Re: [PATCHv6 01/37] mm, shmem: swich huge tmpfs to multi-order radix-tree entries

[Kirill A. Shutemov]

On Thu, Feb 09, 2017 at 07:58:20PM +0300, Kirill A. Shutemov wrote:
> I'll look into it.

I ended up with this (I'll test it more later):

void filemap_map_pages(struct vm_fault *vmf,
		pgoff_t start_pgoff, pgoff_t end_pgoff)
{
	struct radix_tree_iter iter;
	void **slot;
	struct file *file = vmf->vma->vm_file;
	struct address_space *mapping = file->f_mapping;
	pgoff_t last_pgoff = start_pgoff;
	loff_t size;
	struct page *page;
	bool mapped;

	rcu_read_lock();
	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter,
			start_pgoff) {
		unsigned long index = iter.index;
		if (index < start_pgoff)
			index = start_pgoff;
		if (index > end_pgoff)
			break;
repeat:
		page = radix_tree_deref_slot(slot);
		if (unlikely(!page))
			continue;
		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page))
				slot = radix_tree_iter_retry(&iter);
			continue;
		}

		if (!page_cache_get_speculative(page))
			goto repeat;

		/* Has the page moved? */
		if (unlikely(page != *slot)) {
			put_page(page);
			goto repeat;
		}

		/* For multi-order entries, find relevant subpage */
		page = find_subpage(page, index);

		if (!PageUptodate(page) || PageReadahead(page))
			goto skip;
		if (!trylock_page(page))
			goto skip;

		if (page_mapping(page) != mapping || !PageUptodate(page))
			goto skip_unlock;

		size = round_up(i_size_read(mapping->host), PAGE_SIZE);
		if (compound_head(page)->index >= size >> PAGE_SHIFT)
			goto skip_unlock;

		if (file->f_ra.mmap_miss > 0)
			file->f_ra.mmap_miss--;
map_next_subpage:
		if (PageHWPoison(page))
			goto next;

		vmf->address += (index - last_pgoff) << PAGE_SHIFT;
		if (vmf->pte)
			vmf->pte += index - last_pgoff;
		last_pgoff = index;
		mapped = !alloc_set_pte(vmf, NULL, page);

		/* Huge page is mapped or last index? No need to proceed. */
		if (pmd_trans_huge(*vmf->pmd) ||
				index == end_pgoff) {
			unlock_page(page);
			break;
		}
next:
		if (page && PageCompound(page)) {
			/* Last subpage handled? */
			if ((index & (compound_nr_pages(page) - 1)) ==
					compound_nr_pages(page) - 1)
				goto skip_unlock;
			index++;
			page++;

			/*
			 * One page reference goes to page table mapping.
			 * Need additional reference, if last alloc_set_pte()
			 * succeed.
			 */
			if (mapped)
				get_page(page);
			goto map_next_subpage;
		}
skip_unlock:
		unlock_page(page);
skip:
		iter.index = compound_head(page)->index +
			compound_nr_pages(page) - 1;
		/* Only give up reference if alloc_set_pte() failed. */
		if (!mapped)
			put_page(page);
	}
	rcu_read_unlock();
}

-- 
 Kirill A. Shutemov