highmem: Use this_cpu_xx_return() operations

Use this_cpu operations to optimize access primitives for highmem.

The main effect is the avoidance of address calculations through the
use of a segment prefix.

V3->V4
	- kmap_atomic_idx: Do not return a value.
	- Use __this_cpu_dec without HIGHMEM_DEBUG

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index b676c58..3a93f73 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -81,7 +81,8 @@
 
 static inline int kmap_atomic_idx_push(void)
 {
-	int idx = __get_cpu_var(__kmap_atomic_idx)++;
+	int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1;
+
 #ifdef CONFIG_DEBUG_HIGHMEM
 	WARN_ON_ONCE(in_irq() && !irqs_disabled());
 	BUG_ON(idx > KM_TYPE_NR);
@@ -91,16 +92,18 @@
 
 static inline int kmap_atomic_idx(void)
 {
-	return __get_cpu_var(__kmap_atomic_idx) - 1;
+	return __this_cpu_read(__kmap_atomic_idx) - 1;
 }
 
-static inline int kmap_atomic_idx_pop(void)
+static inline void kmap_atomic_idx_pop(void)
 {
-	int idx = --__get_cpu_var(__kmap_atomic_idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
+	int idx = __this_cpu_dec_return(__kmap_atomic_idx);
+
 	BUG_ON(idx < 0);
+#else
+	__this_cpu_dec(__kmap_atomic_idx);
 #endif
-	return idx;
 }
 
 #endif