diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index ca6f0491412b..fded453fd25c 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -41,7 +41,9 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
  * Only S390 provides its own means of moving the pointer.
  */
 #ifndef SHIFT_PERCPU_PTR
-#define SHIFT_PERCPU_PTR(__p, __offset)	RELOC_HIDE((__p), (__offset))
+/* Weird cast keeps both GCC and sparse happy. */
+#define SHIFT_PERCPU_PTR(__p, __offset)				\
+	RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset))
 #endif
 
 /*
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 04fb5135b4e1..abba8045c6ef 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -5,7 +5,7 @@
 
 #ifdef __CHECKER__
 # define __user		__attribute__((noderef, address_space(1)))
-# define __kernel	/* default address space */
+# define __kernel	__attribute__((address_space(0)))
 # define __safe		__attribute__((safe))
 # define __force	__attribute__((force))
 # define __nocast	__attribute__((nocast))
@@ -15,6 +15,7 @@
 # define __acquire(x)	__context__(x,1)
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
+# define __percpu	__attribute__((noderef, address_space(3)))
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
 #else
@@ -32,6 +33,7 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # define __acquire(x) (void)0
 # define __release(x) (void)0
 # define __cond_lock(x,c) (c)
+# define __percpu
 #endif
 
 #ifdef __KERNEL__
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index ee99f6c2cdcd..0fa0cb524250 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -12,7 +12,7 @@
  * that section.
  */
 #define __PCPU_ATTRS(sec)						\
-	__attribute__((section(PER_CPU_BASE_SECTION sec)))		\
+	__percpu __attribute__((section(PER_CPU_BASE_SECTION sec)))	\
 	PER_CPU_ATTRIBUTES
 
 #define __PCPU_DUMMY_ATTRS						\
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index f965f833a643..2c0d31a3f6b6 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -30,8 +30,12 @@
 	preempt_disable();				\
 	&__get_cpu_var(var); }))
 
+/*
+ * The weird & is necessary because sparse considers (void)(var) to be
+ * a direct dereference of percpu variable (var).
+ */
 #define put_cpu_var(var) do {				\
-	(void)(var);					\
+	(void)&(var);					\
 	preempt_enable();				\
 } while (0)
 
@@ -130,9 +134,9 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
  */
 #define per_cpu_ptr(ptr, cpu)	SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
 
-extern void *__alloc_reserved_percpu(size_t size, size_t align);
-extern void *__alloc_percpu(size_t size, size_t align);
-extern void free_percpu(void *__pdata);
+extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
+extern void __percpu *__alloc_percpu(size_t size, size_t align);
+extern void free_percpu(void __percpu *__pdata);
 
 #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void __init setup_per_cpu_areas(void);
@@ -142,7 +146,7 @@ extern void __init setup_per_cpu_areas(void);
 
 #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
 
-static inline void *__alloc_percpu(size_t size, size_t align)
+static inline void __percpu *__alloc_percpu(size_t size, size_t align)
 {
 	/*
 	 * Can't easily make larger alignment work with kmalloc.  WARN
@@ -153,7 +157,7 @@ static inline void *__alloc_percpu(size_t size, size_t align)
 	return kzalloc(size, GFP_KERNEL);
 }
 
-static inline void free_percpu(void *p)
+static inline void free_percpu(void __percpu *p)
 {
 	kfree(p);
 }
@@ -168,7 +172,7 @@ static inline void *pcpu_lpage_remapped(void *kaddr)
 #endif /* CONFIG_SMP */
 
 #define alloc_percpu(type)	\
-	(typeof(type) *)__alloc_percpu(sizeof(type), __alignof__(type))
+	(typeof(type) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type))
 
 /*
  * Optional methods for optimized non-lvalue per-cpu variable access.