[PATCH] hugetlb: force alloc_contig_range hugetlb migrations to allocate new pages

[Mike Kravetz]

When migrating hugetlb pages as the result of an alloc_contig_range
operation, allocate a new page from buddy for the migration target.
This guarantees that the number of hugetlb pages is not decreased by
the operation.  In addition, this will result in the special HPageTemporary
flag being set in the source page so that it will be dissolved when
freed.

Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
---
 include/linux/hugetlb.h |  5 +++--
 mm/hugetlb.c            | 12 ++++++++++--
 mm/internal.h           |  1 +
 mm/migrate.c            |  3 ++-
 mm/page_alloc.c         |  1 +
 5 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index cfe15b32e2d4..558831bf1087 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -702,7 +702,8 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-				nodemask_t *nmask, gfp_t gfp_mask);
+				nodemask_t *nmask, gfp_t gfp_mask,
+				bool temporary);
 struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
 int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping,
@@ -1003,7 +1004,7 @@ static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
 
 static inline struct page *
 alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-			nodemask_t *nmask, gfp_t gfp_mask)
+			nodemask_t *nmask, gfp_t gfp_mask, bool temporary)
 {
 	return NULL;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8bcaf66defc5..19de8ae79ec8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2308,8 +2308,11 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
 
 /* page migration callback function */
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-		nodemask_t *nmask, gfp_t gfp_mask)
+		nodemask_t *nmask, gfp_t gfp_mask, bool temporary)
 {
+	if (temporary)
+		goto temporary_alloc;
+
 	spin_lock_irq(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0) {
 		struct page *page;
@@ -2322,6 +2325,11 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
 	}
 	spin_unlock_irq(&hugetlb_lock);
 
+temporary_alloc:
+	/*
+	 * Try to allocate a fresh page that with special HPageTemporary
+	 * characteristics
+	 */
 	return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask);
 }
 
@@ -2337,7 +2345,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 
 	gfp_mask = htlb_alloc_mask(h);
 	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask);
+	page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask, false);
 	mpol_cond_put(mpol);
 
 	return page;
diff --git a/mm/internal.h b/mm/internal.h
index b3002e03c28f..3ebf8885e24f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -800,6 +800,7 @@ struct migration_target_control {
 	int nid;		/* preferred node id */
 	nodemask_t *nmask;
 	gfp_t gfp_mask;
+	bool alloc_contig;	/* alloc_contig_range allocation */
 };
 
 /*
diff --git a/mm/migrate.c b/mm/migrate.c
index c228afba0963..6505ba2070d7 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1610,7 +1610,8 @@ struct page *alloc_migration_target(struct page *page, unsigned long private)
 		struct hstate *h = page_hstate(&folio->page);
 
 		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
-		return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask);
+		return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask,
+						mtc->alloc_contig);
 	}
 
 	if (folio_test_large(folio)) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d7b20bf09c1c..2b8a5a2b51cd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -9166,6 +9166,7 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 	struct migration_target_control mtc = {
 		.nid = zone_to_nid(cc->zone),
 		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+		.alloc_contig = true,
 	};
 
 	lru_cache_disable();
-- 
2.37.3