6dbde35308
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>
39 lines
702 B
C
39 lines
702 B
C
#ifndef _ASM_X86_CURRENT_H
|
|
#define _ASM_X86_CURRENT_H
|
|
|
|
#ifdef CONFIG_X86_32
|
|
#include <linux/compiler.h>
|
|
#include <asm/percpu.h>
|
|
|
|
struct task_struct;
|
|
|
|
DECLARE_PER_CPU(struct task_struct *, current_task);
|
|
static __always_inline struct task_struct *get_current(void)
|
|
{
|
|
return percpu_read(current_task);
|
|
}
|
|
|
|
#else /* X86_32 */
|
|
|
|
#ifndef __ASSEMBLY__
|
|
#include <asm/pda.h>
|
|
|
|
struct task_struct;
|
|
|
|
static __always_inline struct task_struct *get_current(void)
|
|
{
|
|
return read_pda(pcurrent);
|
|
}
|
|
|
|
#else /* __ASSEMBLY__ */
|
|
|
|
#include <asm/asm-offsets.h>
|
|
#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
|
|
|
|
#endif /* __ASSEMBLY__ */
|
|
|
|
#endif /* X86_32 */
|
|
|
|
#define current get_current()
|
|
|
|
#endif /* _ASM_X86_CURRENT_H */
|