[GIT PULL] futex fix

[GIT PULL] futex fix

[Ingo Molnar]

Linus,

Please pull the latest core-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus

 Thanks,

	Ingo

------------------>
Thomas Gleixner (1):
      futex: Fix spurious wakeup for requeue_pi really


 kernel/futex.c |    6 +-----
 1 files changed, 1 insertions(+), 5 deletions(-)

diff --git a/kernel/futex.c b/kernel/futex.c
index 642f3bb..fb65e82 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2127,7 +2127,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
 		plist_del(&q->list, &q->list.plist);
 
 		/* Handle spurious wakeups gracefully */
-		ret = -EAGAIN;
+		ret = -EWOULDBLOCK;
 		if (timeout && !timeout->task)
 			ret = -ETIMEDOUT;
 		else if (signal_pending(current))
@@ -2208,7 +2208,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
 	debug_rt_mutex_init_waiter(&rt_waiter);
 	rt_waiter.task = NULL;
 
-retry:
 	key2 = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
@@ -2303,9 +2302,6 @@ out_put_keys:
 out_key2:
 	put_futex_key(fshared, &key2);
 
-	/* Spurious wakeup ? */
-	if (ret == -EAGAIN)
-		goto retry;
 out:
 	if (to) {
 		hrtimer_cancel(&to->timer);

[GIT PULL] futex fix

[Ingo Molnar]

Linus,

Please pull the latest core-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus

 Thanks,

	Ingo

------------------>
KOSAKI Motohiro (1):
      futexes: Remove rw parameter from get_futex_key()


 kernel/futex.c |   27 ++++++++++++---------------
 1 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/kernel/futex.c b/kernel/futex.c
index 8e3c3ff..d9b3a22 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -203,8 +203,6 @@ static void drop_futex_key_refs(union futex_key *key)
  * @uaddr:	virtual address of the futex
  * @fshared:	0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
  * @key:	address where result is stored.
- * @rw:		mapping needs to be read/write (values: VERIFY_READ,
- * 		VERIFY_WRITE)
  *
  * Returns a negative error code or 0
  * The key words are stored in *key on success.
@@ -216,7 +214,7 @@ static void drop_futex_key_refs(union futex_key *key)
  * lock_page() might sleep, the caller should not hold a spinlock.
  */
 static int
-get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
+get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
@@ -239,7 +237,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	 *        but access_ok() should be faster than find_vma()
 	 */
 	if (!fshared) {
-		if (unlikely(!access_ok(rw, uaddr, sizeof(u32))))
+		if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
 			return -EFAULT;
 		key->private.mm = mm;
 		key->private.address = address;
@@ -248,7 +246,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	}
 
 again:
-	err = get_user_pages_fast(address, 1, rw == VERIFY_WRITE, &page);
+	err = get_user_pages_fast(address, 1, 1, &page);
 	if (err < 0)
 		return err;
 
@@ -867,7 +865,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 	if (!bitset)
 		return -EINVAL;
 
-	ret = get_futex_key(uaddr, fshared, &key, VERIFY_READ);
+	ret = get_futex_key(uaddr, fshared, &key);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -913,10 +911,10 @@ futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 	int ret, op_ret;
 
 retry:
-	ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ);
+	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
+	ret = get_futex_key(uaddr2, fshared, &key2);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -1175,11 +1173,10 @@ retry:
 		pi_state = NULL;
 	}
 
-	ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ);
+	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, fshared, &key2,
-			    requeue_pi ? VERIFY_WRITE : VERIFY_READ);
+	ret = get_futex_key(uaddr2, fshared, &key2);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -1738,7 +1735,7 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared,
 	 */
 retry:
 	q->key = FUTEX_KEY_INIT;
-	ret = get_futex_key(uaddr, fshared, &q->key, VERIFY_READ);
+	ret = get_futex_key(uaddr, fshared, &q->key);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -1904,7 +1901,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared,
 	q.requeue_pi_key = NULL;
 retry:
 	q.key = FUTEX_KEY_INIT;
-	ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE);
+	ret = get_futex_key(uaddr, fshared, &q.key);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -2023,7 +2020,7 @@ retry:
 	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
 		return -EPERM;
 
-	ret = get_futex_key(uaddr, fshared, &key, VERIFY_WRITE);
+	ret = get_futex_key(uaddr, fshared, &key);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -2215,7 +2212,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
 	rt_waiter.task = NULL;
 
 	key2 = FUTEX_KEY_INIT;
-	ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
+	ret = get_futex_key(uaddr2, fshared, &key2);
 	if (unlikely(ret != 0))
 		goto out;
 

[GIT PULL] futex fix

[Ingo Molnar]

Linus,

Please pull the latest core-fixes-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus

 Thanks,

	Ingo

------------------>
Darren Hart (1):
      futex: Set FLAGS_HAS_TIMEOUT during futex_wait restart setup


 kernel/futex.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/futex.c b/kernel/futex.c
index dfb924f..fe28dc2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1886,7 +1886,7 @@ retry:
 	restart->futex.val = val;
 	restart->futex.time = abs_time->tv64;
 	restart->futex.bitset = bitset;
-	restart->futex.flags = flags;
+	restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
 
 	ret = -ERESTART_RESTARTBLOCK;
 

[GIT PULL] futex fix

[Ingo Molnar]

Linus,

Please pull the latest locking-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-for-linus

   # HEAD: da791a667536bf8322042e38ca85d55a78d3c273 futex: Cure exit race

A single fix for a robust futexes race between sys_exit() and 
sys_futex_lock_pi().

 Thanks,

	Ingo

------------------>
Thomas Gleixner (1):
      futex: Cure exit race


 kernel/futex.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 63 insertions(+), 6 deletions(-)

diff --git a/kernel/futex.c b/kernel/futex.c
index f423f9b6577e..5cc8083a4c89 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1148,11 +1148,65 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
 	return ret;
 }
 
+static int handle_exit_race(u32 __user *uaddr, u32 uval,
+			    struct task_struct *tsk)
+{
+	u32 uval2;
+
+	/*
+	 * If PF_EXITPIDONE is not yet set, then try again.
+	 */
+	if (tsk && !(tsk->flags & PF_EXITPIDONE))
+		return -EAGAIN;
+
+	/*
+	 * Reread the user space value to handle the following situation:
+	 *
+	 * CPU0				CPU1
+	 *
+	 * sys_exit()			sys_futex()
+	 *  do_exit()			 futex_lock_pi()
+	 *                                futex_lock_pi_atomic()
+	 *   exit_signals(tsk)		    No waiters:
+	 *    tsk->flags |= PF_EXITING;	    *uaddr == 0x00000PID
+	 *  mm_release(tsk)		    Set waiter bit
+	 *   exit_robust_list(tsk) {	    *uaddr = 0x80000PID;
+	 *      Set owner died		    attach_to_pi_owner() {
+	 *    *uaddr = 0xC0000000;	     tsk = get_task(PID);
+	 *   }				     if (!tsk->flags & PF_EXITING) {
+	 *  ...				       attach();
+	 *  tsk->flags |= PF_EXITPIDONE;     } else {
+	 *				       if (!(tsk->flags & PF_EXITPIDONE))
+	 *				         return -EAGAIN;
+	 *				       return -ESRCH; <--- FAIL
+	 *				     }
+	 *
+	 * Returning ESRCH unconditionally is wrong here because the
+	 * user space value has been changed by the exiting task.
+	 *
+	 * The same logic applies to the case where the exiting task is
+	 * already gone.
+	 */
+	if (get_futex_value_locked(&uval2, uaddr))
+		return -EFAULT;
+
+	/* If the user space value has changed, try again. */
+	if (uval2 != uval)
+		return -EAGAIN;
+
+	/*
+	 * The exiting task did not have a robust list, the robust list was
+	 * corrupted or the user space value in *uaddr is simply bogus.
+	 * Give up and tell user space.
+	 */
+	return -ESRCH;
+}
+
 /*
  * Lookup the task for the TID provided from user space and attach to
  * it after doing proper sanity checks.
  */
-static int attach_to_pi_owner(u32 uval, union futex_key *key,
+static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
 			      struct futex_pi_state **ps)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
@@ -1162,12 +1216,15 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
 	/*
 	 * We are the first waiter - try to look up the real owner and attach
 	 * the new pi_state to it, but bail out when TID = 0 [1]
+	 *
+	 * The !pid check is paranoid. None of the call sites should end up
+	 * with pid == 0, but better safe than sorry. Let the caller retry
 	 */
 	if (!pid)
-		return -ESRCH;
+		return -EAGAIN;
 	p = find_get_task_by_vpid(pid);
 	if (!p)
-		return -ESRCH;
+		return handle_exit_race(uaddr, uval, NULL);
 
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		put_task_struct(p);
@@ -1187,7 +1244,7 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
 		 * set, we know that the task has finished the
 		 * cleanup:
 		 */
-		int ret = (p->flags & PF_EXITPIDONE) ? -ESRCH : -EAGAIN;
+		int ret = handle_exit_race(uaddr, uval, p);
 
 		raw_spin_unlock_irq(&p->pi_lock);
 		put_task_struct(p);
@@ -1244,7 +1301,7 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 	 * We are the first waiter - try to look up the owner based on
 	 * @uval and attach to it.
 	 */
-	return attach_to_pi_owner(uval, key, ps);
+	return attach_to_pi_owner(uaddr, uval, key, ps);
 }
 
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
@@ -1352,7 +1409,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 	 * attach to the owner. If that fails, no harm done, we only
 	 * set the FUTEX_WAITERS bit in the user space variable.
 	 */
-	return attach_to_pi_owner(uval, key, ps);
+	return attach_to_pi_owner(uaddr, newval, key, ps);
 }
 
 /**

Re: [GIT PULL] futex fix

[pr-tracker-bot]

The pull request you sent on Fri, 21 Dec 2018 13:30:15 +0100:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-for-linus

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/d5fa080d4ceaa8fec0fb28e27c7447caf4b4d22b

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker

[GIT PULL] futex fix

[Ingo Molnar]

Linus,

Please pull the latest locking/urgent Git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-2026-07-05

for you to fetch changes up to 39def6d250d370298f86c116f4ac60093cefadaa:

 - Fix a futex-requeue deadlock detection regression
   (Thomas Gleixner)

 Thanks,

	Ingo

------------------>
Sebastian Andrzej Siewior (1):
      futex/requeue: Revert "Prevent NULL pointer dereference in remove_waiter() on self-deadlock""


 kernel/futex/requeue.c | 6 ------
 1 file changed, 6 deletions(-)

Re: [GIT PULL] futex fix

[pr-tracker-bot]

The pull request you sent on Sun, 5 Jul 2026 09:32:20 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-2026-07-05

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/fe5881ed7293813e492ad165292ae652b676ff6c

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html

[GIT PULL] futex fix

[Ingo Molnar]

Linus,

Please pull the latest locking/urgent Git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-2026-08-04

for you to fetch changes up to 6d4514ca9cdf61fec4ec634cf50386f6f7e69748:

 - Fix a robust futexes exit race (Keno Fischer)

 Thanks,

	Ingo

------------------>
Keno Fischer (1):
      futex: Prevent robust futex exit race some more


 kernel/futex/core.c | 85 ++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 58 insertions(+), 27 deletions(-)

diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 179b26e9c934..2650d1e52803 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -982,8 +982,11 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
 		return -1;
 
 	/*
-	 * Special case for regular (non PI) futexes. The unlock path in
-	 * user space has two race scenarios:
+	 * Special case for regular (non PI) futexes. Ordinarily, we do
+	 * not perform any processing here unless the current thread was
+	 * the owner of the futex (by the TID check below).
+	 *
+	 * However, the unlock path has three race scenarios:
 	 *
 	 * 1. The unlock path releases the user space futex value and
 	 *    before it can execute the futex() syscall to wake up
@@ -992,42 +995,70 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
 	 * 2. A woken up waiter is killed before it can acquire the
 	 *    futex in user space.
 	 *
-	 * In the second case, the wake up notification could be generated
-	 * by the unlock path in user space after setting the futex value
-	 * to zero or by the kernel after setting the OWNER_DIED bit below.
+	 * 3. A woken up waiter is killed in user space after another
+	 *    thread has acquired the futex, but before it can set
+	 *    FUTEX_WAITERS.
+	 *
+	 * Note that, if userspace uses the FUTEX_ROBUST_UNLOCK flag, we
+	 * will not see case 1 here.
+	 *
+	 * In the second and third case, the wake up notification could
+	 * be generated from any of:
+	 *
+	 *    i.   An ordinary futex wakeup after unlock (with or
+	 *         without FUTEX_ROBUST_UNLOCK)
+	 *    ii.  A robust wakeup from another thread's death
+	 *    iii. A previous round through this special case
+	 *
+	 * As a result, the futex world will be in one of four states:
+	 *
+	 *    A. The futex word is 0 (unlocked)
+	 *    B. The futex word is owned by another thread
+	 *       (FUTEX_WAITERS is not set)
+	 *    C. The futex word is owned by another thread
+	 *       (FUTEX_WAITERS set)
+	 *    D. The futex's owner died and OWNER_DIED is set
+	 *       (the owner part of the word is 0)
 	 *
-	 * In both cases the TID validation below prevents a wakeup of
-	 * potential waiters which can cause these waiters to block
-	 * forever.
+	 * The key issue is that the kernel usually (at least from
+	 * sources ii. and iii. or when so requested by userspace from
+	 * source i.) only ever wakes *one* waiter at a time. If this
+	 * waiter dies before acquiring the futex (or setting the
+	 * FUTEX_WAITERS bit), the kernel *must* still wake the next
+	 * waiter down the line to uphold the futex invariants and
+	 * avoid lost wakeups. Note we do not need to handle state C,
+	 * as it does not matter to us whether *we* successfully set
+	 * the bit or a third thread did so in the meantime.
 	 *
-	 * In both cases the following conditions are met:
+	 * Therefore, in these cases we must issue an additional
+	 * futex_wake(). Note however that we *must not* set OWNER_DIED
+	 * here. Our thread is *not* the owner of the futex.
 	 *
-	 *	1) task->futex.robust_list->list_op_pending != NULL
-	 *	   @pending_op == true
-	 *	2) The owner part of user space futex value == 0
+	 * Thus to summarize, the conditions for needing the additional
+	 * futex_wake() are:
+	 *
+	 *	1) @pending_op == true (the thread has not finished the
+	 *	   mutex operation)
+	 *	2) The futex word is in one of the states A, B or D
 	 *	3) Regular futex: @pi == false
 	 *
-	 * If these conditions are met, it is safe to attempt waking up a
-	 * potential waiter without touching the user space futex value and
-	 * trying to set the OWNER_DIED bit. If the futex value is zero,
-	 * the rest of the user space mutex state is consistent, so a woken
-	 * waiter will just take over the uncontended futex. Setting the
-	 * OWNER_DIED bit would create inconsistent state and malfunction
-	 * of the user space owner died handling. Otherwise, the OWNER_DIED
-	 * bit is already set, and the woken waiter is expected to deal with
-	 * this.
+	 * Note in particular that in all of the states A-D the owner
+	 * portion of the futex word differs from our thread's TID
+	 * (unless the actual owner has the same TID in another PID
+	 * namespace, but we cannot currently distinguish that
+	 * scenario), so this can be a special-case wakeup in the bail
+	 * path of the ordinary TID check.
 	 */
 	owner = uval & FUTEX_TID_MASK;
 
-	if (pending_op && !pi && !owner) {
-		futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1,
-			   FUTEX_BITSET_MATCH_ANY);
+	if (owner != task_pid_vnr(curr)) {
+		if (pending_op && !pi && (!owner || !(uval & FUTEX_WAITERS))) {
+			futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, NULL, 1,
+				   FUTEX_BITSET_MATCH_ANY);
+		}
 		return 0;
 	}
 
-	if (owner != task_pid_vnr(curr))
-		return 0;
-
 	/*
 	 * Ok, this dying thread is truly holding a futex
 	 * of interest. Set the OWNER_DIED bit atomically

Re: [GIT PULL] futex fix

[pr-tracker-bot]

The pull request you sent on Tue, 4 Aug 2026 20:02:05 +0200:

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-urgent-2026-08-04

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/31996e14bd59840692d6c1c6e41ef878b77a2967

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html