mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2025-02-27 11:43:54 +07:00
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>
32 lines
642 B
C
32 lines
642 B
C
/*
|
|
* Per-cpu current frame pointer - the location of the last exception frame on
|
|
* the stack, stored in the per-cpu area.
|
|
*
|
|
* Jeremy Fitzhardinge <jeremy@goop.org>
|
|
*/
|
|
#ifndef _ASM_X86_IRQ_REGS_32_H
|
|
#define _ASM_X86_IRQ_REGS_32_H
|
|
|
|
#include <asm/percpu.h>
|
|
|
|
#define ARCH_HAS_OWN_IRQ_REGS
|
|
|
|
DECLARE_PER_CPU(struct pt_regs *, irq_regs);
|
|
|
|
static inline struct pt_regs *get_irq_regs(void)
|
|
{
|
|
return percpu_read(irq_regs);
|
|
}
|
|
|
|
static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
|
|
{
|
|
struct pt_regs *old_regs;
|
|
|
|
old_regs = get_irq_regs();
|
|
percpu_write(irq_regs, new_regs);
|
|
|
|
return old_regs;
|
|
}
|
|
|
|
#endif /* _ASM_X86_IRQ_REGS_32_H */
|