Merge tag 'locking_urgent_for_v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking fix from Borislav Petkov:

 - Avoid rwsem lockups in certain situations when handling the handoff
   bit

* tag 'locking_urgent_for_v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/rwsem: Allow slowpath writer to ignore handoff bit if not set by first waiter

1 files changed, 20 insertions, 10 deletions

diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 9d1db4a54d34..65f0262f635e 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -335,8 +335,6 @@ struct rwsem_waiter {
 	struct task_struct *task;
 	enum rwsem_waiter_type type;
 	unsigned long timeout;
-
-	/* Writer only, not initialized in reader */
 	bool handoff_set;
 };
 #define rwsem_first_waiter(sem) \
@@ -459,10 +457,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 			 * to give up the lock), request a HANDOFF to
 			 * force the issue.
 			 */
-			if (!(oldcount & RWSEM_FLAG_HANDOFF) &&
-			    time_after(jiffies, waiter->timeout)) {
-				adjustment -= RWSEM_FLAG_HANDOFF;
-				lockevent_inc(rwsem_rlock_handoff);
+			if (time_after(jiffies, waiter->timeout)) {
+				if (!(oldcount & RWSEM_FLAG_HANDOFF)) {
+					adjustment -= RWSEM_FLAG_HANDOFF;
+					lockevent_inc(rwsem_rlock_handoff);
+				}
+				waiter->handoff_set = true;
 			}
 
 			atomic_long_add(-adjustment, &sem->count);
@@ -599,7 +599,7 @@ rwsem_del_wake_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter,
 static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 					struct rwsem_waiter *waiter)
 {
-	bool first = rwsem_first_waiter(sem) == waiter;
+	struct rwsem_waiter *first = rwsem_first_waiter(sem);
 	long count, new;
 
 	lockdep_assert_held(&sem->wait_lock);
@@ -609,11 +609,20 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
 
 		if (has_handoff) {
-			if (!first)
+			/*
+			 * Honor handoff bit and yield only when the first
+			 * waiter is the one that set it. Otherwisee, we
+			 * still try to acquire the rwsem.
+			 */
+			if (first->handoff_set && (waiter != first))
 				return false;
 
-			/* First waiter inherits a previously set handoff bit */
-			waiter->handoff_set = true;
+			/*
+			 * First waiter can inherit a previously set handoff
+			 * bit and spin on rwsem if lock acquisition fails.
+			 */
+			if (waiter == first)
+				waiter->handoff_set = true;
 		}
 
 		new = count;
@@ -1027,6 +1036,7 @@ queue:
 	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_READ;
 	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+	waiter.handoff_set = false;
 
 	raw_spin_lock_irq(&sem->wait_lock);
 	if (list_empty(&sem->wait_list)) {