locking/barriers: Introduce smp_acquire__after_ctrl_dep()

Introduce smp_acquire__after_ctrl_dep(), this construct is not
uncommon, but the lack of this barrier is.

Use it to better express smp_rmb() uses in WRITE_ONCE(), the IPC
semaphore code and the qspinlock code.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/compiler.h

@@ -304,6 +304,17 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	__u.__val;					\
 })
 
+/**
+ * smp_acquire__after_ctrl_dep() - Provide ACQUIRE ordering after a control dependency
+ *
+ * A control dependency provides a LOAD->STORE order, the additional RMB
+ * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
+ * aka. (load)-ACQUIRE.
+ *
+ * Architectures that do not do load speculation can have this be barrier().
+ */
+#define smp_acquire__after_ctrl_dep()		smp_rmb()
+
 /**
  * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
  * @ptr: pointer to the variable to wait on
@@ -314,10 +325,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  *
  * Due to C lacking lambda expressions we load the value of *ptr into a
  * pre-named variable @VAL to be used in @cond.
- *
- * The control dependency provides a LOAD->STORE order, the additional RMB
- * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
- * aka. ACQUIRE.
  */
 #ifndef smp_cond_load_acquire
 #define smp_cond_load_acquire(ptr, cond_expr) ({		\
@@ -329,7 +336,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 			break;					\
 		cpu_relax();					\
 	}							\
-	smp_rmb(); /* ctrl + rmb := acquire */			\
+	smp_acquire__after_ctrl_dep();				\
 	VAL;							\
 })
 #endif

ipc/sem.c

@@ -259,16 +259,6 @@ static void sem_rcu_free(struct rcu_head *head)
 	ipc_rcu_free(head);
 }
 
-/*
- * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they
- * are only control barriers.
- * The code must pair with spin_unlock(&sem->lock) or
- * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient.
- *
- * smp_rmb() is sufficient, as writes cannot pass the control barrier.
- */
-#define ipc_smp_acquire__after_spin_is_unlocked()	smp_rmb()
-
 /*
  * Wait until all currently ongoing simple ops have completed.
  * Caller must own sem_perm.lock.
@@ -292,7 +282,7 @@ static void sem_wait_array(struct sem_array *sma)
 		sem = sma->sem_base + i;
 		spin_unlock_wait(&sem->lock);
 	}
-	ipc_smp_acquire__after_spin_is_unlocked();
+	smp_acquire__after_ctrl_dep();
 }
 
 /*
@@ -350,7 +340,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 			 *	complex_count++;
 			 *	spin_unlock(sem_perm.lock);
 			 */
-			ipc_smp_acquire__after_spin_is_unlocked();
+			smp_acquire__after_ctrl_dep();
 
 			/*
 			 * Now repeat the test of complex_count:

kernel/locking/qspinlock.c

@@ -379,7 +379,7 @@ void queued_spin_unlock_wait(struct qspinlock *lock)
 		cpu_relax();
 
 done:
-	smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+	smp_acquire__after_ctrl_dep();
 }
 EXPORT_SYMBOL(queued_spin_unlock_wait);
 #endif