diff options
| author | Arjan van de Ven <arjan@intel.linux.com> | 2006-03-25 16:30:10 +0100 |
|---|---|---|
| committer | Linus Torvalds <torvalds@g5.osdl.org> | 2006-03-25 09:10:54 -0800 |
| commit | a9ba9a3b3897561d01e04cd21433746df46548c0 (patch) | |
| tree | d222fb0e1c522d4bd506cb8c24c498a7e1589da2 /arch/x86_64/mm/fault.c | |
| parent | 4bc32c4d5cde5c57edcc9c2fe5057da8a4dd0153 (diff) | |
| download | lwn-a9ba9a3b3897561d01e04cd21433746df46548c0.tar.gz lwn-a9ba9a3b3897561d01e04cd21433746df46548c0.zip | |
[PATCH] x86_64: prefetch the mmap_sem in the fault path
In a micro-benchmark that stresses the pagefault path, the down_read_trylock
on the mmap_sem showed up quite high on the profile. Turns out this lock is
bouncing between cpus quite a bit and thus is cache-cold a lot. This patch
prefetches the lock (for write) as early as possible (and before some other
somewhat expensive operations). With this patch, the down_read_trylock
basically fell out of the top of profile.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'arch/x86_64/mm/fault.c')
| -rw-r--r-- | arch/x86_64/mm/fault.c | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c index de91e17daf6f..316c53de47bd 100644 --- a/arch/x86_64/mm/fault.c +++ b/arch/x86_64/mm/fault.c @@ -314,11 +314,13 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long flags; siginfo_t info; + tsk = current; + mm = tsk->mm; + prefetchw(&mm->mmap_sem); + /* get the address */ __asm__("movq %%cr2,%0":"=r" (address)); - tsk = current; - mm = tsk->mm; info.si_code = SEGV_MAPERR; |