[PATCH 07/10] mm: page_alloc: close migratetype race between freeing and stealing

[Johannes Weiner <hannes@cmpxchg.org>]

There are three freeing paths that read the page's migratetype
optimistically before grabbing the zone lock. When this races with
block stealing, those pages go on the wrong freelist.

The paths in question are:
- when freeing >costly orders that aren't THP
- when freeing pages to the buddy upon pcp lock contention
- when freeing pages that are isolated
- when freeing pages initially during boot
- when freeing the remainder in alloc_pages_exact()
- when "accepting" unaccepted VM host memory before first use
- when freeing pages during unpoisoning

None of these are so hot that they would need this optimization at the
cost of hampering defrag efforts. Especially when contrasted with the
fact that the most common buddy freeing path - free_pcppages_bulk - is
checking the migratetype under the zone->lock just fine.

In addition, isolated pages need to look up the migratetype under the
lock anyway, which adds branches to the locked section, and results in
a double lookup when the pages are in fact isolated.

Move the lookups into the lock.

Reported-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 mm/page_alloc.c | 52 ++++++++++++++++++-------------------------------
 1 file changed, 19 insertions(+), 33 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e7d0d4711bdd..3f65b565eaad 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1227,18 +1227,15 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
 
-static void free_one_page(struct zone *zone,
-				struct page *page, unsigned long pfn,
-				unsigned int order,
-				int migratetype, fpi_t fpi_flags)
+static void free_one_page(struct zone *zone, struct page *page,
+			  unsigned long pfn, unsigned int order,
+			  fpi_t fpi_flags)
 {
 	unsigned long flags;
+	int migratetype;
 
 	spin_lock_irqsave(&zone->lock, flags);
-	if (unlikely(has_isolate_pageblock(zone) ||
-		is_migrate_isolate(migratetype))) {
-		migratetype = get_pfnblock_migratetype(page, pfn);
-	}
+	migratetype = get_pfnblock_migratetype(page, pfn);
 	__free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
@@ -1246,21 +1243,13 @@ static void free_one_page(struct zone *zone,
 static void __free_pages_ok(struct page *page, unsigned int order,
 			    fpi_t fpi_flags)
 {
-	int migratetype;
 	unsigned long pfn = page_to_pfn(page);
 	struct zone *zone = page_zone(page);
 
 	if (!free_pages_prepare(page, order))
 		return;
 
-	/*
-	 * Calling get_pfnblock_migratetype() without spin_lock_irqsave() here
-	 * is used to avoid calling get_pfnblock_migratetype() under the lock.
-	 * This will reduce the lock holding time.
-	 */
-	migratetype = get_pfnblock_migratetype(page, pfn);
-
-	free_one_page(zone, page, pfn, order, migratetype, fpi_flags);
+	free_one_page(zone, page, pfn, order, fpi_flags);
 
 	__count_vm_events(PGFREE, 1 << order);
 }
@@ -2533,7 +2522,7 @@ void free_unref_page(struct page *page, unsigned int order)
 	struct per_cpu_pages *pcp;
 	struct zone *zone;
 	unsigned long pfn = page_to_pfn(page);
-	int migratetype, pcpmigratetype;
+	int migratetype;
 
 	if (!free_pages_prepare(page, order))
 		return;
@@ -2545,23 +2534,23 @@ void free_unref_page(struct page *page, unsigned int order)
 	 * get those areas back if necessary. Otherwise, we may have to free
 	 * excessively into the page allocator
 	 */
-	migratetype = pcpmigratetype = get_pfnblock_migratetype(page, pfn);
+	migratetype = get_pfnblock_migratetype(page, pfn);
 	if (unlikely(migratetype >= MIGRATE_PCPTYPES)) {
 		if (unlikely(is_migrate_isolate(migratetype))) {
-			free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE);
+			free_one_page(page_zone(page), page, pfn, order, FPI_NONE);
 			return;
 		}
-		pcpmigratetype = MIGRATE_MOVABLE;
+		migratetype = MIGRATE_MOVABLE;
 	}
 
 	zone = page_zone(page);
 	pcp_trylock_prepare(UP_flags);
 	pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 	if (pcp) {
-		free_unref_page_commit(zone, pcp, page, pcpmigratetype, order);
+		free_unref_page_commit(zone, pcp, page, migratetype, order);
 		pcp_spin_unlock(pcp);
 	} else {
-		free_one_page(zone, page, pfn, order, migratetype, FPI_NONE);
+		free_one_page(zone, page, pfn, order, FPI_NONE);
 	}
 	pcp_trylock_finish(UP_flags);
 }
@@ -2591,12 +2580,8 @@ void free_unref_folios(struct folio_batch *folios)
 		 * allocator.
 		 */
 		if (!pcp_allowed_order(order)) {
-			int migratetype;
-
-			migratetype = get_pfnblock_migratetype(&folio->page,
-							       pfn);
-			free_one_page(folio_zone(folio), &folio->page, pfn,
-					order, migratetype, FPI_NONE);
+			free_one_page(folio_zone(folio), &folio->page,
+				      pfn, order, FPI_NONE);
 			continue;
 		}
 		folio->private = (void *)(unsigned long)order;
@@ -2632,7 +2617,7 @@ void free_unref_folios(struct folio_batch *folios)
 			 */
 			if (is_migrate_isolate(migratetype)) {
 				free_one_page(zone, &folio->page, pfn,
-					      order, migratetype, FPI_NONE);
+					      order, FPI_NONE);
 				continue;
 			}
 
@@ -2645,7 +2630,7 @@ void free_unref_folios(struct folio_batch *folios)
 			if (unlikely(!pcp)) {
 				pcp_trylock_finish(UP_flags);
 				free_one_page(zone, &folio->page, pfn,
-					      order, migratetype, FPI_NONE);
+					      order, FPI_NONE);
 				continue;
 			}
 			locked_zone = zone;
@@ -6823,13 +6808,14 @@ bool take_page_off_buddy(struct page *page)
 bool put_page_back_buddy(struct page *page)
 {
 	struct zone *zone = page_zone(page);
-	unsigned long pfn = page_to_pfn(page);
 	unsigned long flags;
-	int migratetype = get_pfnblock_migratetype(page, pfn);
 	bool ret = false;
 
 	spin_lock_irqsave(&zone->lock, flags);
 	if (put_page_testzero(page)) {
+		unsigned long pfn = page_to_pfn(page);
+		int migratetype = get_pfnblock_migratetype(page, pfn);
+
 		ClearPageHWPoisonTakenOff(page);
 		__free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE);
 		if (TestClearPageHWPoison(page)) {
-- 
2.44.0