mm: filemap: use xa_get_order() to get the swap entry order

In the following patches, shmem will support the swap out of large folios,
which means the shmem mappings may contain large order swap entries, so
using xa_get_order() to get the folio order of the shmem swap entry to
update the '*start' correctly.

[hughd@google.com: use xa_get_order() to get the swap entry order]
  Link: https://lkml.kernel.org/r/c336e6e4-da7f-b714-c0f1-12df715f2611@google.com
Link: https://lkml.kernel.org/r/6876d55145c1cc80e79df7884aa3a62e397b101d.1723434324.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Chris Li <chrisl@kernel.org>
Cc: Daniel Gomez <da.gomez@samsung.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 27 insertions, 14 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index fcfec2a78a30..fdaa1e5e3078 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2046,17 +2046,20 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
 		if (!folio_batch_add(fbatch, folio))
 			break;
 	}
-	rcu_read_unlock();
 
 	if (folio_batch_count(fbatch)) {
-		unsigned long nr = 1;
+		unsigned long nr;
 		int idx = folio_batch_count(fbatch) - 1;
 
 		folio = fbatch->folios[idx];
 		if (!xa_is_value(folio))
 			nr = folio_nr_pages(folio);
-		*start = indices[idx] + nr;
+		else
+			nr = 1 << xa_get_order(&mapping->i_pages, indices[idx]);
+		*start = round_down(indices[idx] + nr, nr);
 	}
+	rcu_read_unlock();
+
 	return folio_batch_count(fbatch);
 }
 
@@ -2088,10 +2091,17 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
 
 	rcu_read_lock();
 	while ((folio = find_get_entry(&xas, end, XA_PRESENT))) {
+		unsigned long base;
+		unsigned long nr;
+
 		if (!xa_is_value(folio)) {
-			if (folio->index < *start)
+			nr = folio_nr_pages(folio);
+			base = folio->index;
+			/* Omit large folio which begins before the start */
+			if (base < *start)
 				goto put;
-			if (folio_next_index(folio) - 1 > end)
+			/* Omit large folio which extends beyond the end */
+			if (base + nr - 1 > end)
 				goto put;
 			if (!folio_trylock(folio))
 				goto put;
@@ -2100,7 +2110,19 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
 				goto unlock;
 			VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index),
 					folio);
+		} else {
+			nr = 1 << xa_get_order(&mapping->i_pages, xas.xa_index);
+			base = xas.xa_index & ~(nr - 1);
+			/* Omit order>0 value which begins before the start */
+			if (base < *start)
+				continue;
+			/* Omit order>0 value which extends beyond the end */
+			if (base + nr - 1 > end)
+				break;
 		}
+
+		/* Update start now so that last update is correct on return */
+		*start = base + nr;
 		indices[fbatch->nr] = xas.xa_index;
 		if (!folio_batch_add(fbatch, folio))
 			break;
@@ -2112,15 +2134,6 @@ put:
 	}
 	rcu_read_unlock();
 
-	if (folio_batch_count(fbatch)) {
-		unsigned long nr = 1;
-		int idx = folio_batch_count(fbatch) - 1;
-
-		folio = fbatch->folios[idx];
-		if (!xa_is_value(folio))
-			nr = folio_nr_pages(folio);
-		*start = indices[idx] + nr;
-	}
 	return folio_batch_count(fbatch);
 }