The current percpu-rwsem read side is entirely free of serializing
instructions at the cost of having a synchronize_sched() in the write
path.

The latency of the synchronize_sched() is too high for some users
(cgroups), so provide a __percpu_init_rwsem(.bias) argument to forgot
this synchronize_sched() at the cost of forcing all readers into the
slow path, which has serializing instructions.

Cc: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Reported-by: John Stultz <john.stultz@linaro.org>
Reported-by: Dmitry Shmidt <dimitrysh@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 fs/super.c                    |    3 ++-
 include/linux/percpu-rwsem.h  |   15 +++++++++++++--
 kernel/cgroup.c               |    2 +-
 kernel/locking/percpu-rwsem.c |   10 +++++++++-
 4 files changed, 25 insertions(+), 5 deletions(-)

--- a/fs/super.c
+++ b/fs/super.c
@@ -195,7 +195,8 @@ static struct super_block *alloc_super(s
 	for (i = 0; i < SB_FREEZE_LEVELS; i++) {
 		if (__percpu_init_rwsem(&s->s_writers.rw_sem[i],
 					sb_writers_name[i],
-					&type->s_writers_key[i]))
+					&type->s_writers_key[i],
+					PERCPU_RWSEM_READER))
 			goto fail;
 	}
 	init_waitqueue_head(&s->s_writers.wait_unfrozen);
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -90,15 +90,26 @@ static inline void percpu_up_read(struct
 extern void percpu_down_write(struct percpu_rw_semaphore *);
 extern void percpu_up_write(struct percpu_rw_semaphore *);
 
+enum percpu_rwsem_bias { PERCPU_RWSEM_READER, PERCPU_RWSEM_WRITER };
+
 extern int __percpu_init_rwsem(struct percpu_rw_semaphore *,
-				const char *, struct lock_class_key *);
+				const char *, struct lock_class_key *,
+				enum percpu_rwsem_bias bias);
 
 extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
 
 #define percpu_init_rwsem(sem)					\
 ({								\
 	static struct lock_class_key rwsem_key;			\
-	__percpu_init_rwsem(sem, #sem, &rwsem_key);		\
+	__percpu_init_rwsem(sem, #sem, &rwsem_key,		\
+			    PERCPU_RWSEM_READER);		\
+})
+
+#define percpu_init_rwsem_writer(sem)				\
+({								\
+	static struct lock_class_key rwsem_key;			\
+	__percpu_init_rwsem(sem, #sem, &rwsem_key,		\
+			    PERCPU_RWSEM_WRITER);		\
 })
 
 #define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -5605,7 +5605,7 @@ int __init cgroup_init(void)
 	int ssid;
 
 	BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
-	BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
+	BUG_ON(percpu_init_rwsem_writer(&cgroup_threadgroup_rwsem));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
 
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -11,7 +11,8 @@
 enum { readers_slow, readers_block };
 
 int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
-			const char *name, struct lock_class_key *rwsem_key)
+			const char *name, struct lock_class_key *rwsem_key,
+			enum percpu_rwsem_bias bias)
 {
 	sem->read_count = alloc_percpu(int);
 	if (unlikely(!sem->read_count))
@@ -19,6 +20,13 @@ int __percpu_init_rwsem(struct percpu_rw
 
 	/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
 	rcu_sync_init(&sem->rss, RCU_SCHED_SYNC);
+	if (bias == PERCPU_RWSEM_WRITER) {
+		/*
+		 * Disable rcu_sync() and force slow path.
+		 */
+		sem->rss.gp_count++;
+		sem->rss.gp_state = !0;
+	}
 	__init_rwsem(&sem->rw_sem, name, rwsem_key);
 	init_waitqueue_head(&sem->writer);
 	sem->state = readers_slow;