
|
||||
EXT4_IGET_EA_INODE | EXT4_IGET_NOWAIT);
|
||||
if (IS_ERR(ea_inode))
|
||||
goto next_entry;
|
||||
ext4_xattr_inode_set_class(ea_inode);
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user