[patch V3 08/14] futex: Add support for unlocking robust futexes
From: Thomas Gleixner
Date: Mon Mar 30 2026 - 08:08:49 EST
Unlocking robust non-PI futexes happens in user space with the following
sequence:
1) robust_list_set_op_pending(mutex);
2) robust_list_remove(mutex);
lval = 0;
3) lval = atomic_xchg(lock, lval);
4) if (lval & WAITERS)
5) sys_futex(WAKE,....);
6) robust_list_clear_op_pending();
That opens a window between #3 and #6 where the mutex could be acquired by
some other task which observes that it is the last user and:
A) unmaps the mutex memory
B) maps a different file, which ends up covering the same address
When the original task exits before reaching #6 then the kernel robust list
handling observes the pending op entry and tries to fix up user space.
In case that the newly mapped data contains the TID of the exiting thread
at the address of the mutex/futex the kernel will set the owner died bit in
that memory and therefore corrupting unrelated data.
PI futexes have a similar problem both for the non-contented user space
unlock and the in kernel unlock:
1) robust_list_set_op_pending(mutex);
2) robust_list_remove(mutex);
lval = gettid();
3) if (!atomic_try_cmpxchg(lock, lval, 0))
4) sys_futex(UNLOCK_PI,....);
5) robust_list_clear_op_pending();
Address the first part of the problem where the futexes have waiters and
need to enter the kernel anyway. Add a new FUTEX_ROBUST_UNLOCK flag, which
is valid for the sys_futex() FUTEX_UNLOCK_PI, FUTEX_WAKE, FUTEX_WAKE_BITSET
operations.
This deliberately omits FUTEX_WAKE_OP from this treatment as it's unclear
whether this is needed and there is no usage of it in glibc either to
investigate.
For the futex2 syscall family this needs to be implemented with a new
syscall.
The sys_futex() case [ab]uses the @uaddr2 argument to hand the pointer to
robust_list_head::list_pending_op into the kernel. This argument is only
evaluated when the FUTEX_ROBUST_UNLOCK bit is set and is therefore backward
compatible.
This is an explicit argument to avoid the lookup of the robust list pointer
and retrieving the pending op pointer from there. User space has the
pointer already available so it can just put it into the @uaddr2
argument. Aside of that this allows the usage of multiple robust lists in
the future without any changes to the internal functions as they just operate
on the provided pointer.
This requires a second flag FUTEX_ROBUST_LIST32 which indicates that the
robust list pointer points to an u32 and not to an u64. This is required
for two reasons:
1) sys_futex() has no compat variant
2) The gaming emulators use both both 64-bit and compat 32-bit robust
lists in the same 64-bit application
As a consequence 32-bit applications have to set this flag unconditionally
so they can run on a 64-bit kernel in compat mode unmodified. 32-bit
kernels return an error code when the flag is not set. 64-bit kernels will
happily clear the full 64 bits if user space fails to set it.
In case of FUTEX_UNLOCK_PI this clears the robust list pending op when the
unlock succeeded. In case of errors, the user space value is still locked
by the caller and therefore the above cannot happen.
In case of FUTEX_WAKE* this does the unlock of the futex in the kernel and
clears the robust list pending op when the unlock was successful. If not,
the user space value is still locked and user space has to deal with the
returned error. That means that the unlocking of non-PI robust futexes has
to use the same try_cmpxchg() unlock scheme as PI futexes.
If the clearing of the pending list op fails (fault) then the kernel clears
the registered robust list pointer if it matches to prevent that exit()
will try to handle invalid data. That's a valid paranoid decision because
the robust list head sits usually in the TLS and if the TLS is not longer
accessible then the chance for fixing up the resulting mess is very close
to zero.
The problem of non-contended unlocks still exists and will be addressed
separately.
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxx>
Reviewed-by: André Almeida <andrealmeid@xxxxxxxxxx>
---
V3: Expand changelog to explain @uaddr2 - Andre
V2: Use store release for unlock - Andre, Peter
Use a separate FLAG for 32bit lists - Florian
Add command defines
---
include/uapi/linux/futex.h | 29 +++++++++++++++++++++++-
io_uring/futex.c | 2 -
kernel/futex/core.c | 53 +++++++++++++++++++++++++++++++++++++++++++--
kernel/futex/futex.h | 15 +++++++++++-
kernel/futex/pi.c | 15 +++++++++++-
kernel/futex/syscalls.c | 13 ++++++++---
kernel/futex/waitwake.c | 30 +++++++++++++++++++++++--
7 files changed, 144 insertions(+), 13 deletions(-)
--- a/include/uapi/linux/futex.h
+++ b/include/uapi/linux/futex.h
@@ -25,8 +25,11 @@
#define FUTEX_PRIVATE_FLAG 128
#define FUTEX_CLOCK_REALTIME 256
+#define FUTEX_UNLOCK_ROBUST 512
+#define FUTEX_ROBUST_LIST32 1024
-#define FUTEX_CMD_MASK ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
+#define FUTEX_CMD_MASK ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME | \
+ FUTEX_UNLOCK_ROBUST | FUTEX_ROBUST_LIST32)
#define FUTEX_WAIT_PRIVATE (FUTEX_WAIT | FUTEX_PRIVATE_FLAG)
#define FUTEX_WAKE_PRIVATE (FUTEX_WAKE | FUTEX_PRIVATE_FLAG)
@@ -43,6 +46,30 @@
#define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | FUTEX_PRIVATE_FLAG)
/*
+ * Operations to unlock a futex, clear the robust list pending op pointer and
+ * wake waiters.
+ */
+#define FUTEX_UNLOCK_PI_LIST64 (FUTEX_UNLOCK_PI | FUTEX_UNLOCK_ROBUST)
+#define FUTEX_UNLOCK_PI_LIST64_PRIVATE (FUTEX_UNLOCK_PI_LIST64 | FUTEX_PRIVATE_FLAG)
+#define FUTEX_UNLOCK_PI_LIST32 (FUTEX_UNLOCK_PI | FUTEX_UNLOCK_ROBUST | \
+ FUTEX_ROBUST_LIST32)
+#define FUTEX_UNLOCK_PI_LIST32_PRIVATE (FUTEX_UNLOCK_PI_LIST32 | FUTEX_PRIVATE_FLAG)
+
+#define FUTEX_UNLOCK_WAKE_LIST64 (FUTEX_WAKE | FUTEX_UNLOCK_ROBUST)
+#define FUTEX_UNLOCK_WAKE_LIST64_PRIVATE (FUTEX_UNLOCK_LIST64 | FUTEX_PRIVATE_FLAG)
+
+#define FUTEX_UNLOCK_WAKE_LIST32 (FUTEX_WAKE | FUTEX_UNLOCK_ROBUST | \
+ FUTEX_ROBUST_LIST32)
+#define FUTEX_UNLOCK_WAKE_LIST32_PRIVATE (FUTEX_UNLOCK_LIST32 | FUTEX_PRIVATE_FLAG)
+
+#define FUTEX_UNLOCK_BITSET_LIST64 (FUTEX_WAKE_BITSET | FUTEX_UNLOCK_ROBUST)
+#define FUTEX_UNLOCK_BITSET_LIST64_PRIVATE (FUTEX_UNLOCK_BITSET_LIST64 | FUTEX_PRIVATE_FLAG)
+
+#define FUTEX_UNLOCK_BITSET_LIST32 (FUTEX_WAKE_BITSET | FUTEX_UNLOCK_ROBUST | \
+ FUTEX_ROBUST_LIST32)
+#define FUTEX_UNLOCK_BITSET_LIST32_PRIVATE (FUTEX_UNLOCK_BITSET_LIST32 | FUTEX_PRIVATE_FLAG)
+
+/*
* Flags for futex2 syscalls.
*
* NOTE: these are not pure flags, they can also be seen as:
--- a/io_uring/futex.c
+++ b/io_uring/futex.c
@@ -325,7 +325,7 @@ int io_futex_wake(struct io_kiocb *req,
* Strict flags - ensure that waking 0 futexes yields a 0 result.
* See commit 43adf8449510 ("futex: FLAGS_STRICT") for details.
*/
- ret = futex_wake(iof->uaddr, FLAGS_STRICT | iof->futex_flags,
+ ret = futex_wake(iof->uaddr, FLAGS_STRICT | iof->futex_flags, NULL,
iof->futex_val, iof->futex_mask);
if (ret < 0)
req_set_fail(req);
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -1063,7 +1063,7 @@ static int handle_futex_death(u32 __user
owner = uval & FUTEX_TID_MASK;
if (pending_op && !pi && !owner) {
- futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+ futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1,
FUTEX_BITSET_MATCH_ANY);
return 0;
}
@@ -1117,7 +1117,7 @@ static int handle_futex_death(u32 __user
* PI futexes happens in exit_pi_state():
*/
if (!pi && (uval & FUTEX_WAITERS)) {
- futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1,
+ futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1,
FUTEX_BITSET_MATCH_ANY);
}
@@ -1209,6 +1209,27 @@ static void exit_robust_list(struct task
}
}
+static bool robust_list_clear_pending(unsigned long __user *pop)
+{
+ struct robust_list_head __user *head = current->futex.robust_list;
+
+ if (!put_user(0UL, pop))
+ return true;
+
+ /*
+ * Just give up. The robust list head is usually part of TLS, so the
+ * chance that this gets resolved is close to zero.
+ *
+ * If @pop_addr is the robust_list_head::list_op_pending pointer then
+ * clear the robust list head pointer to prevent further damage when the
+ * task exits. Better a few stale futexes than corrupted memory. But
+ * that's mostly an academic exercise.
+ */
+ if (pop == (unsigned long __user *)&head->list_op_pending)
+ current->futex.robust_list = NULL;
+ return false;
+}
+
#ifdef CONFIG_COMPAT
static void __user *futex_uaddr(struct robust_list __user *entry,
compat_long_t futex_offset)
@@ -1305,6 +1326,21 @@ static void compat_exit_robust_list(stru
handle_futex_death(uaddr, curr, pend_mod, HANDLE_DEATH_PENDING);
}
}
+
+static bool compat_robust_list_clear_pending(u32 __user *pop)
+{
+ struct compat_robust_list_head __user *head = current->futex.compat_robust_list;
+
+ if (!put_user(0U, pop))
+ return true;
+
+ /* See comment in robust_list_clear_pending(). */
+ if (pop == &head->list_op_pending)
+ current->futex.compat_robust_list = NULL;
+ return false;
+}
+#else
+static bool compat_robust_list_clear_pending(u32 __user *pop_addr) { return false; }
#endif
#ifdef CONFIG_FUTEX_PI
@@ -1398,6 +1434,19 @@ static void exit_pi_state_list(struct ta
static inline void exit_pi_state_list(struct task_struct *curr) { }
#endif
+bool futex_robust_list_clear_pending(void __user *pop, unsigned int flags)
+{
+ bool size32bit = !!(flags & FLAGS_ROBUST_LIST32);
+
+ if (!IS_ENABLED(CONFIG_64BIT) && !size32bit)
+ return false;
+
+ if (IS_ENABLED(CONFIG_64BIT) && size32bit)
+ return compat_robust_list_clear_pending(pop);
+
+ return robust_list_clear_pending(pop);
+}
+
static void futex_cleanup(struct task_struct *tsk)
{
if (unlikely(tsk->futex.robust_list)) {
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -40,6 +40,8 @@
#define FLAGS_NUMA 0x0080
#define FLAGS_STRICT 0x0100
#define FLAGS_MPOL 0x0200
+#define FLAGS_UNLOCK_ROBUST 0x0400
+#define FLAGS_ROBUST_LIST32 0x0800
/* FUTEX_ to FLAGS_ */
static inline unsigned int futex_to_flags(unsigned int op)
@@ -52,6 +54,12 @@ static inline unsigned int futex_to_flag
if (op & FUTEX_CLOCK_REALTIME)
flags |= FLAGS_CLOCKRT;
+ if (op & FUTEX_UNLOCK_ROBUST)
+ flags |= FLAGS_UNLOCK_ROBUST;
+
+ if (op & FUTEX_ROBUST_LIST32)
+ flags |= FLAGS_ROBUST_LIST32;
+
return flags;
}
@@ -438,13 +446,16 @@ extern int futex_unqueue_multiple(struct
extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
struct hrtimer_sleeper *to);
-extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset);
+extern int futex_wake(u32 __user *uaddr, unsigned int flags, void __user *pop,
+ int nr_wake, u32 bitset);
extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags,
u32 __user *uaddr2, int nr_wake, int nr_wake2, int op);
-extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags);
+extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags, void __user *pop);
extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock);
+bool futex_robust_list_clear_pending(void __user *pop, unsigned int flags);
+
#endif /* _FUTEX_H */
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -1129,7 +1129,7 @@ int futex_lock_pi(u32 __user *uaddr, uns
* This is the in-kernel slowpath: we look up the PI state (if any),
* and do the rt-mutex unlock.
*/
-int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
+static int __futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
u32 curval, uval, vpid = task_pid_vnr(current);
union futex_key key = FUTEX_KEY_INIT;
@@ -1138,7 +1138,6 @@ int futex_unlock_pi(u32 __user *uaddr, u
if (!IS_ENABLED(CONFIG_FUTEX_PI))
return -ENOSYS;
-
retry:
if (get_user(uval, uaddr))
return -EFAULT;
@@ -1292,3 +1291,15 @@ int futex_unlock_pi(u32 __user *uaddr, u
return ret;
}
+int futex_unlock_pi(u32 __user *uaddr, unsigned int flags, void __user *pop)
+{
+ int ret = __futex_unlock_pi(uaddr, flags);
+
+ if (ret || !(flags & FLAGS_UNLOCK_ROBUST))
+ return ret;
+
+ if (!futex_robust_list_clear_pending(pop, flags))
+ return -EFAULT;
+
+ return 0;
+}
--- a/kernel/futex/syscalls.c
+++ b/kernel/futex/syscalls.c
@@ -118,6 +118,13 @@ long do_futex(u32 __user *uaddr, int op,
return -ENOSYS;
}
+ if (flags & FLAGS_UNLOCK_ROBUST) {
+ if (cmd != FUTEX_WAKE &&
+ cmd != FUTEX_WAKE_BITSET &&
+ cmd != FUTEX_UNLOCK_PI)
+ return -ENOSYS;
+ }
+
switch (cmd) {
case FUTEX_WAIT:
val3 = FUTEX_BITSET_MATCH_ANY;
@@ -128,7 +135,7 @@ long do_futex(u32 __user *uaddr, int op,
val3 = FUTEX_BITSET_MATCH_ANY;
fallthrough;
case FUTEX_WAKE_BITSET:
- return futex_wake(uaddr, flags, val, val3);
+ return futex_wake(uaddr, flags, uaddr2, val, val3);
case FUTEX_REQUEUE:
return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0);
case FUTEX_CMP_REQUEUE:
@@ -141,7 +148,7 @@ long do_futex(u32 __user *uaddr, int op,
case FUTEX_LOCK_PI2:
return futex_lock_pi(uaddr, flags, timeout, 0);
case FUTEX_UNLOCK_PI:
- return futex_unlock_pi(uaddr, flags);
+ return futex_unlock_pi(uaddr, flags, uaddr2);
case FUTEX_TRYLOCK_PI:
return futex_lock_pi(uaddr, flags, NULL, 1);
case FUTEX_WAIT_REQUEUE_PI:
@@ -375,7 +382,7 @@ SYSCALL_DEFINE4(futex_wake,
if (!futex_validate_input(flags, mask))
return -EINVAL;
- return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask);
+ return futex_wake(uaddr, FLAGS_STRICT | flags, NULL, nr, mask);
}
/*
--- a/kernel/futex/waitwake.c
+++ b/kernel/futex/waitwake.c
@@ -150,12 +150,35 @@ void futex_wake_mark(struct wake_q_head
}
/*
+ * If requested, clear the robust list pending op and unlock the futex
+ */
+static bool futex_robust_unlock(u32 __user *uaddr, unsigned int flags, void __user *pop)
+{
+ if (!(flags & FLAGS_UNLOCK_ROBUST))
+ return true;
+
+ /* First unlock the futex, which requires release semantics. */
+ scoped_user_write_access(uaddr, efault)
+ unsafe_atomic_store_release_user(0, uaddr, efault);
+
+ /*
+ * Clear the pending list op now. If that fails, then the task is in
+ * deeper trouble as the robust list head is usually part of the TLS.
+ * The chance of survival is close to zero.
+ */
+ return futex_robust_list_clear_pending(pop, flags);
+
+efault:
+ return false;
+}
+
+/*
* Wake up waiters matching bitset queued on this futex (uaddr).
*/
-int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
+int futex_wake(u32 __user *uaddr, unsigned int flags, void __user *pop, int nr_wake, u32 bitset)
{
- struct futex_q *this, *next;
union futex_key key = FUTEX_KEY_INIT;
+ struct futex_q *this, *next;
DEFINE_WAKE_Q(wake_q);
int ret;
@@ -166,6 +189,9 @@ int futex_wake(u32 __user *uaddr, unsign
if (unlikely(ret != 0))
return ret;
+ if (!futex_robust_unlock(uaddr, flags, pop))
+ return -EFAULT;
+
if ((flags & FLAGS_STRICT) && !nr_wake)
return 0;