Re: [PATCH 10/12] xfs: use vmalloc instead of vm_map_area for buffer backing memory

[Dave Chinner <david@fromorbit.com>]

On Wed, Mar 05, 2025 at 07:05:27AM -0700, Christoph Hellwig wrote:
> The fallback buffer allocation path currently open codes a suboptimal
> version of vmalloc to allocate pages that are then mapped into
> vmalloc space.  Switch to using vmalloc instead, which uses all the
> optimizations in the common vmalloc code, and removes the need to
> track the backing pages in the xfs_buf structure.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
.....

> @@ -1500,29 +1373,43 @@ static void
>  xfs_buf_submit_bio(
>  	struct xfs_buf		*bp)
>  {
> -	unsigned int		size = BBTOB(bp->b_length);
> -	unsigned int		map = 0, p;
> +	unsigned int		map = 0;
>  	struct blk_plug		plug;
>  	struct bio		*bio;
>  
> -	bio = bio_alloc(bp->b_target->bt_bdev, bp->b_page_count,
> -			xfs_buf_bio_op(bp), GFP_NOIO);
> -	bio->bi_private = bp;
> -	bio->bi_end_io = xfs_buf_bio_end_io;
> +	if (is_vmalloc_addr(bp->b_addr)) {
> +		unsigned int	size = BBTOB(bp->b_length);
> +		unsigned int	alloc_size = roundup(size, PAGE_SIZE);
> +		void		*data = bp->b_addr;
>  
> -	if (bp->b_page_count == 1) {
> -		__bio_add_page(bio, virt_to_page(bp->b_addr), size,
> -				offset_in_page(bp->b_addr));
> -	} else {
> -		for (p = 0; p < bp->b_page_count; p++)
> -			__bio_add_page(bio, bp->b_pages[p], PAGE_SIZE, 0);
> -		bio->bi_iter.bi_size = size; /* limit to the actual size used */
> +		bio = bio_alloc(bp->b_target->bt_bdev, alloc_size >> PAGE_SHIFT,
> +				xfs_buf_bio_op(bp), GFP_NOIO);
> +
> +		do {
> +			unsigned int	len = min(size, PAGE_SIZE);
>  
> -		if (is_vmalloc_addr(bp->b_addr))
> -			flush_kernel_vmap_range(bp->b_addr,
> -					xfs_buf_vmap_len(bp));
> +			ASSERT(offset_in_page(data) == 0);
> +			__bio_add_page(bio, vmalloc_to_page(data), len, 0);
> +			data += len;
> +			size -= len;
> +		} while (size);
> +
> +		flush_kernel_vmap_range(bp->b_addr, alloc_size);
> +	} else {
> +		/*
> +		 * Single folio or slab allocation.  Must be contiguous and thus
> +		 * only a single bvec is needed.
> +		 */
> +		bio = bio_alloc(bp->b_target->bt_bdev, 1, xfs_buf_bio_op(bp),
> +				GFP_NOIO);
> +		__bio_add_page(bio, virt_to_page(bp->b_addr),
> +				BBTOB(bp->b_length),
> +				offset_in_page(bp->b_addr));
>  	}

How does offset_in_page() work with a high order folio? It can only
return a value between 0 and (PAGE_SIZE - 1). i.e. shouldn't this
be:

		folio = kmem_to_folio(bp->b_addr);

		bio_add_folio_nofail(bio, folio, BBTOB(bp->b_length),
				offset_in_folio(folio, bp->b_addr));


-Dave.
-- 
Dave Chinner
david@fromorbit.com