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>

1 files changed, 52 insertions, 0 deletions

diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index b0e63c672ebd..00f45ff081a6 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -80,4 +80,56 @@ extern void setup_per_cpu_areas(void);
 #define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \
                                         __typeof__(type) per_cpu_var(name)
 
+/*
+ * Optional methods for optimized non-lvalue per-cpu variable access.
+ *
+ * @var can be a percpu variable or a field of it and its size should
+ * equal char, int or long.  percpu_read() evaluates to a lvalue and
+ * all others to void.
+ *
+ * These operations are guaranteed to be atomic w.r.t. preemption.
+ * The generic versions use plain get/put_cpu_var().  Archs are
+ * encouraged to implement single-instruction alternatives which don't
+ * require preemption protection.
+ */
+#ifndef percpu_read
+# define percpu_read(var)                                               \
+  ({                                                                    \
+        typeof(per_cpu_var(var)) __tmp_var__;                           \
+        __tmp_var__ = get_cpu_var(var);                                 \
+        put_cpu_var(var);                                               \
+        __tmp_var__;                                                    \
+  })
+#endif
+
+#define __percpu_generic_to_op(var, val, op)                            \
+do {                                                                    \
+        get_cpu_var(var) op val;                                        \
+        put_cpu_var(var);                                               \
+} while (0)
+
+#ifndef percpu_write
+# define percpu_write(var, val)         __percpu_generic_to_op(var, (val), =)
+#endif
+
+#ifndef percpu_add
+# define percpu_add(var, val)           __percpu_generic_to_op(var, (val), +=)
+#endif
+
+#ifndef percpu_sub
+# define percpu_sub(var, val)           __percpu_generic_to_op(var, (val), -=)
+#endif
+
+#ifndef percpu_and
+# define percpu_and(var, val)           __percpu_generic_to_op(var, (val), &=)
+#endif
+
+#ifndef percpu_or
+# define percpu_or(var, val)            __percpu_generic_to_op(var, (val), |=)
+#endif
+
+#ifndef percpu_xor
+# define percpu_xor(var, val)           __percpu_generic_to_op(var, (val), ^=)
+#endif
+
 #endif /* _ASM_GENERIC_PERCPU_H_ */