x86/percpu: Clean up percpu_stable_op()

Use __pcpu_size_call_return() to simplify this_cpu_read_stable().
Also remove __bad_percpu_size() which is now unused.
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Dennis Zhou <dennis@kernel.org>
Link: https://lkml.kernel.org/r/20200720204925.3654302-10-ndesaulniers@google.com

arch/x86/include/asm/percpu.h

@@ -85,7 +85,6 @@
 
 /* For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though). */
-extern void __bad_percpu_size(void);
 
 #define __pcpu_type_1 u8
 #define __pcpu_type_2 u16
@@ -167,33 +166,13 @@ do {									\
 	(typeof(_var))(unsigned long) pfo_val__;			\
 })
 
-#define percpu_stable_op(op, var)			\
-({							\
-	typeof(var) pfo_ret__;				\
-	switch (sizeof(var)) {				\
-	case 1:						\
-		asm(op "b "__percpu_arg(P1)",%0"	\
-		    : "=q" (pfo_ret__)			\
-		    : "p" (&(var)));			\
-		break;					\
-	case 2:						\
-		asm(op "w "__percpu_arg(P1)",%0"	\
-		    : "=r" (pfo_ret__)			\
-		    : "p" (&(var)));			\
-		break;					\
-	case 4:						\
-		asm(op "l "__percpu_arg(P1)",%0"	\
-		    : "=r" (pfo_ret__)			\
-		    : "p" (&(var)));			\
-		break;					\
-	case 8:						\
-		asm(op "q "__percpu_arg(P1)",%0"	\
-		    : "=r" (pfo_ret__)			\
-		    : "p" (&(var)));			\
-		break;					\
-	default: __bad_percpu_size();			\
-	}						\
-	pfo_ret__;					\
+#define percpu_stable_op(size, op, _var)				\
+({									\
+	__pcpu_type_##size pfo_val__;					\
+	asm(__pcpu_op2_##size(op, __percpu_arg(P[var]), "%[val]")	\
+	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
+	    : [var] "p" (&(_var)));					\
+	(typeof(_var))(unsigned long) pfo_val__;			\
 })
 
 /*
@@ -258,7 +237,11 @@ do {									\
  * per-thread variables implemented as per-cpu variables and thus
  * stable for the duration of the respective task.
  */
-#define this_cpu_read_stable(var)	percpu_stable_op("mov", var)
+#define this_cpu_read_stable_1(pcp)	percpu_stable_op(1, "mov", pcp)
+#define this_cpu_read_stable_2(pcp)	percpu_stable_op(2, "mov", pcp)
+#define this_cpu_read_stable_4(pcp)	percpu_stable_op(4, "mov", pcp)
+#define this_cpu_read_stable_8(pcp)	percpu_stable_op(8, "mov", pcp)
+#define this_cpu_read_stable(pcp)	__pcpu_size_call_return(this_cpu_read_stable_, pcp)
 
 #define raw_cpu_read_1(pcp)		percpu_from_op(1, , "mov", pcp)
 #define raw_cpu_read_2(pcp)		percpu_from_op(2, , "mov", pcp)