Re: [PATCH 3/3] mm: don't remap clean subpages when splitting isolated thp

[Matthew Wilcox]

On Sat, Jul 31, 2021 at 12:39:38AM -0600, Yu Zhao wrote:
> +++ b/mm/migrate.c
> @@ -168,14 +168,53 @@ void putback_movable_pages(struct list_head *l)
>  	}
>  }
>  
> +static bool try_to_unmap_clean(struct page_vma_mapped_walk *pvmw, struct page *page)
> +{
> +	void *addr;
> +	bool dirty;
> +
> +	VM_BUG_ON_PAGE(PageLRU(page), page);
> +	VM_BUG_ON_PAGE(PageCompound(page), page);
> +	VM_BUG_ON_PAGE(!PageAnon(page), page);
> +	VM_BUG_ON_PAGE(!PageLocked(page), page);
> +	VM_BUG_ON_PAGE(pte_present(*pvmw->pte), page);
> +
> +	if (PageMlocked(page) || (pvmw->vma->vm_flags & VM_LOCKED))
> +		return false;
> +
> +	/*
> +	 * The pmd entry mapping the old thp was flushed and the pte mapping
> +	 * this subpage has been non present. Therefore, this subpage is
> +	 * inaccessible. We don't need to remap it if it contains only zeros.
> +	 */
> +	addr = kmap_atomic(page);
> +	dirty = !!memchr_inv(addr, 0, PAGE_SIZE);
> +	kunmap_atomic(addr);

kmap_local() is preferred now.  Also, Linus has a particular hatred for
the !! idiom; just compare against NULL.