1 files changed, 369 insertions, 22 deletions

diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index f67c4c70f17f..c643c8420809 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -15,11 +15,142 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/page_isolation.h>
 
-static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
+/*
+ * This function checks whether the range [start_pfn, end_pfn) includes
+ * unmovable pages or not. The range must fall into a single pageblock and
+ * consequently belong to a single zone.
+ *
+ * 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(unsigned long start_pfn, unsigned long end_pfn,
+				int migratetype, int flags)
+{
+	struct page *page = pfn_to_page(start_pfn);
+	struct zone *zone = page_zone(page);
+	unsigned long pfn;
+
+	VM_BUG_ON(ALIGN_DOWN(start_pfn, pageblock_nr_pages) !=
+		  ALIGN_DOWN(end_pfn - 1, 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 (pfn = start_pfn; pfn < end_pfn; pfn++) {
+		page = pfn_to_page(pfn);
+
+		/*
+		 * 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);
+			pfn += 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))
+				pfn += (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;
+}
+
+/*
+ * This function set pageblock migratetype to isolate if no unmovable page is
+ * present in [start_pfn, end_pfn). The pageblock must intersect with
+ * [start_pfn, end_pfn).
+ */
+static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags,
+			unsigned long start_pfn, unsigned long end_pfn)
 {
 	struct zone *zone = page_zone(page);
 	struct page *unmovable;
 	unsigned long flags;
+	unsigned long check_unmovable_start, check_unmovable_end;
 
 	spin_lock_irqsave(&zone->lock, flags);
 
@@ -36,8 +167,16 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	/*
 	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
 	 * We just check MOVABLE pages.
+	 *
+	 * Pass the intersection of [start_pfn, end_pfn) and the page's pageblock
+	 * to avoid redundant checks.
 	 */
-	unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags);
+	check_unmovable_start = max(page_to_pfn(page), start_pfn);
+	check_unmovable_end = min(ALIGN(page_to_pfn(page) + 1, pageblock_nr_pages),
+				  end_pfn);
+
+	unmovable = has_unmovable_pages(check_unmovable_start, check_unmovable_end,
+			migratetype, isol_flags);
 	if (!unmovable) {
 		unsigned long nr_pages;
 		int mt = get_pageblock_migratetype(page);
@@ -64,13 +203,12 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	return -EBUSY;
 }
 
-static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
+static void unset_migratetype_isolate(struct page *page, int migratetype)
 {
 	struct zone *zone;
 	unsigned long flags, nr_pages;
 	bool isolated_page = false;
 	unsigned int order;
-	unsigned long pfn, buddy_pfn;
 	struct page *buddy;
 
 	zone = page_zone(page);
@@ -89,11 +227,9 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 	if (PageBuddy(page)) {
 		order = buddy_order(page);
 		if (order >= pageblock_order && order < MAX_ORDER - 1) {
-			pfn = page_to_pfn(page);
-			buddy_pfn = __find_buddy_pfn(pfn, order);
-			buddy = page + (buddy_pfn - pfn);
-
-			if (!is_migrate_isolate_page(buddy)) {
+			buddy = find_buddy_page_pfn(page, page_to_pfn(page),
+						    order, NULL);
+			if (buddy && !is_migrate_isolate_page(buddy)) {
 				isolated_page = !!__isolate_free_page(page, order);
 				/*
 				 * Isolating a free page in an isolated pageblock
@@ -144,11 +280,198 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
 }
 
 /**
+ * isolate_single_pageblock() -- tries to isolate a pageblock that might be
+ * within a free or in-use page.
+ * @boundary_pfn:		pageblock-aligned pfn that a page might cross
+ * @flags:			isolation flags
+ * @gfp_flags:			GFP flags used for migrating pages
+ * @isolate_before:	isolate the pageblock before the boundary_pfn
+ *
+ * Free and in-use pages can be as big as MAX_ORDER-1 and contain more than one
+ * pageblock. When not all pageblocks within a page are isolated at the same
+ * time, free page accounting can go wrong. For example, in the case of
+ * MAX_ORDER-1 = pageblock_order + 1, a MAX_ORDER-1 page has two pagelbocks.
+ * [         MAX_ORDER-1         ]
+ * [  pageblock0  |  pageblock1  ]
+ * When either pageblock is isolated, if it is a free page, the page is not
+ * split into separate migratetype lists, which is supposed to; if it is an
+ * in-use page and freed later, __free_one_page() does not split the free page
+ * either. The function handles this by splitting the free page or migrating
+ * the in-use page then splitting the free page.
+ */
+static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
+			gfp_t gfp_flags, bool isolate_before)
+{
+	unsigned char saved_mt;
+	unsigned long start_pfn;
+	unsigned long isolate_pageblock;
+	unsigned long pfn;
+	struct zone *zone;
+	int ret;
+
+	VM_BUG_ON(!IS_ALIGNED(boundary_pfn, pageblock_nr_pages));
+
+	if (isolate_before)
+		isolate_pageblock = boundary_pfn - pageblock_nr_pages;
+	else
+		isolate_pageblock = boundary_pfn;
+
+	/*
+	 * scan at the beginning of MAX_ORDER_NR_PAGES aligned range to avoid
+	 * only isolating a subset of pageblocks from a bigger than pageblock
+	 * free or in-use page. Also make sure all to-be-isolated pageblocks
+	 * are within the same zone.
+	 */
+	zone  = page_zone(pfn_to_page(isolate_pageblock));
+	start_pfn  = max(ALIGN_DOWN(isolate_pageblock, MAX_ORDER_NR_PAGES),
+				      zone->zone_start_pfn);
+
+	saved_mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
+	ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt, flags,
+			isolate_pageblock, isolate_pageblock + pageblock_nr_pages);
+
+	if (ret)
+		return ret;
+
+	/*
+	 * Bail out early when the to-be-isolated pageblock does not form
+	 * a free or in-use page across boundary_pfn:
+	 *
+	 * 1. isolate before boundary_pfn: the page after is not online
+	 * 2. isolate after boundary_pfn: the page before is not online
+	 *
+	 * This also ensures correctness. Without it, when isolate after
+	 * boundary_pfn and [start_pfn, boundary_pfn) are not online,
+	 * __first_valid_page() will return unexpected NULL in the for loop
+	 * below.
+	 */
+	if (isolate_before) {
+		if (!pfn_to_online_page(boundary_pfn))
+			return 0;
+	} else {
+		if (!pfn_to_online_page(boundary_pfn - 1))
+			return 0;
+	}
+
+	for (pfn = start_pfn; pfn < boundary_pfn;) {
+		struct page *page = __first_valid_page(pfn, boundary_pfn - pfn);
+
+		VM_BUG_ON(!page);
+		pfn = page_to_pfn(page);
+		/*
+		 * start_pfn is MAX_ORDER_NR_PAGES aligned, if there is any
+		 * free pages in [start_pfn, boundary_pfn), its head page will
+		 * always be in the range.
+		 */
+		if (PageBuddy(page)) {
+			int order = buddy_order(page);
+
+			if (pfn + (1UL << order) > boundary_pfn)
+				split_free_page(page, order, boundary_pfn - pfn);
+			pfn += (1UL << order);
+			continue;
+		}
+		/*
+		 * migrate compound pages then let the free page handling code
+		 * above do the rest. If migration is not possible, just fail.
+		 */
+		if (PageCompound(page)) {
+			unsigned long nr_pages = compound_nr(page);
+			struct page *head = compound_head(page);
+			unsigned long head_pfn = page_to_pfn(head);
+
+			if (head_pfn + nr_pages <= boundary_pfn) {
+				pfn = head_pfn + nr_pages;
+				continue;
+			}
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+			/*
+			 * hugetlb, lru compound (THP), and movable compound pages
+			 * can be migrated. Otherwise, fail the isolation.
+			 */
+			if (PageHuge(page) || PageLRU(page) || __PageMovable(page)) {
+				int order;
+				unsigned long outer_pfn;
+				int page_mt = get_pageblock_migratetype(page);
+				bool isolate_page = !is_migrate_isolate_page(page);
+				struct compact_control cc = {
+					.nr_migratepages = 0,
+					.order = -1,
+					.zone = page_zone(pfn_to_page(head_pfn)),
+					.mode = MIGRATE_SYNC,
+					.ignore_skip_hint = true,
+					.no_set_skip_hint = true,
+					.gfp_mask = gfp_flags,
+					.alloc_contig = true,
+				};
+				INIT_LIST_HEAD(&cc.migratepages);
+
+				/*
+				 * XXX: mark the page as MIGRATE_ISOLATE so that
+				 * no one else can grab the freed page after migration.
+				 * Ideally, the page should be freed as two separate
+				 * pages to be added into separate migratetype free
+				 * lists.
+				 */
+				if (isolate_page) {
+					ret = set_migratetype_isolate(page, page_mt,
+						flags, head_pfn, head_pfn + nr_pages);
+					if (ret)
+						goto failed;
+				}
+
+				ret = __alloc_contig_migrate_range(&cc, head_pfn,
+							head_pfn + nr_pages);
+
+				/*
+				 * restore the page's migratetype so that it can
+				 * be split into separate migratetype free lists
+				 * later.
+				 */
+				if (isolate_page)
+					unset_migratetype_isolate(page, page_mt);
+
+				if (ret)
+					goto failed;
+				/*
+				 * reset pfn to the head of the free page, so
+				 * that the free page handling code above can split
+				 * the free page to the right migratetype list.
+				 *
+				 * head_pfn is not used here as a hugetlb page order
+				 * can be bigger than MAX_ORDER-1, but after it is
+				 * freed, the free page order is not. Use pfn within
+				 * the range to find the head of the free page.
+				 */
+				order = 0;
+				outer_pfn = pfn;
+				while (!PageBuddy(pfn_to_page(outer_pfn))) {
+					/* stop if we cannot find the free page */
+					if (++order >= MAX_ORDER)
+						goto failed;
+					outer_pfn &= ~0UL << order;
+				}
+				pfn = outer_pfn;
+				continue;
+			} else
+#endif
+				goto failed;
+		}
+
+		pfn++;
+	}
+	return 0;
+failed:
+	/* restore the original migratetype */
+	unset_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt);
+	return -EBUSY;
+}
+
+/**
  * start_isolate_page_range() - make page-allocation-type of range of pages to
  * be MIGRATE_ISOLATE.
  * @start_pfn:		The lower PFN of the range to be isolated.
  * @end_pfn:		The upper PFN of the range to be isolated.
- *			start_pfn/end_pfn must be aligned to pageblock_order.
  * @migratetype:	Migrate type to set in error recovery.
  * @flags:		The following flags are allowed (they can be combined in
  *			a bit mask)
@@ -157,6 +480,8 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  *					 and PageOffline() pages.
  *			REPORT_FAILURE - report details about the failure to
  *			isolate the range
+ * @gfp_flags:		GFP flags used for migrating pages that sit across the
+ *			range boundaries.
  *
  * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
  * the range will never be allocated. Any free pages and pages freed in the
@@ -165,6 +490,10 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * pages in the range finally, the caller have to free all pages in the range.
  * test_page_isolated() can be used for test it.
  *
+ * The function first tries to isolate the pageblocks at the beginning and end
+ * of the range, since there might be pages across the range boundaries.
+ * Afterwards, it isolates the rest of the range.
+ *
  * There is no high level synchronization mechanism that prevents two threads
  * from trying to isolate overlapping ranges. If this happens, one thread
  * will notice pageblocks in the overlapping range already set to isolate.
@@ -185,20 +514,38 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * Return: 0 on success and -EBUSY if any part of range cannot be isolated.
  */
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     unsigned migratetype, int flags)
+			     int migratetype, int flags, gfp_t gfp_flags)
 {
 	unsigned long pfn;
 	struct page *page;
+	/* isolation is done at page block granularity */
+	unsigned long isolate_start = ALIGN_DOWN(start_pfn, pageblock_nr_pages);
+	unsigned long isolate_end = ALIGN(end_pfn, pageblock_nr_pages);
+	int ret;
+
+	/* isolate [isolate_start, isolate_start + pageblock_nr_pages) pageblock */
+	ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false);
+	if (ret)
+		return ret;
 
-	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
-	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
+	/* isolate [isolate_end - pageblock_nr_pages, isolate_end) pageblock */
+	ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true);
+	if (ret) {
+		unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype);
+		return ret;
+	}
 
-	for (pfn = start_pfn;
-	     pfn < end_pfn;
+	/* skip isolated pageblocks at the beginning and end */
+	for (pfn = isolate_start + pageblock_nr_pages;
+	     pfn < isolate_end - pageblock_nr_pages;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
-		if (page && set_migratetype_isolate(page, migratetype, flags)) {
-			undo_isolate_page_range(start_pfn, pfn, migratetype);
+		if (page && set_migratetype_isolate(page, migratetype, flags,
+					start_pfn, end_pfn)) {
+			undo_isolate_page_range(isolate_start, pfn, migratetype);
+			unset_migratetype_isolate(
+				pfn_to_page(isolate_end - pageblock_nr_pages),
+				migratetype);
 			return -EBUSY;
 		}
 	}
@@ -209,16 +556,16 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  * Make isolated pages available again.
  */
 void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			    unsigned migratetype)
+			    int migratetype)
 {
 	unsigned long pfn;
 	struct page *page;
+	unsigned long isolate_start = ALIGN_DOWN(start_pfn, pageblock_nr_pages);
+	unsigned long isolate_end = ALIGN(end_pfn, pageblock_nr_pages);
 
-	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
-	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
 
-	for (pfn = start_pfn;
-	     pfn < end_pfn;
+	for (pfn = isolate_start;
+	     pfn < isolate_end;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
 		if (!page || !is_migrate_isolate_page(page))