[PATCH v13 125/137] mm/filemap: Return only head pages from find_get_entries

["Matthew Wilcox (Oracle)" <willy@infradead.org>]

All callers now expect head (and base) pages, and can handle multiple
head pages in a single batch, so make find_get_entries() behave that way.
Also take the opportunity to make it use the pagevec infrastructure
instead of open-coding how pvecs behave.  This has the side-effect of
being able to append to a pagevec with existing contents, although we
don't make use of that functionality anywhere yet.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
---
 include/linux/pagemap.h |  2 --
 mm/filemap.c            | 40 ++++++++++------------------------------
 mm/internal.h           |  2 ++
 3 files changed, 12 insertions(+), 32 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e7539da390d2..90935f231419 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -502,8 +502,6 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index)
 	return head + (index & (thp_nr_pages(head) - 1));
 }
 
-unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
-		pgoff_t end, struct pagevec *pvec, pgoff_t *indices);
 unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
 			pgoff_t end, unsigned int nr_pages,
 			struct page **pages);
diff --git a/mm/filemap.c b/mm/filemap.c
index 82f985f61224..aaed0396db28 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1955,49 +1955,29 @@ static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max,
  * the mapping.  The entries are placed in @pvec.  find_get_entries()
  * takes a reference on any actual pages it returns.
  *
- * The search returns a group of mapping-contiguous page cache entries
- * with ascending indexes.  There may be holes in the indices due to
- * not-present pages.
+ * The entries have ascending indexes.  The indices may not be consecutive
+ * due to not-present entries or THPs.
  *
  * Any shadow entries of evicted pages, or swap entries from
  * shmem/tmpfs, are included in the returned array.
  *
- * If it finds a Transparent Huge Page, head or tail, find_get_entries()
- * stops at that page: the caller is likely to have a better way to handle
- * the compound page as a whole, and then skip its extent, than repeatedly
- * calling find_get_entries() to return all its tails.
- *
- * Return: the number of pages and shadow entries which were found.
+ * Return: The number of entries which were found.
  */
 unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
 		pgoff_t end, struct pagevec *pvec, pgoff_t *indices)
 {
 	XA_STATE(xas, &mapping->i_pages, start);
-	struct page *page;
-	unsigned int ret = 0;
-	unsigned nr_entries = PAGEVEC_SIZE;
+	struct folio *folio;
 
 	rcu_read_lock();
-	while ((page = &find_get_entry(&xas, end, XA_PRESENT)->page)) {
-		/*
-		 * Terminate early on finding a THP, to allow the caller to
-		 * handle it all at once; but continue if this is hugetlbfs.
-		 */
-		if (!xa_is_value(page) && PageTransHuge(page) &&
-				!PageHuge(page)) {
-			page = find_subpage(page, xas.xa_index);
-			nr_entries = ret + 1;
-		}
-
-		indices[ret] = xas.xa_index;
-		pvec->pages[ret] = page;
-		if (++ret == nr_entries)
+	while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) {
+		indices[pvec->nr] = xas.xa_index;
+		if (!pagevec_add(pvec, &folio->page))
 			break;
 	}
 	rcu_read_unlock();
 
-	pvec->nr = ret;
-	return ret;
+	return pagevec_count(pvec);
 }
 
 /**
@@ -2016,8 +1996,8 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
  * not returned.
  *
  * The entries have ascending indexes.  The indices may not be consecutive
- * due to not-present entries, THP pages, pages which could not be locked
- * or pages under writeback.
+ * due to not-present entries, THPs, pages which could not be locked or
+ * pages under writeback.
  *
  * Return: The number of entries which were found.
  */
diff --git a/mm/internal.h b/mm/internal.h
index 4730e9267bfc..65314d4380d0 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -70,6 +70,8 @@ static inline void force_page_cache_readahead(struct address_space *mapping,
 
 unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
 		pgoff_t end, struct pagevec *pvec, pgoff_t *indices);
+unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
+		pgoff_t end, struct pagevec *pvec, pgoff_t *indices);
 bool truncate_inode_partial_page(struct page *page, loff_t start, loff_t end);
 
 /**
-- 
2.30.2