+ mm-compaction-add-support-for-0-order-folio-memory-compaction.patch added to mm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: mm/compaction: add support for >0 order folio memory compaction.
has been added to the -mm mm-unstable branch.  Its filename is
     mm-compaction-add-support-for-0-order-folio-memory-compaction.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-compaction-add-support-for-0-order-folio-memory-compaction.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Zi Yan <ziy@nvidia.com>
Subject: mm/compaction: add support for >0 order folio memory compaction.
Date: Mon, 22 Jan 2024 22:46:34 -0500

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/20240123034636.1095672-3-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.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>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/compaction.c |  148 +++++++++++++++++++++++++++-------------------
 mm/internal.h   |    9 ++
 mm/page_alloc.c |    6 +
 3 files changed, 103 insertions(+), 60 deletions(-)

--- a/mm/compaction.c~mm-compaction-add-support-for-0-order-folio-memory-compaction
+++ a/mm/compaction.c
@@ -66,45 +66,67 @@ static inline void count_compact_events(
 #define COMPACTION_HPAGE_ORDER	(PMD_SHIFT - PAGE_SHIFT)
 #endif
 
-static unsigned long release_freepages(struct list_head *freelist)
+static void init_page_list(struct page_list *p)
 {
-	struct page *page, *next;
-	unsigned long high_pfn = 0;
-
-	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;
-	}
-
-	return high_pfn;
+	INIT_LIST_HEAD(&p->pages);
+	p->nr_pages = 0;
 }
 
-static void split_map_pages(struct list_head *list)
+static void split_map_pages(struct page_list *freepages)
 {
-	unsigned int i, order, nr_pages;
+	unsigned int i, order, total_nr_pages;
 	struct page *page, *next;
 	LIST_HEAD(tmp_list);
 
-	list_for_each_entry_safe(page, next, list, lru) {
-		list_del(&page->lru);
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
+		total_nr_pages = freepages[order].nr_pages * (1 << order);
+		freepages[order].nr_pages = 0;
+
+		list_for_each_entry_safe(page, next, &freepages[order].pages, lru) {
+			unsigned int nr_pages;
+
+			list_del(&page->lru);
 
-		order = page_private(page);
-		nr_pages = 1 << order;
+			nr_pages = 1 << order;
 
-		post_alloc_hook(page, order, __GFP_MOVABLE);
-		if (order)
-			split_page(page, 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++;
+			for (i = 0; i < nr_pages; i++) {
+				list_add(&page->lru, &tmp_list);
+				page++;
+			}
 		}
+		freepages[0].nr_pages += total_nr_pages;
+		list_splice_init(&tmp_list, &freepages[0].pages);
 	}
+}
 
-	list_splice(&tmp_list, list);
+static unsigned long release_free_list(struct page_list *freepages)
+{
+	int order;
+	unsigned long high_pfn = 0;
+
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
+		struct page *page, *next;
+
+		list_for_each_entry_safe(page, next, &freepages[order].pages, lru) {
+			unsigned long pfn = page_to_pfn(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;
+		}
+		freepages[order].nr_pages = 0;
+	}
+	return high_pfn;
 }
 
 #ifdef CONFIG_COMPACTION
@@ -583,7 +605,7 @@ static bool compact_unlock_should_abort(
 static unsigned long isolate_freepages_block(struct compact_control *cc,
 				unsigned long *start_pfn,
 				unsigned long end_pfn,
-				struct list_head *freelist,
+				struct page_list *freelist,
 				unsigned int stride,
 				bool strict)
 {
@@ -657,7 +679,8 @@ static unsigned long isolate_freepages_b
 		nr_scanned += isolated - 1;
 		total_isolated += isolated;
 		cc->nr_freepages += isolated;
-		list_add_tail(&page->lru, freelist);
+		list_add_tail(&page->lru, &freelist[order].pages);
+		freelist[order].nr_pages++;
 
 		if (!strict && cc->nr_migratepages <= cc->nr_freepages) {
 			blockpfn += isolated;
@@ -722,7 +745,11 @@ isolate_freepages_range(struct compact_c
 			unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long isolated, pfn, block_start_pfn, block_end_pfn;
-	LIST_HEAD(freelist);
+	int order;
+	struct page_list tmp_freepages[NR_PAGE_ORDERS];
+
+	for (order = 0; order < NR_PAGE_ORDERS; order++)
+		init_page_list(&tmp_freepages[order]);
 
 	pfn = start_pfn;
 	block_start_pfn = pageblock_start_pfn(pfn);
@@ -753,7 +780,7 @@ isolate_freepages_range(struct compact_c
 			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
@@ -770,15 +797,15 @@ isolate_freepages_range(struct compact_c
 		 */
 	}
 
-	/* __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;
 }
@@ -1481,7 +1508,7 @@ fast_isolate_around(struct compact_contr
 	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)
@@ -1610,7 +1637,7 @@ static void fast_isolate_freepages(struc
 				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].pages);
 				count_compact_events(COMPACTISOLATED, nr_isolated);
 			} else {
 				/* If isolation fails, abort the search */
@@ -1687,13 +1714,12 @@ static void isolate_freepages(struct com
 	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
@@ -1753,7 +1779,7 @@ static void isolate_freepages(struct com
 
 		/* 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)
@@ -1794,10 +1820,6 @@ static void isolate_freepages(struct com
 	 * 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);
 }
 
 /*
@@ -1808,23 +1830,22 @@ static struct folio *compaction_alloc(st
 {
 	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) > 0)
-		return NULL;
-
-	if (list_empty(&cc->freepages)) {
+	if (!cc->freepages[order].nr_pages) {
 		isolate_freepages(cc);
-
-		if (list_empty(&cc->freepages))
+		if (!cc->freepages[order].nr_pages)
 			return NULL;
 	}
 
-	dst = list_entry(cc->freepages.next, struct folio, lru);
+	dst = list_first_entry(&cc->freepages[order].pages, struct folio, lru);
+	cc->freepages[order].nr_pages--;
 	list_del(&dst->lru);
-	cc->nr_freepages--;
-
-	return dst;
+	post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
+	if (order)
+		prep_compound_page(&dst->page, order);
+	cc->nr_freepages -= 1 << order;
+	return page_rmappable_folio(&dst->page);
 }
 
 /*
@@ -1835,9 +1856,17 @@ static struct folio *compaction_alloc(st
 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;
+
+	folio_set_count(dst, 0);
+	free_pages_prepare_fpi_none(page, order);
 
-	list_add(&dst->lru, &cc->freepages);
-	cc->nr_freepages++;
+	INIT_LIST_HEAD(&dst->lru);
+
+	list_add(&dst->lru, &cc->freepages[order].pages);
+	cc->freepages[order].nr_pages++;
+	cc->nr_freepages += 1 << order;
 }
 
 /* possible outcome of isolate_migratepages */
@@ -2461,6 +2490,7 @@ compact_zone(struct compact_control *cc,
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 	bool update_cached;
 	unsigned int nr_succeeded = 0;
+	int order;
 
 	/*
 	 * These counters track activities during zone compaction.  Initialize
@@ -2470,7 +2500,8 @@ compact_zone(struct compact_control *cc,
 	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_page_list(&cc->freepages[order]);
 	INIT_LIST_HEAD(&cc->migratepages);
 
 	cc->migratetype = gfp_migratetype(cc->gfp_mask);
@@ -2656,7 +2687,7 @@ 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);
@@ -2675,7 +2706,6 @@ 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;
--- a/mm/internal.h~mm-compaction-add-support-for-0-order-folio-memory-compaction
+++ a/mm/internal.h
@@ -447,6 +447,8 @@ extern void prep_compound_page(struct pa
 
 extern void post_alloc_hook(struct page *page, unsigned int order,
 					gfp_t gfp_flags);
+extern bool free_pages_prepare_fpi_none(struct page *page, unsigned int order);
+
 extern int user_min_free_kbytes;
 
 extern void free_unref_page(struct page *page, unsigned int order);
@@ -473,6 +475,11 @@ int split_free_page(struct page *free_pa
 /*
  * in mm/compaction.c
  */
+
+struct page_list {
+	struct list_head	pages;
+	unsigned long		nr_pages;
+};
 /*
  * compact_control is used to track pages being migrated and the free pages
  * they are being migrated to during memory compaction. The free_pfn starts
@@ -481,7 +488,7 @@ int split_free_page(struct page *free_pa
  * completes when free_pfn <= migrate_pfn
  */
 struct compact_control {
-	struct list_head freepages;	/* List of free pages to migrate to */
+	struct page_list 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 */
--- a/mm/page_alloc.c~mm-compaction-add-support-for-0-order-folio-memory-compaction
+++ a/mm/page_alloc.c
@@ -1179,6 +1179,12 @@ static __always_inline bool free_pages_p
 	return true;
 }
 
+__always_inline bool free_pages_prepare_fpi_none(struct page *page,
+			unsigned int order)
+{
+	return free_pages_prepare(page, order, FPI_NONE);
+}
+
 /*
  * Frees a number of pages from the PCP lists
  * Assumes all pages on list are in same zone.
_

Patches currently in -mm which might be from ziy@nvidia.com are

mm-compaction-enable-compacting-0-order-folios.patch
mm-compaction-add-support-for-0-order-folio-memory-compaction.patch
mm-compaction-optimize-0-order-folio-compaction-with-free-page-split.patch