percpu: add optimized generic percpu accessors

It is an optimization and a cleanup, and adds the following new
generic percpu methods:

  percpu_read()
  percpu_write()
  percpu_add()
  percpu_sub()
  percpu_and()
  percpu_or()
  percpu_xor()

and implements support for them on x86. (other architectures will fall
back to a default implementation)

The advantage is that for example to read a local percpu variable,
instead of this sequence:

 return __get_cpu_var(var);

 ffffffff8102ca2b:	48 8b 14 fd 80 09 74 	mov    -0x7e8bf680(,%rdi,8),%rdx
 ffffffff8102ca32:	81
 ffffffff8102ca33:	48 c7 c0 d8 59 00 00 	mov    $0x59d8,%rax
 ffffffff8102ca3a:	48 8b 04 10          	mov    (%rax,%rdx,1),%rax

We can get a single instruction by using the optimized variants:

 return percpu_read(var);

 ffffffff8102ca3f:	65 48 8b 05 91 8f fd 	mov    %gs:0x7efd8f91(%rip),%rax

I also cleaned up the x86-specific APIs and made the x86 code use
these new generic percpu primitives.

tj: * fixed generic percpu_sub() definition as Roel Kluin pointed out
    * added percpu_and() for completeness's sake
    * made generic percpu ops atomic against preemption

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Tejun Heo <tj@kernel.org>
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 328b31a..03aa4b0 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -40,16 +40,11 @@
 
 #ifdef CONFIG_SMP
 #define __percpu_seg_str	"%%"__stringify(__percpu_seg)":"
-#define __my_cpu_offset		x86_read_percpu(this_cpu_off)
+#define __my_cpu_offset		percpu_read(this_cpu_off)
 #else
 #define __percpu_seg_str
 #endif
 
-#include <asm-generic/percpu.h>
-
-/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
-
 /* For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though). */
 extern void __bad_percpu_size(void);
@@ -115,11 +110,13 @@
 	ret__;						\
 })
 
-#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
-#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val)
-#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val)
-#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val)
-#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
+#define percpu_read(var)	percpu_from_op("mov", per_cpu__##var)
+#define percpu_write(var, val)	percpu_to_op("mov", per_cpu__##var, val)
+#define percpu_add(var, val)	percpu_to_op("add", per_cpu__##var, val)
+#define percpu_sub(var, val)	percpu_to_op("sub", per_cpu__##var, val)
+#define percpu_and(var, val)	percpu_to_op("and", per_cpu__##var, val)
+#define percpu_or(var, val)	percpu_to_op("or", per_cpu__##var, val)
+#define percpu_xor(var, val)	percpu_to_op("xor", per_cpu__##var, val)
 
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define x86_test_and_clear_bit_percpu(bit, var)				\
@@ -131,6 +128,11 @@
 	old__;								\
 })
 
+#include <asm-generic/percpu.h>
+
+/* We can use this directly for local CPU (faster). */
+DECLARE_PER_CPU(unsigned long, this_cpu_off);
+
 #ifdef CONFIG_X86_64
 extern void load_pda_offset(int cpu);
 #else