To support runtime resizing of the process private hash, it's required
to not use the obtained hash bucket once the reference count has been
dropped. The reference will be dropped after the unlock of the hash
bucket.
The amount of waiters is decremented after the unlock operation. There
is no requirement that this needs to happen after the unlock. The
increment happens before acquiring the lock to signal early that there
will be a waiter. The waiter can avoid blocking on the lock if it is
known that there will be no waiter.
There is no difference in terms of ordering if the decrement happens
before or after the unlock.

Decrease the waiter count before the unlock operation.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 kernel/futex/core.c    | 2 +-
 kernel/futex/requeue.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 6a1d6b14277f4..5e70cb8eb2507 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -537,8 +537,8 @@ void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb)
 void futex_q_unlock(struct futex_hash_bucket *hb)
 	__releases(&hb->lock)
 {
-	spin_unlock(&hb->lock);
 	futex_hb_waiters_dec(hb);
+	spin_unlock(&hb->lock);
 }
 
 void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c
index 992e3ce005c6f..023c028d2fce3 100644
--- a/kernel/futex/requeue.c
+++ b/kernel/futex/requeue.c
@@ -456,8 +456,8 @@ int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
 			ret = futex_get_value_locked(&curval, uaddr1);
 
 			if (unlikely(ret)) {
-				double_unlock_hb(hb1, hb2);
 				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
 
 				ret = get_user(curval, uaddr1);
 				if (ret)
@@ -542,8 +542,8 @@ int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
 				 * waiter::requeue_state is correct.
 				 */
 			case -EFAULT:
-				double_unlock_hb(hb1, hb2);
 				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
 				ret = fault_in_user_writeable(uaddr2);
 				if (!ret)
 					goto retry;
@@ -556,8 +556,8 @@ int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
 				 *   exit to complete.
 				 * - EAGAIN: The user space value changed.
 				 */
-				double_unlock_hb(hb1, hb2);
 				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
 				/*
 				 * Handle the case where the owner is in the middle of
 				 * exiting. Wait for the exit to complete otherwise
@@ -674,8 +674,8 @@ int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
 		put_pi_state(pi_state);
 
 out_unlock:
-		double_unlock_hb(hb1, hb2);
 		futex_hb_waiters_dec(hb2);
+		double_unlock_hb(hb1, hb2);
 	}
 	wake_up_q(&wake_q);
 	return ret ? ret : task_count;
-- 
2.49.0

The following commit has been merged into the locking/futex branch of tip:

Commit-ID:     fe00e88d217a7bf7a4d0268d08f51e624d40ee53
Gitweb:        https://git.kernel.org/tip/fe00e88d217a7bf7a4d0268d08f51e624d40ee53
Author:        Sebastian Andrzej Siewior <bigeasy@linutronix.de>
AuthorDate:    Wed, 16 Apr 2025 18:29:09 +02:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Sat, 03 May 2025 12:02:06 +02:00

futex: Decrease the waiter count before the unlock operation

To support runtime resizing of the process private hash, it's required
to not use the obtained hash bucket once the reference count has been
dropped. The reference will be dropped after the unlock of the hash
bucket.
The amount of waiters is decremented after the unlock operation. There
is no requirement that this needs to happen after the unlock. The
increment happens before acquiring the lock to signal early that there
will be a waiter. The waiter can avoid blocking on the lock if it is
known that there will be no waiter.
There is no difference in terms of ordering if the decrement happens
before or after the unlock.

Decrease the waiter count before the unlock operation.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250416162921.513656-10-bigeasy@linutronix.de
---
 kernel/futex/core.c    | 2 +-
 kernel/futex/requeue.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 6a1d6b1..5e70cb8 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -537,8 +537,8 @@ void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb)
 void futex_q_unlock(struct futex_hash_bucket *hb)
 	__releases(&hb->lock)
 {
-	spin_unlock(&hb->lock);
 	futex_hb_waiters_dec(hb);
+	spin_unlock(&hb->lock);
 }
 
 void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c
index 992e3ce..023c028 100644
--- a/kernel/futex/requeue.c
+++ b/kernel/futex/requeue.c
@@ -456,8 +456,8 @@ retry_private:
 			ret = futex_get_value_locked(&curval, uaddr1);
 
 			if (unlikely(ret)) {
-				double_unlock_hb(hb1, hb2);
 				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
 
 				ret = get_user(curval, uaddr1);
 				if (ret)
@@ -542,8 +542,8 @@ retry_private:
 				 * waiter::requeue_state is correct.
 				 */
 			case -EFAULT:
-				double_unlock_hb(hb1, hb2);
 				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
 				ret = fault_in_user_writeable(uaddr2);
 				if (!ret)
 					goto retry;
@@ -556,8 +556,8 @@ retry_private:
 				 *   exit to complete.
 				 * - EAGAIN: The user space value changed.
 				 */
-				double_unlock_hb(hb1, hb2);
 				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
 				/*
 				 * Handle the case where the owner is in the middle of
 				 * exiting. Wait for the exit to complete otherwise
@@ -674,8 +674,8 @@ retry_private:
 		put_pi_state(pi_state);
 
 out_unlock:
-		double_unlock_hb(hb1, hb2);
 		futex_hb_waiters_dec(hb2);
+		double_unlock_hb(hb1, hb2);
 	}
 	wake_up_q(&wake_q);
 	return ret ? ret : task_count;