diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 303871651f8a..bc490a746602 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -19,6 +19,7 @@
 #include <asm-generic/iomap.h>
 #endif
 
+#include <asm/mmiowb.h>
 #include <asm-generic/pci_iomap.h>
 
 #ifndef mmiowb
@@ -49,7 +50,7 @@
 
 /* serialize device access against a spin_unlock, usually handled there. */
 #ifndef __io_aw
-#define __io_aw()      barrier()
+#define __io_aw()      mmiowb_set_pending()
 #endif
 
 #ifndef __io_pbw
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index e089157dcf97..ed7c4d6b8235 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -57,6 +57,7 @@
 #include <linux/stringify.h>
 #include <linux/bottom_half.h>
 #include <asm/barrier.h>
+#include <asm/mmiowb.h>
 
 
 /*
@@ -178,6 +179,7 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
 {
 	__acquire(lock);
 	arch_spin_lock(&lock->raw_lock);
+	mmiowb_spin_lock();
 }
 
 #ifndef arch_spin_lock_flags
@@ -189,15 +191,22 @@ do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lo
 {
 	__acquire(lock);
 	arch_spin_lock_flags(&lock->raw_lock, *flags);
+	mmiowb_spin_lock();
 }
 
 static inline int do_raw_spin_trylock(raw_spinlock_t *lock)
 {
-	return arch_spin_trylock(&(lock)->raw_lock);
+	int ret = arch_spin_trylock(&(lock)->raw_lock);
+
+	if (ret)
+		mmiowb_spin_lock();
+
+	return ret;
 }
 
 static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 {
+	mmiowb_spin_unlock();
 	arch_spin_unlock(&lock->raw_lock);
 	__release(lock);
 }
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 9aa0fccd5d43..399669f7eba8 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -111,6 +111,7 @@ void do_raw_spin_lock(raw_spinlock_t *lock)
 {
 	debug_spin_lock_before(lock);
 	arch_spin_lock(&lock->raw_lock);
+	mmiowb_spin_lock();
 	debug_spin_lock_after(lock);
 }
 
@@ -118,8 +119,10 @@ int do_raw_spin_trylock(raw_spinlock_t *lock)
 {
 	int ret = arch_spin_trylock(&lock->raw_lock);
 
-	if (ret)
+	if (ret) {
+		mmiowb_spin_lock();
 		debug_spin_lock_after(lock);
+	}
 #ifndef CONFIG_SMP
 	/*
 	 * Must not happen on UP:
@@ -131,6 +134,7 @@ int do_raw_spin_trylock(raw_spinlock_t *lock)
 
 void do_raw_spin_unlock(raw_spinlock_t *lock)
 {
+	mmiowb_spin_unlock();
 	debug_spin_unlock(lock);
 	arch_spin_unlock(&lock->raw_lock);
 }