If we know we have a folio, we can call put_folio() instead of put_page()
and save the overhead of calling compound_head(). Also skips the
devmap checks.
This commit looks like it should be a no-op, but actually saves 1714 bytes
of text with the distro-derived config that I'm testing. Some functions
grow a little while others shrink. I presume the compiler is making
different inlining decisions.
Signed-off-by: Matthew Wilcox (Oracle) <wi...@infradead.org>
Reviewed-by: Zi Yan <z...@nvidia.com>
---
include/linux/mm.h | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ecfe202aa4ec..30fd431b1b05 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1205,9 +1205,15 @@ static inline __must_check bool try_get_page(struct page
*page)
return true;
}
+static inline void put_folio(struct folio *folio)
+{
+ if (put_page_testzero(&folio->page))
+ __put_page(&folio->page);
+}
+
static inline void put_page(struct page *page)
{
- page = compound_head(page);
+ struct folio *folio = page_folio(page);
/*
* For devmap managed pages we need to catch refcount transition from
@@ -1215,13 +1221,12 @@ static inline void put_page(struct page *page)
* need to inform the device driver through callback. See
* include/linux/memremap.h and HMM for details.
*/
- if (page_is_devmap_managed(page)) {
- put_devmap_managed_page(page);
+ if (page_is_devmap_managed(&folio->page)) {
+ put_devmap_managed_page(&folio->page);
return;
}
- if (put_page_testzero(page))
- __put_page(page);
+ put_folio(folio);
}
/*
--
2.30.0
