x86: convert pda ops to wrappers around x86 percpu accessors

pda is now a percpu variable and there's no reason it can't use plain
x86 percpu accessors.  Add x86_test_and_clear_bit_percpu() and replace
pda op implementations with wrappers around x86 percpu accessors.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

arch/x86/include/asm/pda.h

@@ -45,91 +45,15 @@ extern void pda_init(int);
 
 #define cpu_pda(cpu)		(&per_cpu(__pda, cpu))
 
-/*
- * There is no fast way to get the base address of the PDA, all the accesses
- * have to mention %fs/%gs.  So it needs to be done this Torvaldian way.
- */
-extern void __bad_pda_field(void) __attribute__((noreturn));
-
-/*
- * proxy_pda doesn't actually exist, but tell gcc it is accessed for
- * all PDA accesses so it gets read/write dependencies right.
- */
-extern struct x8664_pda _proxy_pda;
-
-#define pda_offset(field) offsetof(struct x8664_pda, field)
-
-#define pda_to_op(op, field, val)					\
-do {									\
-	typedef typeof(_proxy_pda.field) T__;				\
-	if (0) { T__ tmp__; tmp__ = (val); }	/* type checking */	\
-	switch (sizeof(_proxy_pda.field)) {				\
-	case 2:								\
-		asm(op "w %1,%%gs:%c2" :				\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i"(pda_offset(field)));				\
-		break;							\
-	case 4:								\
-		asm(op "l %1,%%gs:%c2" :				\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i" (pda_offset(field)));				\
-		break;							\
-	case 8:								\
-		asm(op "q %1,%%gs:%c2":					\
-		    "+m" (_proxy_pda.field) :				\
-		    "r" ((T__)val),					\
-		    "i"(pda_offset(field)));				\
-		break;							\
-	default:							\
-		__bad_pda_field();					\
-	}								\
-} while (0)
-
-#define pda_from_op(op, field)			\
-({						\
-	typeof(_proxy_pda.field) ret__;		\
-	switch (sizeof(_proxy_pda.field)) {	\
-	case 2:					\
-		asm(op "w %%gs:%c1,%0" :	\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	case 4:					\
-		asm(op "l %%gs:%c1,%0":		\
-		    "=r" (ret__):		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	case 8:					\
-		asm(op "q %%gs:%c1,%0":		\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	default:				\
-		__bad_pda_field();		\
-	}					\
-	ret__;					\
-})
-
-#define read_pda(field)		pda_from_op("mov", field)
-#define write_pda(field, val)	pda_to_op("mov", field, val)
-#define add_pda(field, val)	pda_to_op("add", field, val)
-#define sub_pda(field, val)	pda_to_op("sub", field, val)
-#define or_pda(field, val)	pda_to_op("or", field, val)
+#define read_pda(field)		x86_read_percpu(__pda.field)
+#define write_pda(field, val)	x86_write_percpu(__pda.field, val)
+#define add_pda(field, val)	x86_add_percpu(__pda.field, val)
+#define sub_pda(field, val)	x86_sub_percpu(__pda.field, val)
+#define or_pda(field, val)	x86_or_percpu(__pda.field, val)
 
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define test_and_clear_bit_pda(bit, field)				\
-({									\
-	int old__;							\
-	asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"			\
-		     : "=r" (old__), "+m" (_proxy_pda.field)		\
-		     : "dIr" (bit), "i" (pda_offset(field)) : "memory");\
-	old__;								\
-})
+	x86_test_and_clear_bit_percpu(bit, __pda.field)
 
 #endif
 

arch/x86/include/asm/percpu.h

@@ -121,6 +121,16 @@ do {							\
 #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)
 
+/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+#define x86_test_and_clear_bit_percpu(bit, var)				\
+({									\
+	int old__;							\
+	asm volatile("btr %1,"__percpu_seg_str"%c2\n\tsbbl %0,%0"	\
+		     : "=r" (old__)					\
+		     : "dIr" (bit), "i" (&per_cpu__##var) : "memory");	\
+	old__;								\
+})
+
 #ifdef CONFIG_X86_64
 extern void load_pda_offset(int cpu);
 #else

arch/x86/kernel/vmlinux_64.lds.S

@@ -14,7 +14,6 @@ OUTPUT_FORMAT("elf64-x86-64", "elf64-x86-64", "elf64-x86-64")
 OUTPUT_ARCH(i386:x86-64)
 ENTRY(phys_startup_64)
 jiffies_64 = jiffies;
-_proxy_pda = 1;
 PHDRS {
 	text PT_LOAD FLAGS(5);	/* R_E */
 	data PT_LOAD FLAGS(7);	/* RWE */

arch/x86/kernel/x8664_ksyms_64.c

@@ -58,5 +58,3 @@ EXPORT_SYMBOL(__memcpy);
 EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(init_level4_pgt);
 EXPORT_SYMBOL(load_gs_index);
-
-EXPORT_SYMBOL(_proxy_pda);