x86/percpu: Clean up percpu_to_op()

The core percpu macros already have a switch on the data size, so the switch
in the x86 code is redundant and produces more dead code.

Also use appropriate types for the width of the instructions.  This avoids
errors when compiling with Clang.
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/20200720204925.3654302-3-ndesaulniers@google.com

arch/x86/include/asm/percpu.h

@@ -117,37 +117,17 @@ extern void __bad_percpu_size(void);
 #define __pcpu_reg_imm_4(x) "ri" (x)
 #define __pcpu_reg_imm_8(x) "re" (x)
 
-#define percpu_to_op(qual, op, var, val)		\
-do {							\
-	typedef typeof(var) pto_T__;			\
-	if (0) {					\
-		pto_T__ pto_tmp__;			\
-		pto_tmp__ = (val);			\
-		(void)pto_tmp__;			\
-	}						\
-	switch (sizeof(var)) {				\
-	case 1:						\
-		asm qual (op "b %1,"__percpu_arg(0)	\
-		    : "+m" (var)			\
-		    : "qi" ((pto_T__)(val)));		\
-		break;					\
-	case 2:						\
-		asm qual (op "w %1,"__percpu_arg(0)	\
-		    : "+m" (var)			\
-		    : "ri" ((pto_T__)(val)));		\
-		break;					\
-	case 4:						\
-		asm qual (op "l %1,"__percpu_arg(0)	\
-		    : "+m" (var)			\
-		    : "ri" ((pto_T__)(val)));		\
-		break;					\
-	case 8:						\
-		asm qual (op "q %1,"__percpu_arg(0)	\
-		    : "+m" (var)			\
-		    : "re" ((pto_T__)(val)));		\
-		break;					\
-	default: __bad_percpu_size();			\
-	}						\
+#define percpu_to_op(size, qual, op, _var, _val)			\
+do {									\
+	__pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val);	\
+	if (0) {		                                        \
+		typeof(_var) pto_tmp__;					\
+		pto_tmp__ = (_val);					\
+		(void)pto_tmp__;					\
+	}								\
+	asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var]))	\
+	    : [var] "+m" (_var)						\
+	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
 
 /*
@@ -425,18 +405,18 @@ do {									\
 #define raw_cpu_read_2(pcp)		percpu_from_op(, "mov", pcp)
 #define raw_cpu_read_4(pcp)		percpu_from_op(, "mov", pcp)
 
-#define raw_cpu_write_1(pcp, val)	percpu_to_op(, "mov", (pcp), val)
-#define raw_cpu_write_2(pcp, val)	percpu_to_op(, "mov", (pcp), val)
-#define raw_cpu_write_4(pcp, val)	percpu_to_op(, "mov", (pcp), val)
+#define raw_cpu_write_1(pcp, val)	percpu_to_op(1, , "mov", (pcp), val)
+#define raw_cpu_write_2(pcp, val)	percpu_to_op(2, , "mov", (pcp), val)
+#define raw_cpu_write_4(pcp, val)	percpu_to_op(4, , "mov", (pcp), val)
 #define raw_cpu_add_1(pcp, val)		percpu_add_op(, (pcp), val)
 #define raw_cpu_add_2(pcp, val)		percpu_add_op(, (pcp), val)
 #define raw_cpu_add_4(pcp, val)		percpu_add_op(, (pcp), val)
-#define raw_cpu_and_1(pcp, val)		percpu_to_op(, "and", (pcp), val)
-#define raw_cpu_and_2(pcp, val)		percpu_to_op(, "and", (pcp), val)
-#define raw_cpu_and_4(pcp, val)		percpu_to_op(, "and", (pcp), val)
-#define raw_cpu_or_1(pcp, val)		percpu_to_op(, "or", (pcp), val)
-#define raw_cpu_or_2(pcp, val)		percpu_to_op(, "or", (pcp), val)
-#define raw_cpu_or_4(pcp, val)		percpu_to_op(, "or", (pcp), val)
+#define raw_cpu_and_1(pcp, val)		percpu_to_op(1, , "and", (pcp), val)
+#define raw_cpu_and_2(pcp, val)		percpu_to_op(2, , "and", (pcp), val)
+#define raw_cpu_and_4(pcp, val)		percpu_to_op(4, , "and", (pcp), val)
+#define raw_cpu_or_1(pcp, val)		percpu_to_op(1, , "or", (pcp), val)
+#define raw_cpu_or_2(pcp, val)		percpu_to_op(2, , "or", (pcp), val)
+#define raw_cpu_or_4(pcp, val)		percpu_to_op(4, , "or", (pcp), val)
 
 /*
  * raw_cpu_xchg() can use a load-store since it is not required to be
@@ -456,18 +436,18 @@ do {									\
 #define this_cpu_read_1(pcp)		percpu_from_op(volatile, "mov", pcp)
 #define this_cpu_read_2(pcp)		percpu_from_op(volatile, "mov", pcp)
 #define this_cpu_read_4(pcp)		percpu_from_op(volatile, "mov", pcp)
-#define this_cpu_write_1(pcp, val)	percpu_to_op(volatile, "mov", (pcp), val)
-#define this_cpu_write_2(pcp, val)	percpu_to_op(volatile, "mov", (pcp), val)
-#define this_cpu_write_4(pcp, val)	percpu_to_op(volatile, "mov", (pcp), val)
+#define this_cpu_write_1(pcp, val)	percpu_to_op(1, volatile, "mov", (pcp), val)
+#define this_cpu_write_2(pcp, val)	percpu_to_op(2, volatile, "mov", (pcp), val)
+#define this_cpu_write_4(pcp, val)	percpu_to_op(4, volatile, "mov", (pcp), val)
 #define this_cpu_add_1(pcp, val)	percpu_add_op(volatile, (pcp), val)
 #define this_cpu_add_2(pcp, val)	percpu_add_op(volatile, (pcp), val)
 #define this_cpu_add_4(pcp, val)	percpu_add_op(volatile, (pcp), val)
-#define this_cpu_and_1(pcp, val)	percpu_to_op(volatile, "and", (pcp), val)
-#define this_cpu_and_2(pcp, val)	percpu_to_op(volatile, "and", (pcp), val)
-#define this_cpu_and_4(pcp, val)	percpu_to_op(volatile, "and", (pcp), val)
-#define this_cpu_or_1(pcp, val)		percpu_to_op(volatile, "or", (pcp), val)
-#define this_cpu_or_2(pcp, val)		percpu_to_op(volatile, "or", (pcp), val)
-#define this_cpu_or_4(pcp, val)		percpu_to_op(volatile, "or", (pcp), val)
+#define this_cpu_and_1(pcp, val)	percpu_to_op(1, volatile, "and", (pcp), val)
+#define this_cpu_and_2(pcp, val)	percpu_to_op(2, volatile, "and", (pcp), val)
+#define this_cpu_and_4(pcp, val)	percpu_to_op(4, volatile, "and", (pcp), val)
+#define this_cpu_or_1(pcp, val)		percpu_to_op(1, volatile, "or", (pcp), val)
+#define this_cpu_or_2(pcp, val)		percpu_to_op(2, volatile, "or", (pcp), val)
+#define this_cpu_or_4(pcp, val)		percpu_to_op(4, volatile, "or", (pcp), val)
 #define this_cpu_xchg_1(pcp, nval)	percpu_xchg_op(volatile, pcp, nval)
 #define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(volatile, pcp, nval)
 #define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(volatile, pcp, nval)
@@ -509,19 +489,19 @@ do {									\
  */
 #ifdef CONFIG_X86_64
 #define raw_cpu_read_8(pcp)			percpu_from_op(, "mov", pcp)
-#define raw_cpu_write_8(pcp, val)		percpu_to_op(, "mov", (pcp), val)
+#define raw_cpu_write_8(pcp, val)		percpu_to_op(8, , "mov", (pcp), val)
 #define raw_cpu_add_8(pcp, val)			percpu_add_op(, (pcp), val)
-#define raw_cpu_and_8(pcp, val)			percpu_to_op(, "and", (pcp), val)
-#define raw_cpu_or_8(pcp, val)			percpu_to_op(, "or", (pcp), val)
+#define raw_cpu_and_8(pcp, val)			percpu_to_op(8, , "and", (pcp), val)
+#define raw_cpu_or_8(pcp, val)			percpu_to_op(8, , "or", (pcp), val)
 #define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(, pcp, val)
 #define raw_cpu_xchg_8(pcp, nval)		raw_percpu_xchg_op(pcp, nval)
 #define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
 
 #define this_cpu_read_8(pcp)			percpu_from_op(volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val)		percpu_to_op(volatile, "mov", (pcp), val)
+#define this_cpu_write_8(pcp, val)		percpu_to_op(8, volatile, "mov", (pcp), val)
 #define this_cpu_add_8(pcp, val)		percpu_add_op(volatile, (pcp), val)
-#define this_cpu_and_8(pcp, val)		percpu_to_op(volatile, "and", (pcp), val)
-#define this_cpu_or_8(pcp, val)			percpu_to_op(volatile, "or", (pcp), val)
+#define this_cpu_and_8(pcp, val)		percpu_to_op(8, volatile, "and", (pcp), val)
+#define this_cpu_or_8(pcp, val)			percpu_to_op(8, volatile, "or", (pcp), val)
 #define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(volatile, pcp, val)
 #define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(volatile, pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)