Hi,

On 2024-10-24 07:00, Christoph Hellwig wrote:
> From: Ming Lei <ming.lei@redhat.com>
> 
> The iov_iter_extract_pages interface allows to return physically
> discontiguous pages, as long as all but the first and last page
> in the array are page aligned and page size.  Rewrite
> iov_iter_extract_bvec_pages to take advantage of that instead of only
> returning ranges of physically contiguous pages.
> 
> Signed-off-by: Ming Lei <ming.lei@redhat.com>
> [hch: minor cleanups, new commit log]
> Signed-off-by: Christoph Hellwig <hch@lst.de>

With this patch (e4e535bff2bc82bb49a633775f9834beeaa527db in 
next-20241030), I'm unable to connect via nvme-tcp with this in the log:

nvme nvme1: failed to send request -5
nvme nvme1: Connect command failed: host path error
nvme nvme1: failed to connect queue: 0 ret=880

With the patch reverted it works as expected:

nvme nvme1: creating 24 I/O queues.
nvme nvme1: mapped 24/0/0 default/read/poll queues.
nvme nvme1: new ctrl: NQN 
"nqn.2018-06.eu.kasm.int:freenas:backup:parmesan.int.kasm.eu", addr 
[2001:0678:0a5c:1204:6245:cbff:fe9c:4f59]:4420, hostnqn: 
nqn.2018-06.eu.kasm.int:parmesan


Please let me know if there's anything else you need.

Regards,
Klara Modin

+CC: linux-nvme

> ---
>   lib/iov_iter.c | 67 +++++++++++++++++++++++++++++++++-----------------
>   1 file changed, 45 insertions(+), 22 deletions(-)
> 
> diff --git a/lib/iov_iter.c b/lib/iov_iter.c
> index 1abb32c0da50..9fc06f5fb748 100644
> --- a/lib/iov_iter.c
> +++ b/lib/iov_iter.c
> @@ -1677,8 +1677,8 @@ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i,
>   }
>   
>   /*
> - * Extract a list of contiguous pages from an ITER_BVEC iterator.  This does
> - * not get references on the pages, nor does it get a pin on them.
> + * Extract a list of virtually contiguous pages from an ITER_BVEC iterator.
> + * This does not get references on the pages, nor does it get a pin on them.
>    */
>   static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i,
>   					   struct page ***pages, size_t maxsize,
> @@ -1686,35 +1686,58 @@ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i,
>   					   iov_iter_extraction_t extraction_flags,
>   					   size_t *offset0)
>   {
> -	struct page **p, *page;
> -	size_t skip = i->iov_offset, offset, size;
> -	int k;
> +	size_t skip = i->iov_offset, size = 0;
> +	struct bvec_iter bi;
> +	int k = 0;
>   
> -	for (;;) {
> -		if (i->nr_segs == 0)
> -			return 0;
> -		size = min(maxsize, i->bvec->bv_len - skip);
> -		if (size)
> -			break;
> +	if (i->nr_segs == 0)
> +		return 0;
> +
> +	if (i->iov_offset == i->bvec->bv_len) {
>   		i->iov_offset = 0;
>   		i->nr_segs--;
>   		i->bvec++;
>   		skip = 0;
>   	}
> +	bi.bi_size = maxsize + skip;
> +	bi.bi_bvec_done = skip;
> +
> +	maxpages = want_pages_array(pages, maxsize, skip, maxpages);
> +
> +	while (bi.bi_size && bi.bi_idx < i->nr_segs) {
> +		struct bio_vec bv = bvec_iter_bvec(i->bvec, bi);
> +
> +		/*
> +		 * The iov_iter_extract_pages interface only allows an offset
> +		 * into the first page.  Break out of the loop if we see an
> +		 * offset into subsequent pages, the caller will have to call
> +		 * iov_iter_extract_pages again for the reminder.
> +		 */
> +		if (k) {
> +			if (bv.bv_offset)
> +				break;
> +		} else {
> +			*offset0 = bv.bv_offset;
> +		}
>   
> -	skip += i->bvec->bv_offset;
> -	page = i->bvec->bv_page + skip / PAGE_SIZE;
> -	offset = skip % PAGE_SIZE;
> -	*offset0 = offset;
> +		(*pages)[k++] = bv.bv_page;
> +		size += bv.bv_len;
>   
> -	maxpages = want_pages_array(pages, size, offset, maxpages);
> -	if (!maxpages)
> -		return -ENOMEM;
> -	p = *pages;
> -	for (k = 0; k < maxpages; k++)
> -		p[k] = page + k;
> +		if (k >= maxpages)
> +			break;
> +
> +		/*
> +		 * We are done when the end of the bvec doesn't align to a page
> +		 * boundary as that would create a hole in the returned space.
> +		 * The caller will handle this with another call to
> +		 * iov_iter_extract_pages.
> +		 */
> +		if (bv.bv_offset + bv.bv_len != PAGE_SIZE)
> +			break;
> +
> +		bvec_iter_advance_single(i->bvec, &bi, bv.bv_len);
> +	}
>   
> -	size = min_t(size_t, size, maxpages * PAGE_SIZE - offset);
>   	iov_iter_advance(i, size);
>   	return size;
>   }