mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-11 21:38:32 +08:00
ea7145477a
Put x86 entry code into a separate link section: .entry.text.
Separating the entry text section seems to have performance
benefits - caused by more efficient instruction cache usage.
Running hackbench with perf stat --repeat showed that the change
compresses the icache footprint. The icache load miss rate went
down by about 15%:
before patch:
19417627 L1-icache-load-misses ( +- 0.147% )
after patch:
16490788 L1-icache-load-misses ( +- 0.180% )
The motivation of the patch was to fix a particular kprobes
bug that relates to the entry text section, the performance
advantage was discovered accidentally.
Whole perf output follows:
- results for current tip tree:
Performance counter stats for './hackbench/hackbench 10' (500 runs):
19417627 L1-icache-load-misses ( +- 0.147% )
2676914223 instructions # 0.497 IPC ( +- 0.079% )
5389516026 cycles ( +- 0.144% )
0.206267711 seconds time elapsed ( +- 0.138% )
- results for current tip tree with the patch applied:
Performance counter stats for './hackbench/hackbench 10' (500 runs):
16490788 L1-icache-load-misses ( +- 0.180% )
2717734941 instructions # 0.502 IPC ( +- 0.079% )
5414756975 cycles ( +- 0.148% )
0.206747566 seconds time elapsed ( +- 0.137% )
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: masami.hiramatsu.pt@hitachi.com
Cc: ananth@in.ibm.com
Cc: davem@davemloft.net
Cc: 2nddept-manager@sdl.hitachi.co.jp
LKML-Reference: <20110307181039.GB15197@jolsa.redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
44 lines
1.2 KiB
C
44 lines
1.2 KiB
C
#ifndef _ASM_GENERIC_SECTIONS_H_
|
|
#define _ASM_GENERIC_SECTIONS_H_
|
|
|
|
/* References to section boundaries */
|
|
|
|
extern char _text[], _stext[], _etext[];
|
|
extern char _data[], _sdata[], _edata[];
|
|
extern char __bss_start[], __bss_stop[];
|
|
extern char __init_begin[], __init_end[];
|
|
extern char _sinittext[], _einittext[];
|
|
extern char _end[];
|
|
extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
|
|
extern char __kprobes_text_start[], __kprobes_text_end[];
|
|
extern char __entry_text_start[], __entry_text_end[];
|
|
extern char __initdata_begin[], __initdata_end[];
|
|
extern char __start_rodata[], __end_rodata[];
|
|
|
|
/* Start and end of .ctors section - used for constructor calls. */
|
|
extern char __ctors_start[], __ctors_end[];
|
|
|
|
/* function descriptor handling (if any). Override
|
|
* in asm/sections.h */
|
|
#ifndef dereference_function_descriptor
|
|
#define dereference_function_descriptor(p) (p)
|
|
#endif
|
|
|
|
/* random extra sections (if any). Override
|
|
* in asm/sections.h */
|
|
#ifndef arch_is_kernel_text
|
|
static inline int arch_is_kernel_text(unsigned long addr)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifndef arch_is_kernel_data
|
|
static inline int arch_is_kernel_data(unsigned long addr)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#endif /* _ASM_GENERIC_SECTIONS_H_ */
|