locking/percpu-rwsem: Remove the embedded rwsem

The filesystem freezer uses percpu-rwsem in a way that is effectively
write_non_owner() and achieves this with a few horrible hacks that
rely on the rwsem (!percpu) implementation.

When PREEMPT_RT replaces the rwsem implementation with a PI aware
variant this comes apart.

Remove the embedded rwsem and implement it using a waitqueue and an
atomic_t.

 - make readers_block an atomic, and use it, with the waitqueue
   for a blocking test-and-set write-side.

 - have the read-side wait for the 'lock' state to clear.

Have the waiters use FIFO queueing and mark them (reader/writer) with
a new WQ_FLAG. Use a custom wake_function to wake either a single
writer or all readers until a writer.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Davidlohr Bueso <dbueso@suse.de>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Waiman Long <longman@redhat.com>
Tested-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lkml.kernel.org/r/20200204092403.GB14879@hirez.programming.kicks-ass.net

1 files changed, 6 insertions, 13 deletions

diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index bb5b71c1e446..f5ecf6a8a1dd 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -3,18 +3,18 @@
 #define _LINUX_PERCPU_RWSEM_H
 
 #include <linux/atomic.h>
-#include <linux/rwsem.h>
 #include <linux/percpu.h>
 #include <linux/rcuwait.h>
+#include <linux/wait.h>
 #include <linux/rcu_sync.h>
 #include <linux/lockdep.h>
 
 struct percpu_rw_semaphore {
 	struct rcu_sync		rss;
 	unsigned int __percpu	*read_count;
-	struct rw_semaphore	rw_sem; /* slowpath */
-	struct rcuwait          writer; /* blocked writer */
-	int			readers_block;
+	struct rcuwait		writer;
+	wait_queue_head_t	waiters;
+	atomic_t		block;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
@@ -31,8 +31,9 @@ static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name);		\
 is_static struct percpu_rw_semaphore name = {				\
 	.rss = __RCU_SYNC_INITIALIZER(name.rss),			\
 	.read_count = &__percpu_rwsem_rc_##name,			\
-	.rw_sem = __RWSEM_INITIALIZER(name.rw_sem),			\
 	.writer = __RCUWAIT_INITIALIZER(name.writer),			\
+	.waiters = __WAIT_QUEUE_HEAD_INITIALIZER(name.waiters),		\
+	.block = ATOMIC_INIT(0),					\
 	__PERCPU_RWSEM_DEP_MAP_INIT(name)				\
 }
 
@@ -130,20 +131,12 @@ static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
 					bool read, unsigned long ip)
 {
 	lock_release(&sem->dep_map, ip);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-	if (!read)
-		atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN);
-#endif
 }
 
 static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
 					bool read, unsigned long ip)
 {
 	lock_acquire(&sem->dep_map, 0, 1, read, 1, NULL, ip);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-	if (!read)
-		atomic_long_set(&sem->rw_sem.owner, (long)current);
-#endif
 }
 
 #endif