On 2025/3/7 07:00, Nhat Pham wrote:
Similar to zswap_load(), also return proper error codes for
swap_read_folio_zeromap():
* 0 on success. The folio is unlocked and marked up-to-date.
* -ENOENT, if the folio is entirely not zeromapped.
* -EINVAL (with the follio unlocked but not marked to date), if the
folio is partially zeromapped. This is not supported, and will SIGBUS
the faulting process.
This patch is purely a clean-up, and should not have any behavioral
change. It is based on (and should be applied on top of) [1].
[1]: https://lore.kernel.org/linux-mm/20250306205011.784787-1-nphamcs@xxxxxxxxx/
Suggested-by: Yosry Ahmed <yosry.ahmed@xxxxxxxxx>
Suggested-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Signed-off-by: Nhat Pham <nphamcs@xxxxxxxxx>
Reviewed-by: Chengming Zhou <chengming.zhou@xxxxxxxxx>
Thanks!
---
mm/page_io.c | 35 ++++++++++++++++++++++++++---------
1 file changed, 26 insertions(+), 9 deletions(-)
diff --git a/mm/page_io.c b/mm/page_io.c
index 4bce19df557b..48ed1e810392 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -511,7 +511,23 @@ static void sio_read_complete(struct kiocb *iocb, long ret)
mempool_free(sio, sio_pool);
}
-static bool swap_read_folio_zeromap(struct folio *folio)
+/**
+ * swap_read_folio_zeromap - check if the folio was zeromapped, and if so,
+ * zero-fill it.
+ * @folio: the folio.
+ *
+ * Return: 0 on success, with the folio zero-filled, unlocked, and marked
+ * up-to-date, or one of the following error codes:
+ *
+ * -ENOENT: the folio is entirely not zeromapped. The folio remains locked.
+ *
+ * -EINVAL: some of the subpages in the folio are zeromaped, but not all of
+ * them. This is an error because we don't currently support a large folio
+ * that is partially in the zeromap. The folio is unlocked, but NOT marked
+ * up-to-date, so that an IO error is emitted (e.g. do_swap_page() will
+ * sigbus).
+ */
+static int swap_read_folio_zeromap(struct folio *folio)
{
int nr_pages = folio_nr_pages(folio);
struct obj_cgroup *objcg;
@@ -519,15 +535,17 @@ static bool swap_read_folio_zeromap(struct folio *folio)
/*
* Swapping in a large folio that is partially in the zeromap is not
- * currently handled. Return true without marking the folio uptodate so
+ * currently handled. Return -EINVAL without marking the folio uptodate so
* that an IO error is emitted (e.g. do_swap_page() will sigbus).
*/
if (WARN_ON_ONCE(swap_zeromap_batch(folio->swap, nr_pages,
- &is_zeromap) != nr_pages))
- return true;
+ &is_zeromap) != nr_pages)) {
+ folio_unlock(folio);
+ return -EINVAL;
+ }
if (!is_zeromap)
- return false;
+ return -ENOENT;
objcg = get_obj_cgroup_from_folio(folio);
count_vm_events(SWPIN_ZERO, nr_pages);
@@ -538,7 +556,8 @@ static bool swap_read_folio_zeromap(struct folio *folio)
folio_zero_range(folio, 0, folio_size(folio));
folio_mark_uptodate(folio);
- return true;
+ folio_unlock(folio);
+ return 0;
}
static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
@@ -635,10 +654,8 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
}
delayacct_swapin_start();
- if (swap_read_folio_zeromap(folio)) {
- folio_unlock(folio);
+ if (swap_read_folio_zeromap(folio) != -ENOENT)
goto finish;
- }
if (zswap_load(folio) != -ENOENT)
goto finish;
