An io_uring openat operation can update an audit reference count
from multiple threads resulting in the call trace below.
A call to io_uring_submit() with a single openat op with a flag of
IOSQE_ASYNC results in the following reference count updates.
These first part of the system call performs two increments that do not race.
do_syscall_64()
__do_sys_io_uring_enter()
io_submit_sqes()
io_openat_prep()
__io_openat_prep()
getname()
getname_flags() /* update 1 (increment) */
__audit_getname() /* update 2 (increment) */
The openat op is queued to an io_uring worker thread which starts the
opportunity for a race. The system call exit performs one decrement.
do_syscall_64()
syscall_exit_to_user_mode()
syscall_exit_to_user_mode_prepare()
__audit_syscall_exit()
audit_reset_context()
putname() /* update 3 (decrement) */
The io_uring worker thread performs one increment and two decrements.
These updates can race with the system call decrement.
io_wqe_worker()
io_worker_handle_work()
io_wq_submit_work()
io_issue_sqe()
io_openat()
io_openat2()
do_filp_open()
path_openat()
__audit_inode() /* update 4 (increment) */
putname() /* update 5 (decrement) */
__audit_uring_exit()
audit_reset_context()
putname() /* update 6 (decrement) */
The fix is to change the refcnt member of struct audit_names
from int to atomic_t.
kernel BUG at fs/namei.c:262!
Call Trace:
...
? putname+0x68/0x70
audit_reset_context.part.0.constprop.0+0xe1/0x300
__audit_uring_exit+0xda/0x1c0
io_issue_sqe+0x1f3/0x450
? lock_timer_base+0x3b/0xd0
io_wq_submit_work+0x8d/0x2b0
? __try_to_del_timer_sync+0x67/0xa0
io_worker_handle_work+0x17c/0x2b0
io_wqe_worker+0x10a/0x350
Cc: <[email protected]>
Link:
https://lore.kernel.org/lkml/mw2pr2101mb1033fff044a258f84aeaa584f1...@mw2pr2101mb1033.namprd21.prod.outlook.com/
Fixes: 5bd2182d58e9 ("audit,io_uring,io-wq: add some basic audit support to
io_uring")
Signed-off-by: Dan Clash <[email protected]>
---
fs/namei.c | 9 +++++----
include/linux/fs.h | 2 +-
kernel/auditsc.c | 8 ++++----
3 files changed, 10 insertions(+), 9 deletions(-)
diff --git a/fs/namei.c b/fs/namei.c
index 567ee547492b..94565bd7e73f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -188,7 +188,7 @@ getname_flags(const char __user *filename, int flags, int
*empty)
}
}
- result->refcnt = 1;
+ atomic_set(&result->refcnt, 1);
/* The empty path is special. */
if (unlikely(!len)) {
if (empty)
@@ -249,7 +249,7 @@ getname_kernel(const char * filename)
memcpy((char *)result->name, filename, len);
result->uptr = NULL;
result->aname = NULL;
- result->refcnt = 1;
+ atomic_set(&result->refcnt, 1);
audit_getname(result);
return result;
@@ -261,9 +261,10 @@ void putname(struct filename *name)
if (IS_ERR(name))
return;
- BUG_ON(name->refcnt <= 0);
+ if (WARN_ON_ONCE(!atomic_read(&name->refcnt)))
+ return;
- if (--name->refcnt > 0)
+ if (!atomic_dec_and_test(&name->refcnt))
return;
if (name->name != name->iname) {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4aeb3fa11927..85653ce30d2c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2444,7 +2444,7 @@ struct audit_names;
struct filename {
const char *name; /* pointer to actual string */
const __user char *uptr; /* original userland pointer */
- int refcnt;
+ atomic_t refcnt;
struct audit_names *aname;
const char iname[];
};
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 21d2fa815e78..6f0d6fb6523f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2212,7 +2212,7 @@ __audit_reusename(const __user char *uptr)
if (!n->name)
continue;
if (n->name->uptr == uptr) {
- n->name->refcnt++;
+ atomic_inc(&n->name->refcnt);
return n->name;
}
}
@@ -2241,7 +2241,7 @@ void __audit_getname(struct filename *name)
n->name = name;
n->name_len = AUDIT_NAME_FULL;
name->aname = n;
- name->refcnt++;
+ atomic_inc(&name->refcnt);
}
static inline int audit_copy_fcaps(struct audit_names *name,
@@ -2373,7 +2373,7 @@ void __audit_inode(struct filename *name, const struct
dentry *dentry,
return;
if (name) {
n->name = name;
- name->refcnt++;
+ atomic_inc(&name->refcnt);
}
out:
@@ -2500,7 +2500,7 @@ void __audit_inode_child(struct inode *parent,
if (found_parent) {
found_child->name = found_parent->name;
found_child->name_len = AUDIT_NAME_FULL;
- found_child->name->refcnt++;
+ atomic_inc(&found_child->name->refcnt);
}
}
base-commit: 0bb80ecc33a8fb5a682236443c1e740d5c917d1d
--
2.34.1
