[PATCH v6 2/6] locking/rwsem: Disable preemption at all down_read*() and up_read() code paths

[Waiman Long <longman@redhat.com>]

Commit 91d2a812dfb9 ("locking/rwsem: Make handoff writer optimistically
spin on owner") assumes that when the owner field is changed to NULL,
the lock will become free soon. Commit 48dfb5d2560d ("locking/rwsem:
Disable preemption while trying for rwsem lock") disables preemption
when acquiring rwsem for write. However, preemption has not yet been
disabled when acquiring a read lock on a rwsem. So a reader can add a
RWSEM_READER_BIAS to count without setting owner to signal a reader,
got preempted out by a RT task which then spins in the writer slowpath
as owner remains NULL leading to live lock.

One easy way to fix this problem is to disable preemption at all the
down_read*() and up_read() code paths as implemented in this patch.

Fixes: 91d2a812dfb9 ("locking/rwsem: Make handoff writer optimistically spin on owner")
Reported-by: Mukesh Ojha <quic_mojha@quicinc.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/locking/rwsem.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index be2df9ea7c30..ebaff8a87e1d 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1091,7 +1091,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
 			/* Ordered by sem->wait_lock against rwsem_mark_wake(). */
 			break;
 		}
-		schedule();
+		schedule_preempt_disabled();
 		lockevent_inc(rwsem_sleep_reader);
 	}
 
@@ -1253,14 +1253,20 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
  */
 static inline int __down_read_common(struct rw_semaphore *sem, int state)
 {
+	int ret = 0;
 	long count;
 
+	preempt_disable();
 	if (!rwsem_read_trylock(sem, &count)) {
-		if (IS_ERR(rwsem_down_read_slowpath(sem, count, state)))
-			return -EINTR;
+		if (IS_ERR(rwsem_down_read_slowpath(sem, count, state))) {
+			ret = -EINTR;
+			goto out;
+		}
 		DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
 	}
-	return 0;
+out:
+	preempt_enable();
+	return ret;
 }
 
 static inline void __down_read(struct rw_semaphore *sem)
@@ -1280,19 +1286,23 @@ static inline int __down_read_killable(struct rw_semaphore *sem)
 
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
+	int ret = 0;
 	long tmp;
 
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
 
+	preempt_disable();
 	tmp = atomic_long_read(&sem->count);
 	while (!(tmp & RWSEM_READ_FAILED_MASK)) {
 		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
 						    tmp + RWSEM_READER_BIAS)) {
 			rwsem_set_reader_owned(sem);
-			return 1;
+			ret = 1;
+			break;
 		}
 	}
-	return 0;
+	preempt_enable();
+	return ret;
 }
 
 /*
@@ -1334,6 +1344,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
 	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
 
+	preempt_disable();
 	rwsem_clear_reader_owned(sem);
 	tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count);
 	DEBUG_RWSEMS_WARN_ON(tmp < 0, sem);
@@ -1342,6 +1353,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 		clear_nonspinnable(sem);
 		rwsem_wake(sem);
 	}
+	preempt_enable();
 }
 
 /*
-- 
2.31.1