Re: [PATCH 1/4] mm/rmap: per anon_vma lock

[Peter Zijlstra <peterz@infradead.org>]

On Fri, Nov 01, 2013 at 03:54:24PM +0800, Yuanhan Liu wrote:
> @@ -497,15 +495,20 @@ static void vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root)
>   * anon_vma_interval_tree_post_update_vma().
>   *
>   * The entire update must be protected by exclusive mmap_sem and by
> - * the root anon_vma's mutex.
> + * the anon_vma's mutex.
>   */
>  static inline void
>  anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma)
>  {
>  	struct anon_vma_chain *avc;
>  
> -	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
> -		anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root);
> +	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) {
> +		struct anon_vma *anon_vma = avc->anon_vma;
> +
> +		anon_vma_lock_write(anon_vma);
> +		anon_vma_interval_tree_remove(avc, &anon_vma->rb_root);
> +		anon_vma_unlock_write(anon_vma);
> +	}
>  }
>  
>  static inline void
> @@ -513,8 +516,13 @@ anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma)
>  {
>  	struct anon_vma_chain *avc;
>  
> -	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
> -		anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root);
> +	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) {
> +		struct anon_vma *anon_vma = avc->anon_vma;
> +
> +		anon_vma_lock_write(anon_vma);
> +		anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
> +		anon_vma_unlock_write(anon_vma);
> +	}
>  }
>  
>  static int find_vma_links(struct mm_struct *mm, unsigned long addr,
> @@ -781,7 +789,6 @@ again:			remove_next = 1 + (end > next->vm_end);
>  	if (anon_vma) {
>  		VM_BUG_ON(adjust_next && next->anon_vma &&
>  			  anon_vma != next->anon_vma);
> -		anon_vma_lock_write(anon_vma);
>  		anon_vma_interval_tree_pre_update_vma(vma);
>  		if (adjust_next)
>  			anon_vma_interval_tree_pre_update_vma(next);
> @@ -845,7 +852,6 @@ again:			remove_next = 1 + (end > next->vm_end);
>  		anon_vma_interval_tree_post_update_vma(vma);
>  		if (adjust_next)
>  			anon_vma_interval_tree_post_update_vma(next);
> -		anon_vma_unlock_write(anon_vma);
>  	}
>  	if (mapping)
>  		mutex_unlock(&mapping->i_mmap_mutex);

AFAICT this isn't correct at all. We used to protect the vma interval
tree with the root lock, now we don't. All we've got left is the
mmap_sem, but anon_vma chains can cross address-spaces and thus we're up
some creek without no paddle.