[to-be-updated] mm-compaction-fix-the-range-to-pageblock_pfn_to_page.patch removed from -mm tree

[to-be-updated] mm-compaction-fix-the-range-to-pageblock_pfn_to_page.patch removed from -mm tree

[Andrew Morton]

The quilt patch titled
     Subject: mm/compaction: fix the range to pageblock_pfn_to_page()
has been removed from the -mm tree.  Its filename was
     mm-compaction-fix-the-range-to-pageblock_pfn_to_page.patch

This patch was dropped because an updated version will be issued

------------------------------------------------------
From: Wei Yang <richard.weiyang@gmail.com>
Subject: mm/compaction: fix the range to pageblock_pfn_to_page()
Date: Thu, 2 Oct 2025 03:31:40 +0000

The function pageblock_pfn_to_page() must confirm that the target range is
contained entirely within the current zone.

Originally, when pageblock_pfn_to_page() was introduced by commit
7d49d8868336, it operated on a single range, [pfn, block_end_pfn], for
both range checking and isolation.

However, commit e1409c325fdc ("mm/compaction: pass only pageblock aligned
range to pageblock_pfn_to_page") changed this behavior, causing the
function to operate on two different ranges:

[block_start_pfn, block_end_pfn] is used to check if the range is in the
same zone.

[pfn, block_end_pfn] is used for page isolation.

This split logic fails when start_pfn < zone_start_pfn, even if both are
within the same pageblock.  In this scenario, the checking range
[block_start_pfn, block_end_pfn] is used, which incorrectly misses the
pages before zone_start_pfn.

         start_pfn     zone_start_pfn
    +----+-------------+-------------------+
    block_start_pfn                        block_end_pfn

This oversight allows the range check to pass, even though the isolation
step ([pfn, block_end_pfn]) may attempt to isolate pages belonging to two
different zones.

To fix this, we should revert to using the same range ([block_start_pfn,
block_end_pfn]) for both checking and isolation in each iteration.

Link: https://lkml.kernel.org/r/20251002033140.24462-3-richard.weiyang@gmail.com
Fixes: e1409c325fdc ("mm/compaction: pass only pageblock aligned range to pageblock_pfn_to_page")
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/compaction.c |   37 ++++++++++++++-----------------------
 1 file changed, 14 insertions(+), 23 deletions(-)

--- a/mm/compaction.c~mm-compaction-fix-the-range-to-pageblock_pfn_to_page
+++ a/mm/compaction.c
@@ -1320,27 +1320,22 @@ int
 isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 							unsigned long end_pfn)
 {
-	unsigned long pfn, block_start_pfn, block_end_pfn;
+	unsigned long block_start_pfn, block_end_pfn;
 	int ret = 0;
 
 	/* Scan block by block. First and last block may be incomplete */
-	pfn = start_pfn;
-	block_start_pfn = pageblock_start_pfn(pfn);
-	if (block_start_pfn < cc->zone->zone_start_pfn)
-		block_start_pfn = cc->zone->zone_start_pfn;
-	block_end_pfn = pageblock_end_pfn(pfn);
+	block_start_pfn = start_pfn;
+	block_end_pfn = pageblock_end_pfn(start_pfn);
 
-	for (; pfn < end_pfn; pfn = block_end_pfn,
-				block_start_pfn = block_end_pfn,
+	for (; block_start_pfn < end_pfn; block_start_pfn = block_end_pfn,
 				block_end_pfn += pageblock_nr_pages) {
 
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
-		if (!pageblock_pfn_to_page(block_start_pfn,
-					block_end_pfn, cc->zone))
+		if (!pageblock_pfn_to_page(block_start_pfn, block_end_pfn, cc->zone))
 			continue;
 
-		ret = isolate_migratepages_block(cc, pfn, block_end_pfn,
+		ret = isolate_migratepages_block(cc, block_start_pfn, block_end_pfn,
 						 ISOLATE_UNEVICTABLE);
 
 		if (ret)
@@ -2046,7 +2041,6 @@ static isolate_migrate_t isolate_migrate
 {
 	unsigned long block_start_pfn;
 	unsigned long block_end_pfn;
-	unsigned long low_pfn;
 	struct page *page;
 	const isolate_mode_t isolate_mode =
 		(sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) |
@@ -2058,20 +2052,17 @@ static isolate_migrate_t isolate_migrate
 	 * initialized by compact_zone(). The first failure will use
 	 * the lowest PFN as the starting point for linear scanning.
 	 */
-	low_pfn = fast_find_migrateblock(cc);
-	block_start_pfn = pageblock_start_pfn(low_pfn);
-	if (block_start_pfn < cc->zone->zone_start_pfn)
-		block_start_pfn = cc->zone->zone_start_pfn;
+	block_start_pfn = fast_find_migrateblock(cc);
 
 	/*
 	 * fast_find_migrateblock() has already ensured the pageblock is not
 	 * set with a skipped flag, so to avoid the isolation_suitable check
 	 * below again, check whether the fast search was successful.
 	 */
-	fast_find_block = low_pfn != cc->migrate_pfn && !cc->fast_search_fail;
+	fast_find_block = block_start_pfn != cc->migrate_pfn && !cc->fast_search_fail;
 
 	/* Only scan within a pageblock boundary */
-	block_end_pfn = pageblock_end_pfn(low_pfn);
+	block_end_pfn = pageblock_end_pfn(block_start_pfn);
 
 	/*
 	 * Iterate over whole pageblocks until we find the first suitable.
@@ -2079,7 +2070,7 @@ static isolate_migrate_t isolate_migrate
 	 */
 	for (; block_end_pfn <= cc->free_pfn;
 			fast_find_block = false,
-			cc->migrate_pfn = low_pfn = block_end_pfn,
+			cc->migrate_pfn = block_end_pfn,
 			block_start_pfn = block_end_pfn,
 			block_end_pfn += pageblock_nr_pages) {
 
@@ -2088,7 +2079,7 @@ static isolate_migrate_t isolate_migrate
 		 * many pageblocks unsuitable, so periodically check if we
 		 * need to schedule.
 		 */
-		if (!(low_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages)))
+		if (!(block_start_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages)))
 			cond_resched();
 
 		page = pageblock_pfn_to_page(block_start_pfn,
@@ -2109,8 +2100,8 @@ static isolate_migrate_t isolate_migrate
 		 * before making it "skip" so other compaction instances do
 		 * not scan the same block.
 		 */
-		if ((pageblock_aligned(low_pfn) ||
-		     low_pfn == cc->zone->zone_start_pfn) &&
+		if ((pageblock_aligned(block_start_pfn) ||
+		     block_start_pfn == cc->zone->zone_start_pfn) &&
 		    !fast_find_block && !isolation_suitable(cc, page))
 			continue;
 
@@ -2128,7 +2119,7 @@ static isolate_migrate_t isolate_migrate
 		}
 
 		/* Perform the isolation */
-		if (isolate_migratepages_block(cc, low_pfn, block_end_pfn,
+		if (isolate_migratepages_block(cc, block_start_pfn, block_end_pfn,
 						isolate_mode))
 			return ISOLATE_ABORT;
 
_

Patches currently in -mm which might be from richard.weiyang@gmail.com are

mm-huge_memory-add-pmd-folio-to-ds_queue-in-do_huge_zero_wp_pmd.patch
mm-khugepaged-unify-pmd-folio-installation-with-map_anon_folio_pmd.patch
mm-huge_memory-only-get-folio_order-once-during-__folio_split.patch
mm-huge_memory-avoid-reinvoking-folio_test_anon.patch
mm-huge_memory-update-folio-stat-after-successful-split.patch
mm-huge_memory-optimize-and-simplify-folio-stat-update-after-split.patch
mm-huge_memory-optimize-old_order-derivation-during-folio-splitting.patch
mm-huge_memory-introduce-enum-split_type-for-clarity.patch
mm-huge_memory-merge-uniform_split_supported-and-non_uniform_split_supported.patch