Commit a9ba9a3b authored Mar 25, 2006 by Arjan van de Ven Committed by Linus Torvalds Mar 25, 2006

[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>

parent 4bc32c4d

arch/x86_64/mm/fault.c

+4 −2

Original line number	Diff line number	Diff line
		@@ -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;