mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-15 15:15:47 +00:00
0d12cdd5f8
in scheduler-intense workloads native_read_tsc() overhead accounts for
20% of the system overhead:
659567 system_call 41222.9375
686796 schedule 435.7843
718382 __switch_to 665.1685
823875 switch_mm 4526.7857
1883122 native_read_tsc 55385.9412
9761990 total 2.8468
this is large part due to the rdtsc_barrier() that is done before
and after reading the TSC.
But sched_clock() is not a precise clock in the GTOD sense, using such
barriers is completely pointless. So remove the barriers and only use
them in vget_cycles().
This improves lat_ctx performance by about 5%.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
68 lines
1.3 KiB
C
68 lines
1.3 KiB
C
/*
|
|
* x86 TSC related functions
|
|
*/
|
|
#ifndef _ASM_X86_TSC_H
|
|
#define _ASM_X86_TSC_H
|
|
|
|
#include <asm/processor.h>
|
|
|
|
#define NS_SCALE 10 /* 2^10, carefully chosen */
|
|
#define US_SCALE 32 /* 2^32, arbitralrily chosen */
|
|
|
|
/*
|
|
* Standard way to access the cycle counter.
|
|
*/
|
|
typedef unsigned long long cycles_t;
|
|
|
|
extern unsigned int cpu_khz;
|
|
extern unsigned int tsc_khz;
|
|
|
|
extern void disable_TSC(void);
|
|
|
|
static inline cycles_t get_cycles(void)
|
|
{
|
|
unsigned long long ret = 0;
|
|
|
|
#ifndef CONFIG_X86_TSC
|
|
if (!cpu_has_tsc)
|
|
return 0;
|
|
#endif
|
|
rdtscll(ret);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static __always_inline cycles_t vget_cycles(void)
|
|
{
|
|
cycles_t cycles;
|
|
|
|
/*
|
|
* We only do VDSOs on TSC capable CPUs, so this shouldnt
|
|
* access boot_cpu_data (which is not VDSO-safe):
|
|
*/
|
|
#ifndef CONFIG_X86_TSC
|
|
if (!cpu_has_tsc)
|
|
return 0;
|
|
#endif
|
|
rdtsc_barrier();
|
|
cycles = (cycles_t)__native_read_tsc();
|
|
rdtsc_barrier();
|
|
|
|
return cycles;
|
|
}
|
|
|
|
extern void tsc_init(void);
|
|
extern void mark_tsc_unstable(char *reason);
|
|
extern int unsynchronized_tsc(void);
|
|
int check_tsc_unstable(void);
|
|
|
|
/*
|
|
* Boot-time check whether the TSCs are synchronized across
|
|
* all CPUs/cores:
|
|
*/
|
|
extern void check_tsc_sync_source(int cpu);
|
|
extern void check_tsc_sync_target(void);
|
|
|
|
extern int notsc_setup(char *);
|
|
|
|
#endif /* _ASM_X86_TSC_H */
|