mm: make alloc_contig_range work at pageblock granularity

alloc_contig_range() worked at MAX_ORDER_NR_PAGES granularity to avoid
merging pageblocks with different migratetypes.  It might unnecessarily
convert extra pageblocks at the beginning and at the end of the range. 
Change alloc_contig_range() to work at pageblock granularity.

Special handling is needed for free pages and in-use pages across the
boundaries of the range specified by alloc_contig_range().  Because these=

Partially isolated pages causes free page accounting issues.  The free
pages will be split and freed into separate migratetype lists; the in-use=

Pages will be migrated then the freed pages will be handled in the
aforementioned way.

[ziy@nvidia.com: fix deadlock/crash]
  Link: https://lkml.kernel.org/r/23A7297E-6C84-4138-A9FE-3598234004E6@nvidia.com
Link: https://lkml.kernel.org/r/20220425143118.2850746-4-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Eric Ren <renzhengeek@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 44 insertions, 10 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0756f046b644..0c7252ed14a0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1094,6 +1094,43 @@ done_merging:
 		page_reporting_notify_free(order);
 }
 
+/**
+ * split_free_page() -- split a free page at split_pfn_offset
+ * @free_page:		the original free page
+ * @order:		the order of the page
+ * @split_pfn_offset:	split offset within the page
+ *
+ * It is used when the free page crosses two pageblocks with different migratetypes
+ * at split_pfn_offset within the page. The split free page will be put into
+ * separate migratetype lists afterwards. Otherwise, the function achieves
+ * nothing.
+ */
+void split_free_page(struct page *free_page,
+				int order, unsigned long split_pfn_offset)
+{
+	struct zone *zone = page_zone(free_page);
+	unsigned long free_page_pfn = page_to_pfn(free_page);
+	unsigned long pfn;
+	unsigned long flags;
+	int free_page_order;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	del_page_from_free_list(free_page, zone, order);
+	for (pfn = free_page_pfn;
+	     pfn < free_page_pfn + (1UL << order);) {
+		int mt = get_pfnblock_migratetype(pfn_to_page(pfn), pfn);
+
+		free_page_order = ffs(split_pfn_offset) - 1;
+		__free_one_page(pfn_to_page(pfn), pfn, zone, free_page_order,
+				mt, FPI_NONE);
+		pfn += 1UL << free_page_order;
+		split_pfn_offset -= (1UL << free_page_order);
+		/* we have done the first part, now switch to second part */
+		if (split_pfn_offset == 0)
+			split_pfn_offset = (1UL << order) - (pfn - free_page_pfn);
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+}
 /*
  * A bad page could be due to a number of fields. Instead of multiple branches,
  * try and check multiple fields with one check. The caller must do a detailed
@@ -8951,7 +8988,7 @@ static inline void alloc_contig_dump_pages(struct list_head *page_list)
 #endif
 
 /* [start, end) must belong to a single zone. */
-static int __alloc_contig_migrate_range(struct compact_control *cc,
+int __alloc_contig_migrate_range(struct compact_control *cc,
 					unsigned long start, unsigned long end)
 {
 	/* This function is based on compact_zone() from compaction.c. */
@@ -9034,7 +9071,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		       unsigned migratetype, gfp_t gfp_mask)
 {
 	unsigned long outer_start, outer_end;
-	unsigned int order;
+	int order;
 	int ret = 0;
 
 	struct compact_control cc = {
@@ -9053,14 +9090,11 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 * What we do here is we mark all pageblocks in range as
 	 * MIGRATE_ISOLATE.  Because pageblock and max order pages may
 	 * have different sizes, and due to the way page allocator
-	 * work, we align the range to biggest of the two pages so
-	 * that page allocator won't try to merge buddies from
-	 * different pageblocks and change MIGRATE_ISOLATE to some
-	 * other migration type.
+	 * work, start_isolate_page_range() has special handlings for this.
 	 *
 	 * Once the pageblocks are marked as MIGRATE_ISOLATE, we
 	 * migrate the pages from an unaligned range (ie. pages that
-	 * we are interested in).  This will put all the pages in
+	 * we are interested in). This will put all the pages in
 	 * range back to page allocator as MIGRATE_ISOLATE.
 	 *
 	 * When this is done, we take the pages in range from page
@@ -9074,9 +9108,9 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 */
 
 	ret = start_isolate_page_range(pfn_max_align_down(start),
-				       pfn_max_align_up(end), migratetype, 0);
+				pfn_max_align_up(end), migratetype, 0, gfp_mask);
 	if (ret)
-		return ret;
+		goto done;
 
 	drain_all_pages(cc.zone);
 
@@ -9096,7 +9130,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	ret = 0;
 
 	/*
-	 * Pages from [start, end) are within a MAX_ORDER_NR_PAGES
+	 * Pages from [start, end) are within a pageblock_nr_pages
 	 * aligned blocks that are marked as MIGRATE_ISOLATE.  What's
 	 * more, all pages in [start, end) are free in page allocator.
 	 * What we are going to do is to allocate all pages from