mm: page_isolation: move has_unmovable_pages() to mm/page_isolation.c

Patch series "Use pageblock_order for cma and alloc_contig_range alignment", v11.

This patchset tries to remove the MAX_ORDER-1 alignment requirement for CMA
and alloc_contig_range(). It prepares for my upcoming changes to make
MAX_ORDER adjustable at boot time[1].

The MAX_ORDER - 1 alignment requirement comes from that
alloc_contig_range() isolates pageblocks to remove free memory from buddy
allocator but isolating only a subset of pageblocks within a page spanning
across multiple pageblocks causes free page accounting issues.  Isolated
page might not be put into the right free list, since the code assumes the
migratetype of the first pageblock as the whole free page migratetype. 
This is based on the discussion at [2].

To remove the requirement, this patchset:
1. isolates pages at pageblock granularity instead of
   max(MAX_ORDER_NR_PAEGS, pageblock_nr_pages);
2. splits free pages across the specified range or migrates in-use pages
   across the specified range then splits the freed page to avoid free page
   accounting issues (it happens when multiple pageblocks within a single page
   have different migratetypes);
3. only checks unmovable pages within the range instead of MAX_ORDER - 1 aligned
   range during isolation to avoid alloc_contig_range() failure when pageblocks
   within a MAX_ORDER - 1 aligned range are allocated separately.
4. returns pages not in the range as it did before.

One optimization might come later:
1. make MIGRATE_ISOLATE a separate bit to be able to restore the original
   migratetypes when isolation fails in the middle of the range.

[1] https://lore.kernel.org/linux-mm/20210805190253.2795604-1-zi.yan@sent.com/
[2] https://lore.kernel.org/linux-mm/d19fb078-cb9b-f60f-e310-fdeea1b947d2@redhat.com/


This patch (of 6):

has_unmovable_pages() is only used in mm/page_isolation.c.  Move it from
mm/page_alloc.c and make it static.

Link: https://lkml.kernel.org/r/20220425143118.2850746-2-zi.yan@sent.comSigned-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Eric Ren <renzhengeek@gmail.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Minchan Kim <minchan@kernel.org>
Cc: kernel test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/page-isolation.h

@@ -33,8 +33,6 @@ static inline bool is_migrate_isolate(int migratetype)
 #define MEMORY_OFFLINE	0x1
 #define REPORT_FAILURE	0x2
 
-struct page *has_unmovable_pages(struct zone *zone, struct page *page,
-				 int migratetype, int flags);
 void set_pageblock_migratetype(struct page *page, int migratetype);
 int move_freepages_block(struct zone *zone, struct page *page,
 				int migratetype, int *num_movable);

mm/page_alloc.c

@@ -8918,125 +8918,6 @@ void *__init alloc_large_system_hash(const char *tablename,
 	return table;
 }
 
-/*
- * This function checks whether pageblock includes unmovable pages or not.
- *
- * PageLRU check without isolation or lru_lock could race so that
- * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
- * check without lock_page also may miss some movable non-lru pages at
- * race condition. So you can't expect this function should be exact.
- *
- * Returns a page without holding a reference. If the caller wants to
- * dereference that page (e.g., dumping), it has to make sure that it
- * cannot get removed (e.g., via memory unplug) concurrently.
- *
- */
-struct page *has_unmovable_pages(struct zone *zone, struct page *page,
-				 int migratetype, int flags)
-{
-	unsigned long iter = 0;
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long offset = pfn % pageblock_nr_pages;
-
-	if (is_migrate_cma_page(page)) {
-		/*
-		 * CMA allocations (alloc_contig_range) really need to mark
-		 * isolate CMA pageblocks even when they are not movable in fact
-		 * so consider them movable here.
-		 */
-		if (is_migrate_cma(migratetype))
-			return NULL;
-
-		return page;
-	}
-
-	for (; iter < pageblock_nr_pages - offset; iter++) {
-		page = pfn_to_page(pfn + iter);
-
-		/*
-		 * Both, bootmem allocations and memory holes are marked
-		 * PG_reserved and are unmovable. We can even have unmovable
-		 * allocations inside ZONE_MOVABLE, for example when
-		 * specifying "movablecore".
-		 */
-		if (PageReserved(page))
-			return page;
-
-		/*
-		 * If the zone is movable and we have ruled out all reserved
-		 * pages then it should be reasonably safe to assume the rest
-		 * is movable.
-		 */
-		if (zone_idx(zone) == ZONE_MOVABLE)
-			continue;
-
-		/*
-		 * Hugepages are not in LRU lists, but they're movable.
-		 * THPs are on the LRU, but need to be counted as #small pages.
-		 * We need not scan over tail pages because we don't
-		 * handle each tail page individually in migration.
-		 */
-		if (PageHuge(page) || PageTransCompound(page)) {
-			struct page *head = compound_head(page);
-			unsigned int skip_pages;
-
-			if (PageHuge(page)) {
-				if (!hugepage_migration_supported(page_hstate(head)))
-					return page;
-			} else if (!PageLRU(head) && !__PageMovable(head)) {
-				return page;
-			}
-
-			skip_pages = compound_nr(head) - (page - head);
-			iter += skip_pages - 1;
-			continue;
-		}
-
-		/*
-		 * We can't use page_count without pin a page
-		 * because another CPU can free compound page.
-		 * This check already skips compound tails of THP
-		 * because their page->_refcount is zero at all time.
-		 */
-		if (!page_ref_count(page)) {
-			if (PageBuddy(page))
-				iter += (1 << buddy_order(page)) - 1;
-			continue;
-		}
-
-		/*
-		 * The HWPoisoned page may be not in buddy system, and
-		 * page_count() is not 0.
-		 */
-		if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
-			continue;
-
-		/*
-		 * We treat all PageOffline() pages as movable when offlining
-		 * to give drivers a chance to decrement their reference count
-		 * in MEM_GOING_OFFLINE in order to indicate that these pages
-		 * can be offlined as there are no direct references anymore.
-		 * For actually unmovable PageOffline() where the driver does
-		 * not support this, we will fail later when trying to actually
-		 * move these pages that still have a reference count > 0.
-		 * (false negatives in this function only)
-		 */
-		if ((flags & MEMORY_OFFLINE) && PageOffline(page))
-			continue;
-
-		if (__PageMovable(page) || PageLRU(page))
-			continue;
-
-		/*
-		 * If there are RECLAIMABLE pages, we need to check
-		 * it.  But now, memory offline itself doesn't call
-		 * shrink_node_slabs() and it still to be fixed.
-		 */
-		return page;
-	}
-	return NULL;
-}
-
 #ifdef CONFIG_CONTIG_ALLOC
 static unsigned long pfn_max_align_down(unsigned long pfn)
 {

mm/page_isolation.c

@@ -15,6 +15,125 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/page_isolation.h>
 
+/*
+ * This function checks whether pageblock includes unmovable pages or not.
+ *
+ * PageLRU check without isolation or lru_lock could race so that
+ * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
+ * check without lock_page also may miss some movable non-lru pages at
+ * race condition. So you can't expect this function should be exact.
+ *
+ * Returns a page without holding a reference. If the caller wants to
+ * dereference that page (e.g., dumping), it has to make sure that it
+ * cannot get removed (e.g., via memory unplug) concurrently.
+ *
+ */
+static struct page *has_unmovable_pages(struct zone *zone, struct page *page,
+				 int migratetype, int flags)
+{
+	unsigned long iter = 0;
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long offset = pfn % pageblock_nr_pages;
+
+	if (is_migrate_cma_page(page)) {
+		/*
+		 * CMA allocations (alloc_contig_range) really need to mark
+		 * isolate CMA pageblocks even when they are not movable in fact
+		 * so consider them movable here.
+		 */
+		if (is_migrate_cma(migratetype))
+			return NULL;
+
+		return page;
+	}
+
+	for (; iter < pageblock_nr_pages - offset; iter++) {
+		page = pfn_to_page(pfn + iter);
+
+		/*
+		 * Both, bootmem allocations and memory holes are marked
+		 * PG_reserved and are unmovable. We can even have unmovable
+		 * allocations inside ZONE_MOVABLE, for example when
+		 * specifying "movablecore".
+		 */
+		if (PageReserved(page))
+			return page;
+
+		/*
+		 * If the zone is movable and we have ruled out all reserved
+		 * pages then it should be reasonably safe to assume the rest
+		 * is movable.
+		 */
+		if (zone_idx(zone) == ZONE_MOVABLE)
+			continue;
+
+		/*
+		 * Hugepages are not in LRU lists, but they're movable.
+		 * THPs are on the LRU, but need to be counted as #small pages.
+		 * We need not scan over tail pages because we don't
+		 * handle each tail page individually in migration.
+		 */
+		if (PageHuge(page) || PageTransCompound(page)) {
+			struct page *head = compound_head(page);
+			unsigned int skip_pages;
+
+			if (PageHuge(page)) {
+				if (!hugepage_migration_supported(page_hstate(head)))
+					return page;
+			} else if (!PageLRU(head) && !__PageMovable(head)) {
+				return page;
+			}
+
+			skip_pages = compound_nr(head) - (page - head);
+			iter += skip_pages - 1;
+			continue;
+		}
+
+		/*
+		 * We can't use page_count without pin a page
+		 * because another CPU can free compound page.
+		 * This check already skips compound tails of THP
+		 * because their page->_refcount is zero at all time.
+		 */
+		if (!page_ref_count(page)) {
+			if (PageBuddy(page))
+				iter += (1 << buddy_order(page)) - 1;
+			continue;
+		}
+
+		/*
+		 * The HWPoisoned page may be not in buddy system, and
+		 * page_count() is not 0.
+		 */
+		if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
+			continue;
+
+		/*
+		 * We treat all PageOffline() pages as movable when offlining
+		 * to give drivers a chance to decrement their reference count
+		 * in MEM_GOING_OFFLINE in order to indicate that these pages
+		 * can be offlined as there are no direct references anymore.
+		 * For actually unmovable PageOffline() where the driver does
+		 * not support this, we will fail later when trying to actually
+		 * move these pages that still have a reference count > 0.
+		 * (false negatives in this function only)
+		 */
+		if ((flags & MEMORY_OFFLINE) && PageOffline(page))
+			continue;
+
+		if (__PageMovable(page) || PageLRU(page))
+			continue;
+
+		/*
+		 * If there are RECLAIMABLE pages, we need to check
+		 * it.  But now, memory offline itself doesn't call
+		 * shrink_node_slabs() and it still to be fixed.
+		 */
+		return page;
+	}
+	return NULL;
+}
+
 static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
 {
 	struct zone *zone = page_zone(page);