On Tue, Sep 16, 2025 at 4:50 PM Joanne Koong <joannelkoong@xxxxxxxxx> wrote:
>
> Iterate over all non-uptodate ranges in a single call to
> iomap_readpage_iter() instead of leaving the partial folio iteration to
> the caller.
>
> This will be useful for supporting caller-provided async folio read
> callbacks (added in later commit) because that will require tracking
> when the first and last async read request for a folio is sent, in order
> to prevent premature read completion of the folio.
>
> This additionally makes the iomap_readahead_iter() logic a bit simpler.
>
> Signed-off-by: Joanne Koong <joannelkoong@xxxxxxxxx>
> Reviewed-by: Christoph Hellwig <hch@xxxxxx>
> ---
> fs/iomap/buffered-io.c | 69 ++++++++++++++++++++----------------------
> 1 file changed, 32 insertions(+), 37 deletions(-)
>
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 2a1709e0757b..0c4ba2a63490 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -420,6 +420,7 @@ static int iomap_readpage_iter(struct iomap_iter *iter,
> loff_t length = iomap_length(iter);
> struct folio *folio = ctx->cur_folio;
> size_t poff, plen;
> + loff_t count;
> int ret;
>
> if (iomap->type == IOMAP_INLINE) {
> @@ -431,39 +432,33 @@ static int iomap_readpage_iter(struct iomap_iter *iter,
>
> /* zero post-eof blocks as the page may be mapped */
> ifs_alloc(iter->inode, folio, iter->flags);
> - iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, &plen);
> - if (plen == 0)
> - goto done;
>
> - if (iomap_block_needs_zeroing(iter, pos)) {
> - folio_zero_range(folio, poff, plen);
> - iomap_set_range_uptodate(folio, poff, plen);
> - } else {
> - iomap_bio_read_folio_range(iter, ctx, pos, plen);
> - }
> + length = min_t(loff_t, length,
> + folio_size(folio) - offset_in_folio(folio, pos));
> + while (length) {
> + iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff,
> + &plen);
>
> -done:
> - /*
> - * Move the caller beyond our range so that it keeps making progress.
> - * For that, we have to include any leading non-uptodate ranges, but
> - * we can skip trailing ones as they will be handled in the next
> - * iteration.
> - */
> - length = pos - iter->pos + plen;
> - return iomap_iter_advance(iter, &length);
> -}
> + count = pos - iter->pos + plen;
> + if (WARN_ON_ONCE(count > length))
> + return -EIO;
>
> -static int iomap_read_folio_iter(struct iomap_iter *iter,
> - struct iomap_readpage_ctx *ctx)
> -{
> - int ret;
> + if (plen == 0)
> + return iomap_iter_advance(iter, &count);
>
> - while (iomap_length(iter)) {
> - ret = iomap_readpage_iter(iter, ctx);
> + if (iomap_block_needs_zeroing(iter, pos)) {
> + folio_zero_range(folio, poff, plen);
> + iomap_set_range_uptodate(folio, poff, plen);
> + } else {
> + iomap_bio_read_folio_range(iter, ctx, pos, plen);
> + }
> +
> + length -= count;
> + ret = iomap_iter_advance(iter, &count);
> if (ret)
> return ret;
> + pos = iter->pos;
> }
> -
> return 0;
> }
>
> @@ -482,7 +477,7 @@ int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
> trace_iomap_readpage(iter.inode, 1);
>
> while ((ret = iomap_iter(&iter, ops)) > 0)
> - iter.status = iomap_read_folio_iter(&iter, &ctx);
> + iter.status = iomap_readpage_iter(&iter, &ctx);
>
> iomap_bio_submit_read(&ctx);
>
> @@ -504,16 +499,16 @@ static int iomap_readahead_iter(struct iomap_iter *iter,
> int ret;
>
> while (iomap_length(iter)) {
> - if (ctx->cur_folio &&
> - offset_in_folio(ctx->cur_folio, iter->pos) == 0) {
> - if (!ctx->cur_folio_in_bio)
> - folio_unlock(ctx->cur_folio);
> - ctx->cur_folio = NULL;
> - }
> - if (!ctx->cur_folio) {
> - ctx->cur_folio = readahead_folio(ctx->rac);
> - ctx->cur_folio_in_bio = false;
> - }
> + if (ctx->cur_folio && !ctx->cur_folio_in_bio)
> + folio_unlock(ctx->cur_folio);
> + ctx->cur_folio = readahead_folio(ctx->rac);
Unfortunately, this logic simplification here doesn't work. It still
needs to check "offset_in_folio() == 0" because the iomap mapping may
only map in part of the folio, in which case the next round of
iomap_iter() should still operate on the same folio. I'll make this
change in v4.
> + /*
> + * We should never in practice hit this case since the iter
> + * length matches the readahead length.
> + */
> + if (WARN_ON_ONCE(!ctx->cur_folio))
> + return -EINVAL;
> + ctx->cur_folio_in_bio = false;
> ret = iomap_readpage_iter(iter, ctx);
> if (ret)
> return ret;
> --
> 2.47.3
>
