Re: [PATCH]mmap: not merge cloned VMA

[Andi Kleen <andi@firstfloor.org>]

Shaohua Li <shaohua.li@intel.com> writes:

> Avoid merging a VMA with another VMA which is cloned from parent process. The
> cloned VMA shares lock with parent process's VMA. If we do the merge, more vma
> area (even the new range is only for current process) uses perent process's
> anon_vma lock, so introduces scalability issues.
> find_mergeable_anon_vma already considers this.

In theory this could prevent quite some VMA merging, but I guess the 
tradeoff is worth it and that should be unlikely to hit anyways.

>  static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
> -					struct anon_vma *anon_vma2)
> +					struct anon_vma *anon_vma2,
> +					struct vm_area_struct *vma)
>  {
> -	return !anon_vma1 || !anon_vma2 || (anon_vma1 == anon_vma2);
> +	if ((!anon_vma1 || !anon_vma2) && (!vma ||
> +		list_is_singular(&vma->anon_vma_chain)))
> +		return 1;

I think this if () needs a comment.

-Andi
-- 
ak@linux.intel.com -- Speaking for myself only

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>