mm/compaction: add support for >0 order folio memory compaction.

Before last commit, memory compaction only migrates order-0 folios and
skips >0 order folios.  Last commit splits all >0 order folios during
compaction.  This commit migrates >0 order folios during compaction by
keeping isolated free pages at their original size without splitting them
into order-0 pages and using them directly during migration process.

What is different from the prior implementation:
1. All isolated free pages are kept in a NR_PAGE_ORDERS array of page
   lists, where each page list stores free pages in the same order.
2. All free pages are not post_alloc_hook() processed nor buddy pages,
   although their orders are stored in first page's private like buddy
   pages.
3. During migration, in new page allocation time (i.e., in
   compaction_alloc()), free pages are then processed by post_alloc_hook().
   When migration fails and a new page is returned (i.e., in
   compaction_free()), free pages are restored by reversing the
   post_alloc_hook() operations using newly added
   free_pages_prepare_fpi_none().

Step 3 is done for a latter optimization that splitting and/or merging
free pages during compaction becomes easier.

Note: without splitting free pages, compaction can end prematurely due to
migration will return -ENOMEM even if there is free pages.  This happens
when no order-0 free page exist and compaction_alloc() return NULL.

Link: https://lkml.kernel.org/r/20240220183220.1451315-4-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Yu Zhao <yuzhao@google.com>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 83 insertions, 63 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 2ba9ba49b0e9ff..61b2c731c9db94 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -79,45 +79,56 @@ static inline bool is_via_compact_memory(int order) { return false; }
 #define COMPACTION_HPAGE_ORDER	(PMD_SHIFT - PAGE_SHIFT)
 #endif
 
-static unsigned long release_freepages(struct list_head *freelist)
+static void split_map_pages(struct list_head *freepages)
 {
+	unsigned int i, order;
 	struct page *page, *next;
-	unsigned long high_pfn = 0;
+	LIST_HEAD(tmp_list);
 
-	list_for_each_entry_safe(page, next, freelist, lru) {
-		unsigned long pfn = page_to_pfn(page);
-		list_del(&page->lru);
-		__free_page(page);
-		if (pfn > high_pfn)
-			high_pfn = pfn;
-	}
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
+		list_for_each_entry_safe(page, next, &freepages[order], lru) {
+			unsigned int nr_pages;
 
-	return high_pfn;
+			list_del(&page->lru);
+
+			nr_pages = 1 << order;
+
+			post_alloc_hook(page, order, __GFP_MOVABLE);
+			if (order)
+				split_page(page, order);
+
+			for (i = 0; i < nr_pages; i++) {
+				list_add(&page->lru, &tmp_list);
+				page++;
+			}
+		}
+		list_splice_init(&tmp_list, &freepages[0]);
+	}
 }
 
-static void split_map_pages(struct list_head *list)
+static unsigned long release_free_list(struct list_head *freepages)
 {
-	unsigned int i, order, nr_pages;
-	struct page *page, *next;
-	LIST_HEAD(tmp_list);
-
-	list_for_each_entry_safe(page, next, list, lru) {
-		list_del(&page->lru);
+	int order;
+	unsigned long high_pfn = 0;
 
-		order = page_private(page);
-		nr_pages = 1 << order;
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
+		struct page *page, *next;
 
-		post_alloc_hook(page, order, __GFP_MOVABLE);
-		if (order)
-			split_page(page, order);
+		list_for_each_entry_safe(page, next, &freepages[order], lru) {
+			unsigned long pfn = page_to_pfn(page);
 
-		for (i = 0; i < nr_pages; i++) {
-			list_add(&page->lru, &tmp_list);
-			page++;
+			list_del(&page->lru);
+			/*
+			 * Convert free pages into post allocation pages, so
+			 * that we can free them via __free_page.
+			 */
+			post_alloc_hook(page, order, __GFP_MOVABLE);
+			__free_pages(page, order);
+			if (pfn > high_pfn)
+				high_pfn = pfn;
 		}
 	}
-
-	list_splice(&tmp_list, list);
+	return high_pfn;
 }
 
 #ifdef CONFIG_COMPACTION
@@ -670,7 +681,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		nr_scanned += isolated - 1;
 		total_isolated += isolated;
 		cc->nr_freepages += isolated;
-		list_add_tail(&page->lru, freelist);
+		list_add_tail(&page->lru, &freelist[order]);
 
 		if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
 			blockpfn += isolated;
@@ -735,7 +746,11 @@ isolate_freepages_range(struct compact_control *cc,
 			unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long isolated, pfn, block_start_pfn, block_end_pfn;
-	LIST_HEAD(freelist);
+	int order;
+	struct list_head tmp_freepages[NR_PAGE_ORDERS];
+
+	for (order = 0; order < NR_PAGE_ORDERS; order++)
+		INIT_LIST_HEAD(&tmp_freepages[order]);
 
 	pfn = start_pfn;
 	block_start_pfn = pageblock_start_pfn(pfn);
@@ -766,7 +781,7 @@ isolate_freepages_range(struct compact_control *cc,
 			break;
 
 		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
-					block_end_pfn, &freelist, 0, true);
+					block_end_pfn, tmp_freepages, 0, true);
 
 		/*
 		 * In strict mode, isolate_freepages_block() returns 0 if
@@ -783,15 +798,15 @@ isolate_freepages_range(struct compact_control *cc,
 		 */
 	}
 
-	/* __isolate_free_page() does not map the pages */
-	split_map_pages(&freelist);
-
 	if (pfn < end_pfn) {
 		/* Loop terminated early, cleanup. */
-		release_freepages(&freelist);
+		release_free_list(tmp_freepages);
 		return 0;
 	}
 
+	/* __isolate_free_page() does not map the pages */
+	split_map_pages(tmp_freepages);
+
 	/* We don't use freelists for anything. */
 	return pfn;
 }
@@ -1518,7 +1533,7 @@ fast_isolate_around(struct compact_control *cc, unsigned long pfn)
 	if (!page)
 		return;
 
-	isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false);
+	isolate_freepages_block(cc, &start_pfn, end_pfn, cc->freepages, 1, false);
 
 	/* Skip this pageblock in the future as it's full or nearly full */
 	if (start_pfn == end_pfn && !cc->no_set_skip_hint)
@@ -1647,7 +1662,7 @@ static void fast_isolate_freepages(struct compact_control *cc)
 				nr_scanned += nr_isolated - 1;
 				total_isolated += nr_isolated;
 				cc->nr_freepages += nr_isolated;
-				list_add_tail(&page->lru, &cc->freepages);
+				list_add_tail(&page->lru, &cc->freepages[order]);
 				count_compact_events(COMPACTISOLATED, nr_isolated);
 			} else {
 				/* If isolation fails, abort the search */
@@ -1724,13 +1739,12 @@ static void isolate_freepages(struct compact_control *cc)
 	unsigned long isolate_start_pfn; /* exact pfn we start at */
 	unsigned long block_end_pfn;	/* end of current pageblock */
 	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
-	struct list_head *freelist = &cc->freepages;
 	unsigned int stride;
 
 	/* Try a small search of the free lists for a candidate */
 	fast_isolate_freepages(cc);
 	if (cc->nr_freepages)
-		goto splitmap;
+		return;
 
 	/*
 	 * Initialise the free scanner. The starting point is where we last
@@ -1790,7 +1804,7 @@ static void isolate_freepages(struct compact_control *cc)
 
 		/* Found a block suitable for isolating free pages from. */
 		nr_isolated = isolate_freepages_block(cc, &isolate_start_pfn,
-					block_end_pfn, freelist, stride, false);
+					block_end_pfn, cc->freepages, stride, false);
 
 		/* Update the skip hint if the full pageblock was scanned */
 		if (isolate_start_pfn == block_end_pfn)
@@ -1831,10 +1845,6 @@ static void isolate_freepages(struct compact_control *cc)
 	 * and the loop terminated due to isolate_start_pfn < low_pfn
 	 */
 	cc->free_pfn = isolate_start_pfn;
-
-splitmap:
-	/* __isolate_free_page() does not map the pages */
-	split_map_pages(freelist);
 }
 
 /*
@@ -1845,24 +1855,22 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
 {
 	struct compact_control *cc = (struct compact_control *)data;
 	struct folio *dst;
+	int order = folio_order(src);
 
-	/* this makes migrate_pages() split the source page and retry */
-	if (folio_test_large(src))
-		return NULL;
-
-	if (list_empty(&cc->freepages)) {
+	if (list_empty(&cc->freepages[order])) {
 		isolate_freepages(cc);
-
-		if (list_empty(&cc->freepages))
+		if (list_empty(&cc->freepages[order]))
 			return NULL;
 	}
 
-	dst = list_entry(cc->freepages.next, struct folio, lru);
+	dst = list_first_entry(&cc->freepages[order], struct folio, lru);
 	list_del(&dst->lru);
-	cc->nr_freepages--;
-	cc->nr_migratepages--;
-
-	return dst;
+	post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
+	if (order)
+		prep_compound_page(&dst->page, order);
+	cc->nr_freepages -= 1 << order;
+	cc->nr_migratepages -= 1 << order;
+	return page_rmappable_folio(&dst->page);
 }
 
 /*
@@ -1873,10 +1881,19 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
 static void compaction_free(struct folio *dst, unsigned long data)
 {
 	struct compact_control *cc = (struct compact_control *)data;
+	int order = folio_order(dst);
+	struct page *page = &dst->page;
 
-	list_add(&dst->lru, &cc->freepages);
-	cc->nr_freepages++;
-	cc->nr_migratepages++;
+	if (folio_put_testzero(dst)) {
+		free_pages_prepare(page, order);
+		list_add(&dst->lru, &cc->freepages[order]);
+		cc->nr_freepages += 1 << order;
+	}
+	cc->nr_migratepages += 1 << order;
+	/*
+	 * someone else has referenced the page, we cannot take it back to our
+	 * free list.
+	 */
 }
 
 /* possible outcome of isolate_migratepages */
@@ -2489,6 +2506,7 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 	bool update_cached;
 	unsigned int nr_succeeded = 0, nr_migratepages;
+	int order;
 
 	/*
 	 * These counters track activities during zone compaction.  Initialize
@@ -2498,7 +2516,8 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
 	cc->total_free_scanned = 0;
 	cc->nr_migratepages = 0;
 	cc->nr_freepages = 0;
-	INIT_LIST_HEAD(&cc->freepages);
+	for (order = 0; order < NR_PAGE_ORDERS; order++)
+		INIT_LIST_HEAD(&cc->freepages[order]);
 	INIT_LIST_HEAD(&cc->migratepages);
 
 	cc->migratetype = gfp_migratetype(cc->gfp_mask);
@@ -2690,7 +2709,7 @@ out:
 	 * so we don't leave any returned pages behind in the next attempt.
 	 */
 	if (cc->nr_freepages > 0) {
-		unsigned long free_pfn = release_freepages(&cc->freepages);
+		unsigned long free_pfn = release_free_list(cc->freepages);
 
 		cc->nr_freepages = 0;
 		VM_BUG_ON(free_pfn == 0);
@@ -2709,7 +2728,6 @@ out:
 
 	trace_mm_compaction_end(cc, start_pfn, end_pfn, sync, ret);
 
-	VM_BUG_ON(!list_empty(&cc->freepages));
 	VM_BUG_ON(!list_empty(&cc->migratepages));
 
 	return ret;
diff --git a/mm/internal.h b/mm/internal.h
index 1e29c5821a1dde..93e2291120452d 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -447,6 +447,8 @@ extern void prep_compound_page(struct page *page, unsigned int order);
 
 extern void post_alloc_hook(struct page *page, unsigned int order,
 					gfp_t gfp_flags);
+extern bool free_pages_prepare(struct page *page, unsigned int order);
+
 extern int user_min_free_kbytes;
 
 extern void free_unref_page(struct page *page, unsigned int order);
@@ -481,7 +483,7 @@ int split_free_page(struct page *free_page,
  * completes when free_pfn <= migrate_pfn
  */
 struct compact_control {
-	struct list_head freepages;	/* List of free pages to migrate to */
+	struct list_head freepages[NR_PAGE_ORDERS];	/* List of free pages to migrate to */
 	struct list_head migratepages;	/* List of pages being migrated */
 	unsigned int nr_freepages;	/* Number of isolated free pages */
 	unsigned int nr_migratepages;	/* Number of pages to migrate */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index dc59fb225cbf5c..51e13aa605ecbd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1080,7 +1080,7 @@ static void kernel_init_pages(struct page *page, int numpages)
 	kasan_enable_current();
 }
 
-static __always_inline bool free_pages_prepare(struct page *page,
+__always_inline bool free_pages_prepare(struct page *page,
 			unsigned int order)
 {
 	int bad = 0;