Merge tag 'x86-percpu-2024-07-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 percpu updates from Ingo Molnar:

 - Enable the named address spaces based percpu accessors optimization
   on all GCC versions that contain this feature, detected through a
   build-time testcase.

   This effectively enables the feature on GCC 6, GCC 7 and GCC 8
   versions.

 - Fix operand constraint modifier in __raw_cpu_write()

 - Reorganize the per-CPU headers for better readability

 - Misc cleanups and fixes

* tag 'x86-percpu-2024-07-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/percpu: Enable named address spaces for all capable GCC versions
  x86/percpu: Clean up <asm/percpu.h> vertical alignment details
  x86/percpu: Clean up <asm/percpu.h> a bit
  x86/percpu: Move some percpu accessors around to reduce ifdeffery
  x86/percpu: Rename percpu_stable_op() to __raw_cpu_read_stable()
  x86/percpu: Fix operand constraint modifier in __raw_cpu_write()
  x86/percpu: Introduce the __raw_cpu_read_const() macro
  x86/percpu: Unify percpu read-write accessors
  x86/percpu: Move some percpu macros around for readability
  x86/percpu: Introduce the pcpu_binary_op() macro

arch/x86/Kconfig

@@ -2428,7 +2428,8 @@ source "kernel/livepatch/Kconfig"
 endmenu
 
 config CC_HAS_NAMED_AS
-	def_bool CC_IS_GCC && GCC_VERSION >= 90100
+	def_bool $(success,echo 'int __seg_fs fs; int __seg_gs gs;' | $(CC) -x c - -S -o /dev/null)
+	depends on CC_IS_GCC
 
 config CC_HAS_NAMED_AS_FIXED_SANITIZERS
 	def_bool CC_IS_GCC && GCC_VERSION >= 130300

arch/x86/include/asm/percpu.h

@@ -3,30 +3,30 @@
 #define _ASM_X86_PERCPU_H
 
 #ifdef CONFIG_X86_64
-#define __percpu_seg		gs
-#define __percpu_rel		(%rip)
+# define __percpu_seg		gs
+# define __percpu_rel		(%rip)
 #else
-#define __percpu_seg		fs
-#define __percpu_rel
+# define __percpu_seg		fs
+# define __percpu_rel
 #endif
 
 #ifdef __ASSEMBLY__
 
 #ifdef CONFIG_SMP
-#define __percpu		%__percpu_seg:
+# define __percpu		%__percpu_seg:
 #else
-#define __percpu
+# define __percpu
 #endif
 
 #define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
 #ifdef CONFIG_X86_64_SMP
-#define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
+# define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
 #else
-#define INIT_PER_CPU_VAR(var)  var
+# define INIT_PER_CPU_VAR(var)  var
 #endif
 
-#else /* ...!ASSEMBLY */
+#else /* !__ASSEMBLY__: */
 
 #include <linux/build_bug.h>
 #include <linux/stringify.h>
@@ -37,19 +37,19 @@
 #ifdef CONFIG_CC_HAS_NAMED_AS
 
 #ifdef __CHECKER__
-#define __seg_gs		__attribute__((address_space(__seg_gs)))
-#define __seg_fs		__attribute__((address_space(__seg_fs)))
+# define __seg_gs		__attribute__((address_space(__seg_gs)))
+# define __seg_fs		__attribute__((address_space(__seg_fs)))
 #endif
 
 #ifdef CONFIG_X86_64
-#define __percpu_seg_override	__seg_gs
+# define __percpu_seg_override	__seg_gs
 #else
-#define __percpu_seg_override	__seg_fs
+# define __percpu_seg_override	__seg_fs
 #endif
 
 #define __percpu_prefix		""
 
-#else /* CONFIG_CC_HAS_NAMED_AS */
+#else /* !CONFIG_CC_HAS_NAMED_AS: */
 
 #define __percpu_seg_override
 #define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
@@ -71,6 +71,7 @@
 #define arch_raw_cpu_ptr(_ptr)						\
 ({									\
 	unsigned long tcp_ptr__ = raw_cpu_read_long(this_cpu_off);	\
+									\
 	tcp_ptr__ += (__force unsigned long)(_ptr);			\
 	(typeof(*(_ptr)) __kernel __force *)tcp_ptr__;			\
 })
@@ -80,7 +81,8 @@
 
 #define PER_CPU_VAR(var)	%__percpu_seg:(var)__percpu_rel
 
-#else /* CONFIG_SMP */
+#else /* !CONFIG_SMP: */
+
 #define __percpu_seg_override
 #define __percpu_prefix		""
 #define __force_percpu_prefix	""
@@ -96,7 +98,7 @@
 #define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
 
 /*
- * Initialized pointers to per-cpu variables needed for the boot
+ * Initialized pointers to per-CPU variables needed for the boot
  * processor need to use these macros to get the proper address
  * offset from __per_cpu_load on SMP.
  *
@@ -106,13 +108,15 @@
        extern typeof(var) init_per_cpu_var(var)
 
 #ifdef CONFIG_X86_64_SMP
-#define init_per_cpu_var(var)  init_per_cpu__##var
+# define init_per_cpu_var(var)  init_per_cpu__##var
 #else
-#define init_per_cpu_var(var)  var
+# define init_per_cpu_var(var)  var
 #endif
 
-/* For arch-specific code, we can use direct single-insn ops (they
- * don't give an lvalue though). */
+/*
+ * For arch-specific code, we can use direct single-insn ops (they
+ * don't give an lvalue though).
+ */
 
 #define __pcpu_type_1		u8
 #define __pcpu_type_2		u16
@@ -144,27 +148,88 @@
 #define __pcpu_reg_imm_4(x)	"ri" (x)
 #define __pcpu_reg_imm_8(x)	"re" (x)
 
-#define percpu_to_op(size, qual, op, _var, _val)			\
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+
+#define __raw_cpu_read(size, qual, pcp)					\
+({									\
+	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp));		\
+})
+
+#define __raw_cpu_write(size, qual, pcp, val)				\
+do {									\
+	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val);	\
+} while (0)
+
+#define __raw_cpu_read_const(pcp)	__raw_cpu_read(, , pcp)
+
+#else /* !CONFIG_USE_X86_SEG_SUPPORT: */
+
+#define __raw_cpu_read(size, qual, _var)				\
+({									\
+	__pcpu_type_##size pfo_val__;					\
+									\
+	asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), "%[val]") \
+	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
+	    : [var] "m" (__my_cpu_var(_var)));				\
+									\
+	(typeof(_var))(unsigned long) pfo_val__;			\
+})
+
+#define __raw_cpu_write(size, qual, _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" (__my_cpu_var(_var))				\
+	asm qual(__pcpu_op2_##size("mov", "%[val]", __percpu_arg([var])) \
+	    : [var] "=m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
 
+/*
+ * The generic per-CPU infrastrucutre is not suitable for
+ * reading const-qualified variables.
+ */
+#define __raw_cpu_read_const(pcp)	({ BUILD_BUG(); (typeof(pcp))0; })
+
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
+#define __raw_cpu_read_stable(size, _var)				\
+({									\
+	__pcpu_type_##size pfo_val__;					\
+									\
+	asm(__pcpu_op2_##size("mov", __force_percpu_arg(a[var]), "%[val]") \
+	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
+	    : [var] "i" (&(_var)));					\
+									\
+	(typeof(_var))(unsigned long) pfo_val__;			\
+})
+
 #define percpu_unary_op(size, qual, op, _var)				\
 ({									\
 	asm qual (__pcpu_op1_##size(op, __percpu_arg([var]))		\
 	    : [var] "+m" (__my_cpu_var(_var)));				\
 })
 
+#define percpu_binary_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" (__my_cpu_var(_var))				\
+	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
+} while (0)
+
 /*
- * Generate a percpu add to memory instruction and optimize code
+ * Generate a per-CPU add to memory instruction and optimize code
  * if one is added or subtracted.
  */
 #define percpu_add_op(size, qual, var, val)				\
@@ -172,6 +237,7 @@ do {									\
 	const int pao_ID__ = (__builtin_constant_p(val) &&		\
 			      ((val) == 1 || (val) == -1)) ?		\
 				(int)(val) : 0;				\
+									\
 	if (0) {							\
 		typeof(var) pao_tmp__;					\
 		pao_tmp__ = (val);					\
@@ -182,33 +248,16 @@ do {									\
 	else if (pao_ID__ == -1)					\
 		percpu_unary_op(size, qual, "dec", var);		\
 	else								\
-		percpu_to_op(size, qual, "add", var, val);		\
+		percpu_binary_op(size, qual, "add", var, val);		\
 } while (0)
 
-#define percpu_from_op(size, qual, op, _var)				\
-({									\
-	__pcpu_type_##size pfo_val__;					\
-	asm qual (__pcpu_op2_##size(op, __percpu_arg([var]), "%[val]")	\
-	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
-	    : [var] "m" (__my_cpu_var(_var)));				\
-	(typeof(_var))(unsigned long) pfo_val__;			\
-})
-
-#define percpu_stable_op(size, op, _var)				\
-({									\
-	__pcpu_type_##size pfo_val__;					\
-	asm(__pcpu_op2_##size(op, __force_percpu_arg(a[var]), "%[val]")	\
-	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
-	    : [var] "i" (&(_var)));					\
-	(typeof(_var))(unsigned long) pfo_val__;			\
-})
-
 /*
  * Add return operation
  */
 #define percpu_add_return_op(size, qual, _var, _val)			\
 ({									\
 	__pcpu_type_##size paro_tmp__ = __pcpu_cast_##size(_val);	\
+									\
 	asm qual (__pcpu_op2_##size("xadd", "%[tmp]",			\
 				     __percpu_arg([var]))		\
 		  : [tmp] __pcpu_reg_##size("+", paro_tmp__),		\
@@ -224,36 +273,42 @@ do {									\
 #define raw_percpu_xchg_op(_var, _nval)					\
 ({									\
 	typeof(_var) pxo_old__ = raw_cpu_read(_var);			\
+									\
 	raw_cpu_write(_var, _nval);					\
+									\
 	pxo_old__;							\
 })
 
 /*
- * this_cpu_xchg() is implemented using cmpxchg without a lock prefix.
- * xchg is expensive due to the implied lock prefix. The processor
- * cannot prefetch cachelines if xchg is used.
+ * this_cpu_xchg() is implemented using CMPXCHG without a LOCK prefix.
+ * XCHG is expensive due to the implied LOCK prefix. The processor
+ * cannot prefetch cachelines if XCHG is used.
  */
 #define this_percpu_xchg_op(_var, _nval)				\
 ({									\
 	typeof(_var) pxo_old__ = this_cpu_read(_var);			\
+									\
 	do { } while (!this_cpu_try_cmpxchg(_var, &pxo_old__, _nval));	\
+									\
 	pxo_old__;							\
 })
 
 /*
- * cmpxchg has no such implied lock semantics as a result it is much
- * more efficient for cpu local operations.
+ * CMPXCHG has no such implied lock semantics as a result it is much
+ * more efficient for CPU-local operations.
  */
 #define percpu_cmpxchg_op(size, qual, _var, _oval, _nval)		\
 ({									\
 	__pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval);	\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
+									\
 	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
 				    __percpu_arg([var]))		\
 		  : [oval] "+a" (pco_old__),				\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
 		  : "memory");						\
+									\
 	(typeof(_var))(unsigned long) pco_old__;			\
 })
 
@@ -263,6 +318,7 @@ do {									\
 	__pcpu_type_##size *pco_oval__ = (__pcpu_type_##size *)(_ovalp); \
 	__pcpu_type_##size pco_old__ = *pco_oval__;			\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
+									\
 	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
 				    __percpu_arg([var]))		\
 		  CC_SET(z)						\
@@ -273,10 +329,12 @@ do {									\
 		  : "memory");						\
 	if (unlikely(!success))						\
 		*pco_oval__ = pco_old__;				\
+									\
 	likely(success);						\
 })
 
 #if defined(CONFIG_X86_32) && !defined(CONFIG_UML)
+
 #define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval)		\
 ({									\
 	union {								\
@@ -332,12 +390,14 @@ do {									\
 		  : "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
+									\
 	likely(success);						\
 })
 
 #define raw_cpu_try_cmpxchg64(pcp, ovalp, nval)		percpu_try_cmpxchg64_op(8,         , pcp, ovalp, nval)
 #define this_cpu_try_cmpxchg64(pcp, ovalp, nval)	percpu_try_cmpxchg64_op(8, volatile, pcp, ovalp, nval)
-#endif
+
+#endif /* defined(CONFIG_X86_32) && !defined(CONFIG_UML) */
 
 #ifdef CONFIG_X86_64
 #define raw_cpu_cmpxchg64(pcp, oval, nval)		percpu_cmpxchg_op(8,         , pcp, oval, nval);
@@ -406,98 +466,36 @@ do {									\
 
 #define raw_cpu_try_cmpxchg128(pcp, ovalp, nval)	percpu_try_cmpxchg128_op(16,         , pcp, ovalp, nval)
 #define this_cpu_try_cmpxchg128(pcp, ovalp, nval)	percpu_try_cmpxchg128_op(16, volatile, pcp, ovalp, nval)
-#endif
-
-/*
- * this_cpu_read() makes gcc load the percpu variable every time it is
- * accessed while this_cpu_read_stable() allows the value to be cached.
- * this_cpu_read_stable() is more efficient and can be used if its value
- * is guaranteed to be valid across cpus.  The current users include
- * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
- * actually per-thread variables implemented as per-CPU variables and
- * thus stable for the duration of the respective task.
- */
-#define this_cpu_read_stable(pcp)	__pcpu_size_call_return(this_cpu_read_stable_, pcp)
-
-#ifdef CONFIG_USE_X86_SEG_SUPPORT
-
-#define __raw_cpu_read(qual, pcp)					\
-({									\
-	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp));		\
-})
-
-#define __raw_cpu_write(qual, pcp, val)					\
-do {									\
-	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val);	\
-} while (0)
 
-#define raw_cpu_read_1(pcp)		__raw_cpu_read(, pcp)
-#define raw_cpu_read_2(pcp)		__raw_cpu_read(, pcp)
-#define raw_cpu_read_4(pcp)		__raw_cpu_read(, pcp)
-#define raw_cpu_write_1(pcp, val)	__raw_cpu_write(, pcp, val)
-#define raw_cpu_write_2(pcp, val)	__raw_cpu_write(, pcp, val)
-#define raw_cpu_write_4(pcp, val)	__raw_cpu_write(, pcp, val)
+#endif /* CONFIG_X86_64 */
 
-#define this_cpu_read_1(pcp)		__raw_cpu_read(volatile, pcp)
-#define this_cpu_read_2(pcp)		__raw_cpu_read(volatile, pcp)
-#define this_cpu_read_4(pcp)		__raw_cpu_read(volatile, pcp)
-#define this_cpu_write_1(pcp, val)	__raw_cpu_write(volatile, pcp, val)
-#define this_cpu_write_2(pcp, val)	__raw_cpu_write(volatile, pcp, val)
-#define this_cpu_write_4(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#define raw_cpu_read_1(pcp)				__raw_cpu_read(1, , pcp)
+#define raw_cpu_read_2(pcp)				__raw_cpu_read(2, , pcp)
+#define raw_cpu_read_4(pcp)				__raw_cpu_read(4, , pcp)
+#define raw_cpu_write_1(pcp, val)			__raw_cpu_write(1, , pcp, val)
+#define raw_cpu_write_2(pcp, val)			__raw_cpu_write(2, , pcp, val)
+#define raw_cpu_write_4(pcp, val)			__raw_cpu_write(4, , pcp, val)
 
-#ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp)		__raw_cpu_read(, pcp)
-#define raw_cpu_write_8(pcp, val)	__raw_cpu_write(, pcp, val)
-
-#define this_cpu_read_8(pcp)		__raw_cpu_read(volatile, pcp)
-#define this_cpu_write_8(pcp, val)	__raw_cpu_write(volatile, pcp, val)
-#endif
-
-#define this_cpu_read_const(pcp)	__raw_cpu_read(, pcp)
-#else /* CONFIG_USE_X86_SEG_SUPPORT */
-
-#define raw_cpu_read_1(pcp)		percpu_from_op(1, , "mov", pcp)
-#define raw_cpu_read_2(pcp)		percpu_from_op(2, , "mov", pcp)
-#define raw_cpu_read_4(pcp)		percpu_from_op(4, , "mov", pcp)
-#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 this_cpu_read_1(pcp)				__raw_cpu_read(1, volatile, pcp)
+#define this_cpu_read_2(pcp)				__raw_cpu_read(2, volatile, pcp)
+#define this_cpu_read_4(pcp)				__raw_cpu_read(4, volatile, pcp)
+#define this_cpu_write_1(pcp, val)			__raw_cpu_write(1, volatile, pcp, val)
+#define this_cpu_write_2(pcp, val)			__raw_cpu_write(2, volatile, pcp, val)
+#define this_cpu_write_4(pcp, val)			__raw_cpu_write(4, volatile, pcp, val)
 
-#define this_cpu_read_1(pcp)		percpu_from_op(1, volatile, "mov", pcp)
-#define this_cpu_read_2(pcp)		percpu_from_op(2, volatile, "mov", pcp)
-#define this_cpu_read_4(pcp)		percpu_from_op(4, volatile, "mov", pcp)
-#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)
-
-#ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp)		percpu_from_op(8, , "mov", pcp)
-#define raw_cpu_write_8(pcp, val)	percpu_to_op(8, , "mov", (pcp), val)
-
-#define this_cpu_read_8(pcp)		percpu_from_op(8, volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val)	percpu_to_op(8, volatile, "mov", (pcp), val)
-#endif
-
-/*
- * The generic per-cpu infrastrucutre is not suitable for
- * reading const-qualified variables.
- */
-#define this_cpu_read_const(pcp)	({ BUILD_BUG(); (typeof(pcp))0; })
-#endif /* CONFIG_USE_X86_SEG_SUPPORT */
-
-#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_1(pcp)			__raw_cpu_read_stable(1, pcp)
+#define this_cpu_read_stable_2(pcp)			__raw_cpu_read_stable(2, pcp)
+#define this_cpu_read_stable_4(pcp)			__raw_cpu_read_stable(4, pcp)
 
 #define raw_cpu_add_1(pcp, val)				percpu_add_op(1, , (pcp), val)
 #define raw_cpu_add_2(pcp, val)				percpu_add_op(2, , (pcp), val)
 #define raw_cpu_add_4(pcp, val)				percpu_add_op(4, , (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)
+#define raw_cpu_and_1(pcp, val)				percpu_binary_op(1, , "and", (pcp), val)
+#define raw_cpu_and_2(pcp, val)				percpu_binary_op(2, , "and", (pcp), val)
+#define raw_cpu_and_4(pcp, val)				percpu_binary_op(4, , "and", (pcp), val)
+#define raw_cpu_or_1(pcp, val)				percpu_binary_op(1, , "or", (pcp), val)
+#define raw_cpu_or_2(pcp, val)				percpu_binary_op(2, , "or", (pcp), val)
+#define raw_cpu_or_4(pcp, val)				percpu_binary_op(4, , "or", (pcp), val)
 #define raw_cpu_xchg_1(pcp, val)			raw_percpu_xchg_op(pcp, val)
 #define raw_cpu_xchg_2(pcp, val)			raw_percpu_xchg_op(pcp, val)
 #define raw_cpu_xchg_4(pcp, val)			raw_percpu_xchg_op(pcp, val)
@@ -505,12 +503,12 @@ do {									\
 #define this_cpu_add_1(pcp, val)			percpu_add_op(1, volatile, (pcp), val)
 #define this_cpu_add_2(pcp, val)			percpu_add_op(2, volatile, (pcp), val)
 #define this_cpu_add_4(pcp, val)			percpu_add_op(4, volatile, (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_and_1(pcp, val)			percpu_binary_op(1, volatile, "and", (pcp), val)
+#define this_cpu_and_2(pcp, val)			percpu_binary_op(2, volatile, "and", (pcp), val)
+#define this_cpu_and_4(pcp, val)			percpu_binary_op(4, volatile, "and", (pcp), val)
+#define this_cpu_or_1(pcp, val)				percpu_binary_op(1, volatile, "or", (pcp), val)
+#define this_cpu_or_2(pcp, val)				percpu_binary_op(2, volatile, "or", (pcp), val)
+#define this_cpu_or_4(pcp, val)				percpu_binary_op(4, volatile, "or", (pcp), val)
 #define this_cpu_xchg_1(pcp, nval)			this_percpu_xchg_op(pcp, nval)
 #define this_cpu_xchg_2(pcp, nval)			this_percpu_xchg_op(pcp, nval)
 #define this_cpu_xchg_4(pcp, nval)			this_percpu_xchg_op(pcp, nval)
@@ -536,40 +534,64 @@ do {									\
 #define this_cpu_try_cmpxchg_4(pcp, ovalp, nval)	percpu_try_cmpxchg_op(4, volatile, pcp, ovalp, nval)
 
 /*
- * Per cpu atomic 64 bit operations are only available under 64 bit.
- * 32 bit must fall back to generic operations.
+ * Per-CPU atomic 64-bit operations are only available under 64-bit kernels.
+ * 32-bit kernels must fall back to generic operations.
  */
 #ifdef CONFIG_X86_64
-#define this_cpu_read_stable_8(pcp)	percpu_stable_op(8, "mov", pcp)
+
+#define raw_cpu_read_8(pcp)				__raw_cpu_read(8, , pcp)
+#define raw_cpu_write_8(pcp, val)			__raw_cpu_write(8, , pcp, val)
+
+#define this_cpu_read_8(pcp)				__raw_cpu_read(8, volatile, pcp)
+#define this_cpu_write_8(pcp, val)			__raw_cpu_write(8, volatile, pcp, val)
+
+#define this_cpu_read_stable_8(pcp)			__raw_cpu_read_stable(8, pcp)
 
 #define raw_cpu_add_8(pcp, val)				percpu_add_op(8, , (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_and_8(pcp, val)				percpu_binary_op(8, , "and", (pcp), val)
+#define raw_cpu_or_8(pcp, val)				percpu_binary_op(8, , "or", (pcp), val)
 #define raw_cpu_add_return_8(pcp, val)			percpu_add_return_op(8, , 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(8, , pcp, oval, nval)
 #define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval)		percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
 
 #define this_cpu_add_8(pcp, val)			percpu_add_op(8, volatile, (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_and_8(pcp, val)			percpu_binary_op(8, volatile, "and", (pcp), val)
+#define this_cpu_or_8(pcp, val)				percpu_binary_op(8, volatile, "or", (pcp), val)
 #define this_cpu_add_return_8(pcp, val)			percpu_add_return_op(8, volatile, pcp, val)
 #define this_cpu_xchg_8(pcp, nval)			this_percpu_xchg_op(pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)		percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
 #define this_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
 
 #define raw_cpu_read_long(pcp)				raw_cpu_read_8(pcp)
-#else
-/* There is no generic 64 bit read stable operation for 32 bit targets. */
+
+#else /* !CONFIG_X86_64: */
+
+/* There is no generic 64-bit read stable operation for 32-bit targets. */
 #define this_cpu_read_stable_8(pcp)			({ BUILD_BUG(); (typeof(pcp))0; })
 
 #define raw_cpu_read_long(pcp)				raw_cpu_read_4(pcp)
-#endif
+
+#endif /* CONFIG_X86_64 */
+
+#define this_cpu_read_const(pcp)			__raw_cpu_read_const(pcp)
+
+/*
+ * this_cpu_read() makes the compiler load the per-CPU variable every time
+ * it is accessed while this_cpu_read_stable() allows the value to be cached.
+ * this_cpu_read_stable() is more efficient and can be used if its value
+ * is guaranteed to be valid across CPUs.  The current users include
+ * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
+ * actually per-thread variables implemented as per-CPU variables and
+ * thus stable for the duration of the respective task.
+ */
+#define this_cpu_read_stable(pcp)			__pcpu_size_call_return(this_cpu_read_stable_, pcp)
 
 #define x86_this_cpu_constant_test_bit(_nr, _var)			\
 ({									\
 	unsigned long __percpu *addr__ =				\
 		(unsigned long __percpu *)&(_var) + ((_nr) / BITS_PER_LONG); \
+									\
 	!!((1UL << ((_nr) % BITS_PER_LONG)) & raw_cpu_read(*addr__));	\
 })
 
@@ -633,12 +655,13 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
 
 #define	early_per_cpu_ptr(_name)			(_name##_early_ptr)
 #define	early_per_cpu_map(_name, _idx)			(_name##_early_map[_idx])
+
 #define	early_per_cpu(_name, _cpu)					\
 	*(early_per_cpu_ptr(_name) ?					\
 		&early_per_cpu_ptr(_name)[_cpu] :			\
 		&per_cpu(_name, _cpu))
 
-#else	/* !CONFIG_SMP */
+#else /* !CONFIG_SMP: */
 #define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)			\
 	DEFINE_PER_CPU(_type, _name) = _initvalue