mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-05 01:36:47 +07:00
beed33a816
This likely profiling is pretty fun. I found a few possible problems in sched.c. This patch may be not measurable, but when I did measure long ago, nooping (un)likely cost a couple of % on scheduler heavy benchmarks, so it all adds up. Tweak some branch hints: - the 2nd 64 bits in the bitmask is likely to be populated, because it contains the first 28 bits (nearly 3/4) of the normal priorities. (ratio of 669669:691 ~= 1000:1). - it isn't unlikely that context switching switches to another process. it might be very rapidly switching to and from the idle process (ratio of 475815:419004 and 471330:423544). Let the branch predictor decide. - preempt_enable seems to be very often called in a nested preempt_disable or with interrupts disabled (ratio of 3567760:87965 ~= 40:1) Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Daniel Walker <dwalker@mvista.com> Cc: Hua Zhong <hzhong@gmail.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
37 lines
897 B
C
37 lines
897 B
C
#ifndef _ASM_GENERIC_BITOPS_SCHED_H_
|
|
#define _ASM_GENERIC_BITOPS_SCHED_H_
|
|
|
|
#include <linux/compiler.h> /* unlikely() */
|
|
#include <asm/types.h>
|
|
|
|
/*
|
|
* Every architecture must define this function. It's the fastest
|
|
* way of searching a 140-bit bitmap where the first 100 bits are
|
|
* unlikely to be set. It's guaranteed that at least one of the 140
|
|
* bits is cleared.
|
|
*/
|
|
static inline int sched_find_first_bit(const unsigned long *b)
|
|
{
|
|
#if BITS_PER_LONG == 64
|
|
if (unlikely(b[0]))
|
|
return __ffs(b[0]);
|
|
if (likely(b[1]))
|
|
return __ffs(b[1]) + 64;
|
|
return __ffs(b[2]) + 128;
|
|
#elif BITS_PER_LONG == 32
|
|
if (unlikely(b[0]))
|
|
return __ffs(b[0]);
|
|
if (unlikely(b[1]))
|
|
return __ffs(b[1]) + 32;
|
|
if (unlikely(b[2]))
|
|
return __ffs(b[2]) + 64;
|
|
if (b[3])
|
|
return __ffs(b[3]) + 96;
|
|
return __ffs(b[4]) + 128;
|
|
#else
|
|
#error BITS_PER_LONG not defined
|
|
#endif
|
|
}
|
|
|
|
#endif /* _ASM_GENERIC_BITOPS_SCHED_H_ */
|