[PATCH RFC v2] ocfs2: fix circular locking dependency in ocfs2_init_acl()
"syzbot" <[email protected]> Wed, 15 Jul 2026 16:14:04 +0000 (UTC)
| Newsgroups | dev.linux.lists.syzbot |
|---|---|
| Message-ID | <[email protected]> |
A lockdep warning indicates a circular locking dependency between
`&oi->ip_xattr_sem` and `&journal->j_trans_barrier`.
The deadlock involves two code paths:
Path 1 (setxattr): `ocfs2_xattr_set()` acquires `ip_xattr_sem` (write) and
then starts a transaction, which acquires `j_trans_barrier` (read).
Path 2 (mkdir/mknod): `ocfs2_mknod()` starts a transaction
(`j_trans_barrier` read) and then calls `ocfs2_init_acl()`, which attempts
to acquire `ip_xattr_sem` (read) on the parent directory to retrieve the
default ACL.
Because rw_semaphores are subject to writer priority, a pending writer on
`j_trans_barrier` (e.g., the journal commit thread) can cause Path 1 to
block, while Path 2 is blocked waiting for Path 1 to release
`ip_xattr_sem`.
======================================================
WARNING: possible circular locking dependency detected
syz.0.17/6116 is trying to acquire lock:
ffff88811dd5a2e8 (&oi->ip_xattr_sem){++++}-{4:4}, at:
ocfs2_init_acl+0x2fd/0x7e0 fs/ocfs2/acl.c:367
but task is already holding lock:
ffff888119b518e0 (&journal->j_trans_barrier){.+.+}-{4:4}, at:
ocfs2_start_trans+0x3ab/0x700 fs/ocfs2/journal.c:369
which lock already depends on the new lock.
Chain exists of:
&oi->ip_xattr_sem --> sb_internal#2 --> &journal->j_trans_barrier
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
rlock(&journal->j_trans_barrier);
lock(sb_internal#2);
lock(&journal->j_trans_barrier);
rlock(&oi->ip_xattr_sem);
*** DEADLOCK ***
The patch fixes the lock ordering by precomputing the ACL state before
starting the OCFS2 transaction, while preserving POSIX ACL storage
semantics and the existing inode/security initialization order. By reading
the parent directory's default ACL and preparing the new inode's ACLs
outside the transaction, `ip_xattr_sem` is always acquired before
`j_trans_barrier`.
Update `ocfs2_calc_xattr_init()` and `ocfs2_init_acl()` to use these
precomputed ACLs, removing internal `ip_xattr_sem` acquisition and
redundant disk reads. In `ocfs2_mknod()` and
`ocfs2_init_security_and_acl()`, the umask or default ACL is applied to
`inode->i_mode` before the transaction begins. If `__posix_acl_create()`
indicates an access ACL is not needed, it is released immediately.
Fixes: 16c8d569f570 ("ocfs2/acl: use 'ip_xattr_sem' to protect getting extended attribute")
Assisted-by: Gemini:gemini-3.1-pro-preview Gemini:gemini-3-flash-preview syzbot
Reported-by: [email protected]
Closes: https://syzkaller.appspot.com/bug?extid=4007ab5229e732466d9f
Link: https://syzkaller.appspot.com/ai_job?id=c2b46419-cb28-4c0c-b757-f315188c1ae8
To: "Joel Becker" <[email protected]>
To: "Joseph Qi" <[email protected]>
To: "Mark Fasheh" <[email protected]>
To: <[email protected]>
Cc: <[email protected]>
---
v2:
- Updated ocfs2_calc_xattr_init() to accept precomputed ACLs for more accurate credit and size calculation.
- Modified ocfs2_mknod() and ocfs2_init_security_and_acl() to fetch and create ACLs before starting a transaction, resolving the lock ordering issue.
- Ensured inode->i_mode is updated correctly during the pre-transaction ACL creation phase.
- Added logic to release the access ACL object if it is not required for storage (i.e., matches the file mode).
v1:
https://lore.kernel.org/all/[email protected]/T/
---
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index af1e2cedb..ec4b36004 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -110,9 +110,8 @@ static void *ocfs2_acl_to_xattr(const struct posix_acl *acl, size_t *size)
return ocfs2_acl;
}
-static struct posix_acl *ocfs2_get_acl_nolock(struct inode *inode,
- int type,
- struct buffer_head *di_bh)
+struct posix_acl *ocfs2_get_acl_nolock(struct inode *inode, int type,
+ struct buffer_head *di_bh)
{
int name_index;
char *value = NULL;
@@ -156,8 +155,8 @@ static struct posix_acl *ocfs2_get_acl_nolock(struct inode *inode,
* will not have di_bh or a journal handle to pass, in which case it
* will create it's own.
*/
-static int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh,
- handle_t *handle, umode_t new_mode)
+int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh,
+ handle_t *handle, umode_t new_mode)
{
int ret, commit_handle = 0;
struct ocfs2_dinode *di;
@@ -349,63 +348,33 @@ int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh)
* Initialize the ACLs of a new inode. If parent directory has default ACL,
* then clone to new inode. Called from ocfs2_mknod.
*/
-int ocfs2_init_acl(handle_t *handle,
- struct inode *inode,
- struct inode *dir,
- struct buffer_head *di_bh,
- struct buffer_head *dir_bh,
+int ocfs2_init_acl(handle_t *handle, struct inode *inode, struct inode *dir,
+ struct buffer_head *di_bh, struct buffer_head *dir_bh,
struct ocfs2_alloc_context *meta_ac,
- struct ocfs2_alloc_context *data_ac)
+ struct ocfs2_alloc_context *data_ac,
+ struct posix_acl *default_acl, struct posix_acl *acl)
{
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- struct posix_acl *acl = NULL;
- int ret = 0, ret2;
- umode_t mode;
-
- if (!S_ISLNK(inode->i_mode)) {
- if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
- down_read(&OCFS2_I(dir)->ip_xattr_sem);
- acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT,
- dir_bh);
- up_read(&OCFS2_I(dir)->ip_xattr_sem);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- }
- if (!acl) {
- mode = inode->i_mode & ~current_umask();
- ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
- if (ret) {
- mlog_errno(ret);
- goto cleanup;
- }
- }
- }
- if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) {
- if (S_ISDIR(inode->i_mode)) {
+ int ret = 0;
+
+ if (S_ISLNK(inode->i_mode))
+ return 0;
+
+ if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+ if (S_ISDIR(inode->i_mode) && default_acl) {
ret = ocfs2_set_acl(handle, inode, di_bh,
- ACL_TYPE_DEFAULT, acl,
+ ACL_TYPE_DEFAULT, default_acl,
meta_ac, data_ac);
if (ret)
- goto cleanup;
- }
- mode = inode->i_mode;
- ret = __posix_acl_create(&acl, GFP_NOFS, &mode);
- if (ret < 0)
- return ret;
-
- ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
- if (ret2) {
- mlog_errno(ret2);
- ret = ret2;
- goto cleanup;
+ return ret;
}
- if (ret > 0) {
+
+ if (acl) {
ret = ocfs2_set_acl(handle, inode,
di_bh, ACL_TYPE_ACCESS,
acl, meta_ac, data_ac);
}
}
-cleanup:
- posix_acl_release(acl);
+
return ret;
}
diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h
index 667c6f03f..786b4d32b 100644
--- a/fs/ocfs2/acl.h
+++ b/fs/ocfs2/acl.h
@@ -23,6 +23,11 @@ extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *);
extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *,
struct buffer_head *, struct buffer_head *,
struct ocfs2_alloc_context *,
- struct ocfs2_alloc_context *);
+ struct ocfs2_alloc_context *, struct posix_acl *,
+ struct posix_acl *);
+struct posix_acl *ocfs2_get_acl_nolock(struct inode *inode, int type,
+ struct buffer_head *di_bh);
+int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh,
+ handle_t *handle, umode_t new_mode);
#endif /* OCFS2_ACL_H */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 1277666c7..30b945ba9 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -27,6 +27,7 @@
#include <linux/highmem.h>
#include <linux/quotaops.h>
#include <linux/iversion.h>
+#include <linux/fs_struct.h>
#include <cluster/masklog.h>
@@ -256,6 +257,7 @@ static int ocfs2_mknod(struct mnt_idmap *idmap,
sigset_t oldset;
int did_block_signals = 0;
struct ocfs2_dentry_lock *dl = NULL;
+ struct posix_acl *default_acl = NULL, *acl = NULL;
trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
(unsigned long long)OCFS2_I(dir)->ip_blkno,
@@ -330,10 +332,41 @@ static int ocfs2_mknod(struct mnt_idmap *idmap,
}
}
+ if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+ down_read(&OCFS2_I(dir)->ip_xattr_sem);
+ default_acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT,
+ parent_fe_bh);
+ up_read(&OCFS2_I(dir)->ip_xattr_sem);
+ if (IS_ERR(default_acl)) {
+ status = PTR_ERR(default_acl);
+ default_acl = NULL;
+ goto leave;
+ }
+ if (default_acl) {
+ acl = posix_acl_dup(default_acl);
+ if (!acl) {
+ status = -ENOMEM;
+ goto leave;
+ }
+ status = __posix_acl_create(&acl, GFP_NOFS,
+ &inode->i_mode);
+ if (status < 0)
+ goto leave;
+ if (status == 0) {
+ posix_acl_release(acl);
+ acl = NULL;
+ }
+ } else {
+ inode->i_mode &= ~current_umask();
+ }
+ } else {
+ inode->i_mode &= ~current_umask();
+ }
+
/* calculate meta data/clusters for setting security and acl xattr */
- status = ocfs2_calc_xattr_init(dir, parent_fe_bh, mode,
- &si, &want_clusters,
- &xattr_credits, &want_meta);
+ status = ocfs2_calc_xattr_init(dir, parent_fe_bh, mode, &si,
+ &want_clusters, &xattr_credits,
+ &want_meta, default_acl, acl);
if (status < 0) {
mlog_errno(status);
goto leave;
@@ -412,7 +445,7 @@ static int ocfs2_mknod(struct mnt_idmap *idmap,
}
status = ocfs2_init_acl(handle, inode, dir, new_fe_bh, parent_fe_bh,
- meta_ac, data_ac);
+ meta_ac, data_ac, default_acl, acl);
if (status < 0) {
mlog_errno(status);
@@ -477,6 +510,9 @@ static int ocfs2_mknod(struct mnt_idmap *idmap,
brelse(parent_fe_bh);
kfree(si.value);
+ posix_acl_release(default_acl);
+ posix_acl_release(acl);
+
ocfs2_free_dir_lookup_result(&lookup);
if (inode_ac)
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index fcddd3c13..3b7d2aea7 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -26,6 +26,7 @@
#include <linux/module.h>
#include <linux/string.h>
#include <linux/security.h>
+#include <linux/fs_struct.h>
#include <cluster/masklog.h>
@@ -611,13 +612,11 @@ int ocfs2_calc_security_init(struct inode *dir,
return ret;
}
-int ocfs2_calc_xattr_init(struct inode *dir,
- struct buffer_head *dir_bh,
- umode_t mode,
- struct ocfs2_security_xattr_info *si,
- int *want_clusters,
- int *xattr_credits,
- int *want_meta)
+int ocfs2_calc_xattr_init(struct inode *dir, struct buffer_head *dir_bh,
+ umode_t mode, struct ocfs2_security_xattr_info *si,
+ int *want_clusters, int *xattr_credits,
+ int *want_meta, struct posix_acl *default_acl,
+ struct posix_acl *acl)
{
int ret = 0;
struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
@@ -628,19 +627,14 @@ int ocfs2_calc_xattr_init(struct inode *dir,
si->value_len);
if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
- down_read(&OCFS2_I(dir)->ip_xattr_sem);
- acl_len = ocfs2_xattr_get_nolock(dir, dir_bh,
- OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT,
- "", NULL, 0);
- up_read(&OCFS2_I(dir)->ip_xattr_sem);
- if (acl_len > 0) {
- a_size = ocfs2_xattr_entry_real_size(0, acl_len);
- if (S_ISDIR(mode))
- a_size <<= 1;
- } else if (acl_len != 0 && acl_len != -ENODATA) {
- ret = acl_len;
- mlog_errno(ret);
- return ret;
+ if (default_acl && S_ISDIR(mode)) {
+ acl_len = default_acl->a_count *
+ sizeof(struct ocfs2_acl_entry);
+ a_size += ocfs2_xattr_entry_real_size(0, acl_len);
+ }
+ if (acl) {
+ acl_len = acl->a_count * sizeof(struct ocfs2_acl_entry);
+ a_size += ocfs2_xattr_entry_real_size(0, acl_len);
}
}
@@ -683,14 +677,28 @@ int ocfs2_calc_xattr_init(struct inode *dir,
new_clusters);
*want_clusters += new_clusters;
}
- if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL &&
- acl_len > OCFS2_XATTR_INLINE_SIZE) {
- /* for directory, it has DEFAULT and ACCESS two types of acls */
- new_clusters = (S_ISDIR(mode) ? 2 : 1) *
- ocfs2_clusters_for_bytes(dir->i_sb, acl_len);
- *xattr_credits += ocfs2_clusters_to_blocks(dir->i_sb,
- new_clusters);
- *want_clusters += new_clusters;
+ if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+ if (default_acl && S_ISDIR(mode)) {
+ acl_len = default_acl->a_count *
+ sizeof(struct ocfs2_acl_entry);
+ if (acl_len > OCFS2_XATTR_INLINE_SIZE) {
+ new_clusters = ocfs2_clusters_for_bytes(
+ dir->i_sb, acl_len);
+ *xattr_credits += ocfs2_clusters_to_blocks(
+ dir->i_sb, new_clusters);
+ *want_clusters += new_clusters;
+ }
+ }
+ if (acl) {
+ acl_len = acl->a_count * sizeof(struct ocfs2_acl_entry);
+ if (acl_len > OCFS2_XATTR_INLINE_SIZE) {
+ new_clusters = ocfs2_clusters_for_bytes(
+ dir->i_sb, acl_len);
+ *xattr_credits += ocfs2_clusters_to_blocks(
+ dir->i_sb, new_clusters);
+ *want_clusters += new_clusters;
+ }
+ }
}
return ret;
@@ -7257,6 +7265,8 @@ int ocfs2_init_security_and_acl(struct inode *dir,
{
int ret = 0;
struct buffer_head *dir_bh = NULL;
+ struct posix_acl *default_acl = NULL, *acl = NULL;
+ umode_t mode = inode->i_mode;
ret = ocfs2_init_security_get(inode, dir, qstr, NULL);
if (ret) {
@@ -7269,12 +7279,55 @@ int ocfs2_init_security_and_acl(struct inode *dir,
mlog_errno(ret);
goto leave;
}
- ret = ocfs2_init_acl(NULL, inode, dir, NULL, dir_bh, NULL, NULL);
+
+ if (OCFS2_SB(dir->i_sb)->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+ down_read(&OCFS2_I(dir)->ip_xattr_sem);
+ default_acl =
+ ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT, dir_bh);
+ up_read(&OCFS2_I(dir)->ip_xattr_sem);
+ if (IS_ERR(default_acl)) {
+ ret = PTR_ERR(default_acl);
+ default_acl = NULL;
+ goto unlock;
+ }
+ if (default_acl) {
+ acl = posix_acl_dup(default_acl);
+ if (!acl) {
+ ret = -ENOMEM;
+ goto unlock;
+ }
+ ret = __posix_acl_create(&acl, GFP_NOFS, &mode);
+ if (ret < 0)
+ goto unlock;
+ if (ret == 0) {
+ posix_acl_release(acl);
+ acl = NULL;
+ }
+ } else {
+ mode &= ~current_umask();
+ }
+ } else {
+ mode &= ~current_umask();
+ }
+
+ if (mode != inode->i_mode) {
+ ret = ocfs2_acl_set_mode(inode, NULL, NULL, mode);
+ if (ret) {
+ mlog_errno(ret);
+ goto unlock;
+ }
+ }
+
+ ret = ocfs2_init_acl(NULL, inode, dir, NULL, dir_bh, NULL, NULL,
+ default_acl, acl);
if (ret)
mlog_errno(ret);
+unlock:
ocfs2_inode_unlock(dir, 0);
brelse(dir_bh);
+ posix_acl_release(default_acl);
+ posix_acl_release(acl);
leave:
return ret;
}
diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h
index 65e9aa743..34f8904de 100644
--- a/fs/ocfs2/xattr.h
+++ b/fs/ocfs2/xattr.h
@@ -55,9 +55,9 @@ int ocfs2_init_security_set(handle_t *, struct inode *,
int ocfs2_calc_security_init(struct inode *,
struct ocfs2_security_xattr_info *,
int *, int *, struct ocfs2_alloc_context **);
-int ocfs2_calc_xattr_init(struct inode *, struct buffer_head *,
- umode_t, struct ocfs2_security_xattr_info *,
- int *, int *, int *);
+int ocfs2_calc_xattr_init(struct inode *, struct buffer_head *, umode_t,
+ struct ocfs2_security_xattr_info *, int *, int *,
+ int *, struct posix_acl *, struct posix_acl *);
/*
* xattrs can live inside an inode, as part of an external xattr block,
base-commit: dc59e4fea9d83f03bad6bddf3fa2e52491777482
--
This is an AI-generated patch subject to moderation.
Reply with '#syz upstream' to Sign-off the patch as a human author
and send it to the upstream kernel mailing lists.
Reply with '#syz reject' to reject it ('#syz unreject' to undo).
See https://goo.gle/syzbot-ai-patches for information about AI-generated patches.
You can comment on the patch as usual, syzbot will try to address
the comments and send a new version of the patch if necessary.
syzbot engineers can be reached at [email protected].