kernel-fxtec-pro1x/arch/x86/include/asm/percpu.h
Ingo Molnar 6dbde35308 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>
2009-01-16 14:20:31 +01:00

189 lines
5 KiB
C

#ifndef _ASM_X86_PERCPU_H
#define _ASM_X86_PERCPU_H
#ifdef CONFIG_X86_64
#define __percpu_seg gs
#define __percpu_mov_op movq
#else
#define __percpu_seg fs
#define __percpu_mov_op movl
#endif
#ifdef __ASSEMBLY__
/*
* PER_CPU finds an address of a per-cpu variable.
*
* Args:
* var - variable name
* reg - 32bit register
*
* The resulting address is stored in the "reg" argument.
*
* Example:
* PER_CPU(cpu_gdt_descr, %ebx)
*/
#ifdef CONFIG_SMP
#define PER_CPU(var, reg) \
__percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg; \
lea per_cpu__##var(reg), reg
#define PER_CPU_VAR(var) %__percpu_seg:per_cpu__##var
#else /* ! SMP */
#define PER_CPU(var, reg) \
__percpu_mov_op $per_cpu__##var, reg
#define PER_CPU_VAR(var) per_cpu__##var
#endif /* SMP */
#else /* ...!ASSEMBLY */
#include <linux/stringify.h>
#ifdef CONFIG_SMP
#define __percpu_seg_str "%%"__stringify(__percpu_seg)":"
#define __my_cpu_offset percpu_read(this_cpu_off)
#else
#define __percpu_seg_str
#endif
/* 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 percpu_to_op(op, var, val) \
do { \
typedef typeof(var) T__; \
if (0) { \
T__ tmp__; \
tmp__ = (val); \
} \
switch (sizeof(var)) { \
case 1: \
asm(op "b %1,"__percpu_seg_str"%0" \
: "+m" (var) \
: "ri" ((T__)val)); \
break; \
case 2: \
asm(op "w %1,"__percpu_seg_str"%0" \
: "+m" (var) \
: "ri" ((T__)val)); \
break; \
case 4: \
asm(op "l %1,"__percpu_seg_str"%0" \
: "+m" (var) \
: "ri" ((T__)val)); \
break; \
case 8: \
asm(op "q %1,"__percpu_seg_str"%0" \
: "+m" (var) \
: "r" ((T__)val)); \
break; \
default: __bad_percpu_size(); \
} \
} while (0)
#define percpu_from_op(op, var) \
({ \
typeof(var) ret__; \
switch (sizeof(var)) { \
case 1: \
asm(op "b "__percpu_seg_str"%1,%0" \
: "=r" (ret__) \
: "m" (var)); \
break; \
case 2: \
asm(op "w "__percpu_seg_str"%1,%0" \
: "=r" (ret__) \
: "m" (var)); \
break; \
case 4: \
asm(op "l "__percpu_seg_str"%1,%0" \
: "=r" (ret__) \
: "m" (var)); \
break; \
case 8: \
asm(op "q "__percpu_seg_str"%1,%0" \
: "=r" (ret__) \
: "m" (var)); \
break; \
default: __bad_percpu_size(); \
} \
ret__; \
})
#define percpu_read(var) percpu_from_op("mov", per_cpu__##var)
#define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val)
#define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val)
#define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val)
#define percpu_and(var, val) percpu_to_op("and", per_cpu__##var, val)
#define percpu_or(var, val) percpu_to_op("or", per_cpu__##var, val)
#define percpu_xor(var, val) percpu_to_op("xor", 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__; \
})
#include <asm-generic/percpu.h>
/* We can use this directly for local CPU (faster). */
DECLARE_PER_CPU(unsigned long, this_cpu_off);
#ifdef CONFIG_X86_64
extern void load_pda_offset(int cpu);
#else
static inline void load_pda_offset(int cpu) { }
#endif
#endif /* !__ASSEMBLY__ */
#ifdef CONFIG_SMP
/*
* Define the "EARLY_PER_CPU" macros. These are used for some per_cpu
* variables that are initialized and accessed before there are per_cpu
* areas allocated.
*/
#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \
DEFINE_PER_CPU(_type, _name) = _initvalue; \
__typeof__(_type) _name##_early_map[NR_CPUS] __initdata = \
{ [0 ... NR_CPUS-1] = _initvalue }; \
__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
EXPORT_PER_CPU_SYMBOL(_name)
#define DECLARE_EARLY_PER_CPU(_type, _name) \
DECLARE_PER_CPU(_type, _name); \
extern __typeof__(_type) *_name##_early_ptr; \
extern __typeof__(_type) _name##_early_map[]
#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 */
#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \
DEFINE_PER_CPU(_type, _name) = _initvalue
#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
EXPORT_PER_CPU_SYMBOL(_name)
#define DECLARE_EARLY_PER_CPU(_type, _name) \
DECLARE_PER_CPU(_type, _name)
#define early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
#define early_per_cpu_ptr(_name) NULL
/* no early_per_cpu_map() */
#endif /* !CONFIG_SMP */
#endif /* _ASM_X86_PERCPU_H */