iomap_readpage_iter() handles "uptodate blocks" and "not uptodate blocks"
within a folio separately. This makes iomap_read_folio() to call into
->iomap_begin() to request for extent mapping even though it might already
have an extent which is not fully processed.
This happens when we either have a large folio or with bs < ps. In these
cases we can have sub blocks which can be uptodate (say for e.g. due to
previous writes). With iomap_read_folio_iter(), this is handled more
efficiently by not calling ->iomap_begin() call until all the sub blocks
with the current folio are processed.
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@xxxxxxxxx>
cc: Ojaswin Mujoo <ojaswin@xxxxxxxxxxxxx>
---
fs/iomap/buffered-io.c | 20 +++++++++++++++++++-
1 file changed, 19 insertions(+), 1 deletion(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 9f79c82d1f73..0a4269095ae2 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -444,6 +444,24 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
return pos - orig_pos + plen;
}
+static loff_t iomap_read_folio_iter(const struct iomap_iter *iter,
+ struct iomap_readpage_ctx *ctx)
+{
+ struct folio *folio = ctx->cur_folio;
+ size_t pos = offset_in_folio(folio, iter->pos);
+ loff_t length = min_t(loff_t, folio_size(folio) - pos,
+ iomap_length(iter));
+ loff_t done, ret;
+
+ for (done = 0; done < length; done += ret) {
+ ret = iomap_readpage_iter(iter, ctx, done);
+ if (ret <= 0)
+ return ret;
+ }
+
+ return done;
+}
+
int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
{
struct iomap_iter iter = {
@@ -459,7 +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.processed = iomap_readpage_iter(&iter, &ctx, 0);
+ iter.processed = iomap_read_folio_iter(&iter, &ctx);
if (ret < 0)
folio_set_error(folio);
--
2.44.0
